KR102568930B1 - Method for generating new speech based on stt result - Google Patents

Abstract

The present disclosure, as a method for generating a speech performed by a computing device, may comprise: a step of obtaining text information generated by speech recognition; a step of identifying a text part wherein a change among the text information has occurred; a step of identifying a speech part corresponding to the identified text part among speech information utilized for the speech recognition; a step of changing the speech part associated with the identified speech part; and a step of generating new speech information based on the changed voice part and remaining voice parts of the speech information. Therefore, the present invention is capable of generating a natural speech.

Description

Method for generating a new voice based on STT results {METHOD FOR GENERATING NEW SPEECH BASED ON STT RESULT}

The present invention relates to a method for generating a voice, and more particularly, to a technique for generating a new voice based on a change generated in text as a result of speech recognition (STT).

In the field of Speech-to-Text (STT) technology, it is important that semantically important parts of speech during speech are accurately converted into text, while real people speak in an unorganized or unrefined form than expected. When transcribed through speech-to-text (STT), you can write short sentences (e.g., ah, uh, this, me, that, ...) or unimportant words (e.g., now, so, .. .), etc. may be included. Since the STT (Speech-to-Text) result may include simplistic and unimportant words, the user may not be satisfied with reading the dictation result or listening to the recorded voice. For usability, you may want to delete or trim unnecessary parts such as punctuation in the dictation result.

Currently, there are many technologies for speech recognition (STT; Speech-to-Text) or text-to-speech synthesis (TTS; Text-to-Speech) itself, but changes in text as a result of speech recognition (STT; Speech-to-Text) may occur. In case (eg, when the STT result text is edited by user input, etc.), there is a lack of technology for synthesizing (generating) a new voice through text-to-speech (TTS) based on this.

Korean Patent Publication No. 10-2021-0014526 (2021.02.09) discloses a server, terminal, and method for providing a voice synthesis service.

An object of the present disclosure is to generate and provide new voice information corresponding to the changed text portion when a change such as deletion, correction, or addition occurs in text information generated by voice recognition.

On the other hand, the technical problem to be achieved by the present disclosure is not limited to the above-mentioned technical problem, and may include various technical problems within a range apparent to those skilled in the art from the contents to be described below.

A method performed by a computing device according to an embodiment of the present disclosure for realizing the above object is disclosed. The method may include obtaining text information generated by voice recognition; identifying a text portion where a change occurs among the text information; identifying a voice portion corresponding to the identified text portion among voice information used for voice recognition; changing a speech portion associated with the identified speech portion; and generating new voice information based on the changed voice portion and the remaining voice portions of the voice information.

In one embodiment, the change to the text information may include deleting a text portion included in the text information; modifying a text portion included in the text information; or adding a new text part to the text information.

In one embodiment, when the change to the text information is to delete a text part included in the text information, the changing may include deleting an audio part corresponding to the deleted text part. there is.

In one embodiment, when the change to the text information is to modify a text part included in the text information, the changing step considers an audio part adjacent to an audio part corresponding to the modified text part, and modifying an audio portion corresponding to the modified text portion.

In one embodiment, modifying the audio portion corresponding to the modified text portion includes removing an audio token corresponding to the modified text portion; determining adjacent audio tokens of the audio token; detecting acoustic properties of the adjacent audio token; and generating a new audio token corresponding to the modified text portion by reflecting sound characteristics of the adjacent audio token.

In one embodiment, determining adjacent audio tokens of the audio token may include determining a predetermined number of tokens before and after the audio token as adjacent audio tokens.

In one embodiment, detecting the acoustic characteristic of the adjacent audio token may include detecting at least one characteristic of gender, voice loudness, tone, pitch, age, or emotional state of the adjacent audio token. there is.

In one embodiment, when the change to the text information is to modify a text part included in the text information, the changing may include modifying an extended audio part associated with the modified text part. can

In one embodiment, modifying the extended audio portion associated with the modified text portion includes identifying an expanded text portion associated with the modified text portion; removing one or more audio tokens corresponding to the expanded text portion; determining adjacent audio tokens of the one or more audio tokens; detecting acoustic properties of the adjacent audio token; and generating one or more new audio tokens corresponding to the extended text portion by reflecting sound characteristics of the adjacent audio tokens.

In one embodiment, the extended text part may correspond to a text part of a predetermined language unit or speech recognition unit including the modified text part.

In one embodiment, the step of removing one or more audio tokens corresponding to the extended text portion may include a timestamp of voice information utilized for the voice recognition, and a time of text information generated by the voice recognition. based on the stamp, identifying one or more audio tokens corresponding to the extended text portion; and removing the identified one or more audio tokens.

In one embodiment, when the change to the text information is to add a new text part to the text information, the changing step comprises: an adjacent audio part corresponding to an adjacent text part at a position where the new text part is to be added. in consideration, generating a new audio portion corresponding to the new text portion.

In one embodiment, generating a new audio portion corresponding to the new text portion includes: identifying an adjacent text portion at a location where the new text portion is to be added; determining a contiguous audio token corresponding to the contiguous text portion; detecting acoustic properties of the adjacent audio token; and generating a new audio token corresponding to the new text portion by reflecting sound characteristics of the adjacent audio token.

A computer program stored in a computer readable storage medium is disclosed according to an embodiment of the present disclosure for realizing the above object. The computer program, when executed in one or more processors, causes the one or more processors to perform the following operations for generating voice, the operations comprising: obtaining text information generated by voice recognition; identifying a text portion where a change has occurred among the text information; identifying a voice part corresponding to the identified text part among voice information used for the voice recognition; changing a speech portion associated with the identified speech portion; and generating new voice information based on the changed voice portion and the remaining voice portions of the voice information.

A computing device according to an embodiment of the present disclosure for realizing the above object is disclosed. The device may include at least one processor; and a memory, wherein the at least one processor is configured to obtain text information generated by voice recognition; identifying a text portion where a change occurs among the text information; identifying a voice part corresponding to the identified text part among voice information used for the voice recognition; change a speech portion associated with the identified speech portion; and generate new voice information based on the changed voice portion and the remaining voice portions of the voice information.

According to the present disclosure, a refined voice file may be obtained in response to a change (eg, deletion, modification, or addition) to text information generated by voice recognition. In addition, the present disclosure can generate a natural voice by utilizing the sound characteristics of adjacent audio tokens with respect to the fundamental problem that Text to Speech (TTS) is not natural.

On the other hand, the effects of the present disclosure are not limited to the effects mentioned above, and various effects may be included within a range apparent to those skilled in the art from the contents to be described below.

1 is a block diagram of a computing device for generating voice according to an embodiment of the present disclosure.
2 is a schematic diagram illustrating a network function according to an embodiment of the present disclosure.
3 is a schematic flowchart of an operation of generating a voice when the type of text information change is deletion according to an embodiment of the present disclosure.
4 is a schematic flowchart of an operation of generating a voice when the type of text information change is modification according to an embodiment of the present disclosure.
5 is a schematic flowchart of an operation of generating a voice when a type of text information conversion is additional according to an embodiment of the present disclosure.
6 is a flowchart of a method for generating voice according to an embodiment of the present disclosure.
7 is a simplified and general schematic diagram of an exemplary computing environment in which embodiments of the present disclosure may be implemented.

Various embodiments are now described with reference to the drawings. In this specification, various descriptions are presented to provide an understanding of the present disclosure. However, it is apparent that these embodiments may be practiced without these specific details.

The terms “component,” “module,” “system,” and the like, as used herein, refer to a computer-related entity, hardware, firmware, software, a combination of software and hardware, or an execution of software. For example, a component may be, but is not limited to, a procedure, processor, object, thread of execution, program, and/or computer running on a processor. For example, both an application running on a computing device and a computing device may be components. One or more components may reside within a processor and/or thread of execution. A component can be localized within a single computer. A component may be distributed between two or more computers. In addition, these components can execute from various computer readable media having various data structures stored thereon. Components may be connected, for example, via signals with one or more packets of data (e.g., data and/or signals from one component interacting with another component in a local system, distributed system) to other systems and over a network such as the Internet. data being transmitted) may communicate via local and/or remote processes.

In addition, the term “or” is intended to mean an inclusive “or” rather than an exclusive “or”. That is, unless otherwise specified or clear from the context, “X employs A or B” is intended to mean one of the natural inclusive substitutions. That is, X uses A; X uses B; Or, if X uses both A and B, "X uses either A or B" may apply to either of these cases. Also, the term "and/or" as used herein should be understood to refer to and include all possible combinations of one or more of the listed related items.

Also, the terms "comprises" and/or "comprising" should be understood to mean that the features and/or components are present. However, it should be understood that the terms "comprises" and/or "comprising" do not exclude the presence or addition of one or more other features, elements, and/or groups thereof. Also, unless otherwise specified or where the context clearly indicates that a singular form is indicated, the singular in this specification and claims should generally be construed to mean "one or more".

In addition, the term “at least one of A or B” should be interpreted as meaning “when only A is included”, “when only B is included”, and “when A and B are combined”.

Those skilled in the art will further understand that the various illustrative logical blocks, components, modules, circuits, means, logics, and algorithm steps described in connection with the embodiments disclosed herein may be implemented using electronic hardware, computer software, or combinations of both. It should be recognized that it can be implemented as To clearly illustrate the interchangeability of hardware and software, various illustrative components, blocks, configurations, means, logics, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented in hardware or as software depends on the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application. However, such implementation decisions should not be interpreted as causing a departure from the scope of this disclosure.

The description of the presented embodiments is provided to enable any person skilled in the art to use or practice the present invention. Various modifications to these embodiments will be apparent to those skilled in the art of this disclosure. The general principles defined herein may be applied to other embodiments without departing from the scope of this disclosure. Thus, the present invention is not limited to the embodiments presented herein. The present invention is to be accorded the widest scope consistent with the principles and novel features set forth herein.

In the present disclosure, network functions, artificial neural networks, and neural networks may be used interchangeably.

1 is a block diagram of a computing device for generating voice according to an embodiment of the present disclosure.

The configuration of the computing device 100 shown in FIG. 1 is only a simplified example. In one embodiment of the present disclosure, the computing device 100 may include other components for performing a computing environment of the computing device 100, and only some of the disclosed components may constitute the computing device 100.

The computing device 100 may include a processor 110 , a memory 130 , and a network unit 150 .

The processor 110 may include one or more cores, and includes a central processing unit (CPU), a general purpose graphics processing unit (GPGPU), and a tensor processing unit (TPU) of a computing device. unit), data analysis, and processors for deep learning. The processor 110 may read a computer program stored in the memory 130 and process data for machine learning according to an embodiment of the present disclosure. According to an embodiment of the present disclosure, the processor 110 may perform an operation for learning a neural network. The processor 110 is used for neural network learning, such as processing input data for learning in deep learning (DL), extracting features from input data, calculating errors, and updating neural network weights using backpropagation. calculations can be performed. At least one of the CPU, GPGPU, and TPU of the processor 110 may process learning of the network function. For example, the CPU and GPGPU can process learning of network functions and data classification using network functions. In addition, in an embodiment of the present disclosure, the learning of a network function and data classification using a network function may be processed by using processors of a plurality of computing devices together. In addition, a computer program executed in a computing device according to an embodiment of the present disclosure may be a CPU, GPGPU or TPU executable program.

According to an embodiment of the present disclosure, the processor 110 generates new voice information based on a change (eg, deletion, modification, or addition) to text information generated by speech recognition (STT). can do. For example, the processor 110 ① performs speech recognition (STT or ASR) for converting voice into text for the original voice uttered by the user, and ② changes (eg, deletion, modification, or addition) of text information A voice part for the generated part is identified, ③ a voice part associated with the identified voice part is changed, and new voice information can be generated based on the remaining voice parts of the voice information.

More specifically, when the change is deletion, the processor 110 may delete an audio portion corresponding to the deleted text portion. In addition, if the change is a correction, the processor 110 removes the audio portion corresponding to the modified portion and generates an audio portion corresponding to the modified text portion through text-to-speech synthesis (TTS) so as to match the existing voice. New voice information can be created through synthesis. Also, when the change is addition, the processor 110 may generate an audio part corresponding to the generated text information and generate new voice information through synthesis with the existing voice. At this time, the processor 110 considers the sound characteristics (eg, gender, voice volume, tone, pitch, age, emotional state, etc.) of the audio parts (audio tokens) adjacent to the generated audio part, so that the corresponding audio file is recorded. New voice information may be generated so that a voice as close as possible to an actual user's voice in a situation may be synthesized (generated).

On the other hand, the processor 110 generates changed voice information from the recorded audio voice when the user removes unnecessary simplistic parts from the speech recognition (STT) result or corrects an incorrectly spoken part such as a word, so that the user can obtain text and voice information. This matching refined voice audio file can be obtained.

According to an embodiment of the present disclosure, the memory 130 may store any type of information generated or determined by the processor 110 and any type of information received by the network unit 150 .

According to an embodiment of the present disclosure, the memory 130 is a flash memory type, a hard disk type, a multimedia card micro type, or a card type memory (eg, SD or XD memory, etc.), RAM (Random Access Memory, RAM), SRAM (Static Random Access Memory), ROM (Read-Only Memory, ROM), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory) -Only Memory), a magnetic memory, a magnetic disk, and an optical disk may include at least one type of storage medium. The computing device 100 may operate in relation to a web storage that performs a storage function of the memory 130 on the Internet. The above description of the memory is only an example, and the present disclosure is not limited thereto.

The network unit 150 according to an embodiment of the present disclosure includes a Public Switched Telephone Network (PSTN), x Digital Subscriber Line (xDSL), Rate Adaptive DSL (RADSL), Multi Rate DSL (MDSL), and VDSL ( Various wired communication systems such as Very High Speed DSL), Universal Asymmetric DSL (UADSL), High Bit Rate DSL (HDSL), and Local Area Network (LAN) may be used.

In addition, the network unit 150 presented in this specification includes Code Division Multi Access (CDMA), Time Division Multi Access (TDMA), Frequency Division Multi Access (FDMA), Orthogonal Frequency Division Multi Access (OFDMA), SC-FDMA ( Single Carrier-FDMA) and other systems.

In the present disclosure, the network unit 150 may be configured regardless of its communication mode, such as wired and wireless, and may include a local area network (LAN), a personal area network (PAN), and a wide area network (WAN: It can be composed of various communication networks such as Wide Area Network). In addition, the network may be the known World Wide Web (WWW), or may use a wireless transmission technology used for short-range communication, such as Infrared Data Association (IrDA) or Bluetooth.

The techniques described herein may be used in the networks mentioned above as well as other networks.

2 is a schematic diagram illustrating a network function according to an embodiment of the present disclosure.

Throughout this specification, computational model, neural network, network function, and neural network may be used interchangeably. A neural network may consist of a set of interconnected computational units, which may generally be referred to as nodes. These nodes may also be referred to as neurons. A neural network includes one or more nodes. Nodes (or neurons) constituting neural networks may be interconnected by one or more links.

In a neural network, one or more nodes connected through a link may form a relative relationship of an input node and an output node. The concept of an input node and an output node is relative, and any node in an output node relationship with one node may have an input node relationship with another node, and vice versa. As described above, an input node to output node relationship may be created around a link. More than one output node can be connected to one input node through a link, and vice versa.

In a relationship between an input node and an output node connected through one link, the value of data of the output node may be determined based on data input to the input node. Here, a link interconnecting an input node and an output node may have a weight. The weight may be variable, and may be changed by a user or an algorithm in order to perform a function desired by the neural network. For example, when one or more input nodes are interconnected by respective links to one output node, the output node is set to a link corresponding to values input to input nodes connected to the output node and respective input nodes. An output node value may be determined based on the weight.

As described above, in the neural network, one or more nodes are interconnected through one or more links to form an input node and output node relationship in the neural network. Characteristics of the neural network may be determined according to the number of nodes and links in the neural network, an association between the nodes and links, and a weight value assigned to each link. For example, when there are two neural networks having the same number of nodes and links and different weight values of the links, the two neural networks may be recognized as different from each other.

A neural network may be composed of a set of one or more nodes. A subset of nodes constituting a neural network may constitute a layer. Some of the nodes constituting the neural network may form one layer based on distances from the first input node. For example, a set of nodes having a distance of n from the first input node may constitute n layers. The distance from the first input node may be defined by the minimum number of links that must be passed through to reach the corresponding node from the first input node. However, the definition of such a layer is arbitrary for explanation, and the order of a layer in a neural network may be defined in a method different from the above. For example, a layer of nodes may be defined by a distance from a final output node.

An initial input node may refer to one or more nodes to which data is directly input without going through a link in relation to other nodes among nodes in the neural network. Alternatively, in a relationship between nodes based on a link in a neural network, it may mean nodes that do not have other input nodes connected by a link. Similarly, the final output node may refer to one or more nodes that do not have an output node in relation to other nodes among nodes in the neural network. Also, the hidden node may refer to nodes constituting the neural network other than the first input node and the last output node.

In the neural network according to an embodiment of the present disclosure, the number of nodes in the input layer may be the same as the number of nodes in the output layer, and the number of nodes decreases and then increases again as the number of nodes progresses from the input layer to the hidden layer. can In addition, the neural network according to another embodiment of the present disclosure may be a neural network in which the number of nodes of the input layer may be less than the number of nodes of the output layer and the number of nodes decreases as the number of nodes increases from the input layer to the hidden layer. there is. In addition, the neural network according to another embodiment of the present disclosure is a neural network in which the number of nodes in the input layer may be greater than the number of nodes in the output layer, and the number of nodes increases as the number of nodes increases from the input layer to the hidden layer. can A neural network according to another embodiment of the present disclosure may be a neural network in the form of a combination of the aforementioned neural networks.

A deep neural network (DNN) may refer to a neural network including a plurality of hidden layers in addition to an input layer and an output layer. Deep neural networks can reveal latent structures in data. In other words, it can identify the latent structure of a photo, text, video, sound, or music (e.g., what objects are in the photo, what the content and emotion of the text are, what the content and emotion of the audio are, etc.). . Deep neural networks include convolutional neural networks (CNNs), recurrent neural networks (RNNs), auto encoders, generative adversarial networks (GANs), and restricted boltzmann machines (RBMs). machine), a deep belief network (DBN), a Q network, a U network, a Siamese network, a Generative Adversarial Network (GAN), and the like. The description of the deep neural network described above is only an example, and the present disclosure is not limited thereto.

In one embodiment of the present disclosure, the network function may include an autoencoder. An autoencoder may be a type of artificial neural network for outputting output data similar to input data. An auto-encoder may include at least one hidden layer, and an odd number of hidden layers may be disposed between input and output layers. The number of nodes of each layer may be reduced from the number of nodes of the input layer to an intermediate layer called the bottleneck layer (encoding), and then expanded symmetrically with the reduction from the bottleneck layer to the output layer (symmetrical to the input layer). Autoencoders can perform non-linear dimensionality reduction. The number of input layers and output layers may correspond to dimensions after preprocessing of input data. In the auto-encoder structure, the number of hidden layer nodes included in the encoder may decrease as the distance from the input layer increases. If the number of nodes in the bottleneck layer (the layer with the fewest nodes located between the encoder and decoder) is too small, a sufficient amount of information may not be conveyed, so more than a certain number (e.g., more than half of the input layer, etc.) ) may be maintained.

The neural network may be trained using at least one of supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning. Learning of the neural network may be a process of applying knowledge for the neural network to perform a specific operation to the neural network.

A neural network can be trained in a way that minimizes output errors. In the learning of the neural network, the learning data is repeatedly input into the neural network, the output of the neural network for the training data and the error of the target are calculated, and the error of the neural network is transferred from the output layer of the neural network to the input layer in the direction of reducing the error. It is a process of updating the weight of each node of the neural network by backpropagating in the same direction. In the case of teacher learning, the learning data in which the correct answer is labeled is used for each learning data (ie, the labeled learning data), and in the case of comparative teacher learning, the correct answer may not be labeled in each learning data. That is, for example, learning data in the case of teacher learning regarding data classification may be data in which each learning data is labeled with a category. Labeled training data is input to a neural network, and an error may be calculated by comparing an output (category) of the neural network and a label of the training data. As another example, in the case of comparative history learning for data classification, an error may be calculated by comparing input learning data with a neural network output. The calculated error is back-propagated in a reverse direction (ie, from the output layer to the input layer) in the neural network, and connection weights of each node of each layer of the neural network may be updated according to the back-propagation. The amount of change in the connection weight of each updated node may be determined according to a learning rate. The neural network's computation of input data and backpropagation of errors can constitute a learning cycle (epoch). The learning rate may be applied differently according to the number of iterations of the learning cycle of the neural network. For example, a high learning rate may be used in the early stage of neural network training to increase efficiency by allowing the neural network to quickly obtain a certain level of performance, and a low learning rate may be used in the late stage to increase accuracy.

In neural network learning, generally, training data can be a subset of real data (ie, data to be processed using the trained neural network), and therefore, errors for training data are reduced, but errors for real data are reduced. There may be incremental learning cycles. Overfitting is a phenomenon in which errors for actual data increase due to excessive learning on training data. For example, a phenomenon in which a neural network that has learned a cat by showing a yellow cat does not recognize that it is a cat when it sees a cat other than yellow may be a type of overfitting. Overfitting can act as a cause of increasing the error of machine learning algorithms. Various optimization methods can be used to prevent such overfitting. To prevent overfitting, methods such as increasing the training data, regularization, inactivating some nodes in the network during learning, and using a batch normalization layer should be applied. can

In the present disclosure, the "reinforcement learning control model" may be an artificial neural network model having the configuration of the neural network described above with reference to FIG. 2, but may be an artificial neural network model learned by a reinforcement learning method.

Reinforcement learning is an artificial neural network based on the reward that an artificial neural network model calculates for an action selected so that the artificial neural network model can determine a better action based on the input state. It is a kind of learning method to train a model. Reinforcement learning methods can be understood as "learning through trial and error" in that decisions (i.e., actions) are rewarded. A reward given to an artificial neural network model in a reinforcement learning process may be a reward obtained by accumulating results of various actions. Reinforcement learning creates an artificial neural network model that maximizes the reward itself or the return (sum of rewards) by considering rewards according to various states and actions through learning. In the present disclosure, a "reinforcement learning control model" is a subject that determines behavior and may be used interchangeably with the term "agent". In the technical field related to reinforcement learning, the term "environment (Env)" or "environment model" is used as a term to refer to "a model that returns a result considering the behavior of an agent." The environment model may be a model that returns output data (e.g. state information) for given input data (e.g. control information). The environment model may be a model structure for reaching from input to output or a model in which the causal relationship between input and output data is unknown. Agents and environments can work by exchanging data.

According to an embodiment of the present disclosure, text to speech (TTS), which will be described below, is a technology for generating voice corresponding to text. In addition, it is important for text to speech (TTS) to generate a voice similar to a reference audio for input text. Meanwhile, a text-to-speech (TTS) model may be implemented in various types of models including the neural network model described above. For example, the Text to Speech (TTS) module may include Tacotron2, HiFi-GAN, and the like.

According to an embodiment of the present disclosure, the processor 110 performs speech recognition (STT or ASR; Speech To Text, or Automatic Speech Recognition) using the acquired audio (voice signal) as an input prior to generating new speech information. Text information can be created through First, the processor 110 may obtain audio (eg, a voice signal or a spectrogram) including voices uttered by one speaker or a plurality of speakers. In addition, the processor 110 may perform noise cancellation, speech enhancement, and voice activity detection (VAD) to improve audio quality. Also, the processor 110 may analyze audio in units of audio tokens and perform speech recognition (STT) on each audio token. In addition, the processor 110 may output text information and timestamp information for audio as a result of speech recognition (STT). Meanwhile, the processor 110 may align audio-text through timestamp information by outputting timestamp information for text information and audio.

According to an embodiment of the present disclosure, speech recognition (STT or ASR; Speech To Text, or Automatic Speech Recognition) is a dictation technology that converts speech into text. The input of the speech recognition (STT) may include at least one of a speech signal, a spectrogram obtained by converting the speech signal, or a speech feature. In addition, the output of speech recognition (STT) is text in the form of a character string. Meanwhile, the speech recognition (STT) model may be implemented in various types of models including the neural network model described above. In addition, the speech recognition (STT) model may be divided into a modular method and a non-modular end-to-end (e2e) method according to an implemented method. Here, the modularized method is divided into an acoustic model (a model that indicates how a voice signal can be expressed), a language model (a model that assigns a probability of occurrence to a word based on a given sentence and word), and a pronunciation dictionary, etc. It may include, but is not limited to, traditional models for performing recognition (eg, some models of Kaldi toolkit-based ASR models, Hybrid-ASR models, etc.). On the other hand, the non-modularized method mainly means an e2e model (eg, a transformer-based encoder decoder model, etc.), and the model can be created by learning a lot of data without having sub-modules. On the other hand, the beam search technique is representative of the decoding technique, and the beam search technique does not predict just one word that is closest to the correct answer according to the situation, but opens up various possibilities and considers the entire sentence to find the most optimal way to find the correct answer.

Voice Activity Detection (VAD), according to an embodiment of the present disclosure, is a technique for determining whether voice activity is detected in an audio stream. For voice detection (VAD), preprocessing techniques such as noise removal and speech enhancement may be applied before applying voice recognition (STT). In addition, voice detection (VAD) is based on a binary classification algorithm that distinguishes whether a person has pronounced (1) or not (0) for each short voice section (eg, 0.01s), In this way, it is possible to determine whether it is a voice section. In addition, voice detection (VAD) has a distribution of spoken voices and a distribution of noise voices, and determines which of the voice and noise is closer based on a probability distribution based on a statistical basis. Distribution based classification classification) algorithm may be mainly used, but is not limited thereto.

According to an embodiment of the present disclosure, prior to generating new voice information, the processor 110 may obtain text information generated by voice recognition. Also, the processor 110 may identify a text portion where a change occurs among text information. Here, the change to the text information includes (1) deleting a text part included in the text information, (2) modifying a text part included in the text information, or (3) adding new text to the text information. It may include at least one of adding parts.

Illustratively, changes to text information may be implemented by user input information. In this case, the user input information may include user input information obtained by performing at least one of deletion, modification, and addition to the text part included in the text information through the user interface. Additionally, changes to text information may be implemented based on information other than the user input information. For example, changes to text information may be implemented by information generated by an artificial intelligence model that verifies the appropriateness of a speech recognition result, and may be implemented based on various types of information in addition to such information.

Also, the processor 110 may identify a voice part corresponding to the identified text part among voice information used for voice recognition. Additionally, the processor 110 may change a speech portion associated with the identified speech portion (eg, the identified speech portion itself, or an extended speech portion related to the identified speech portion, etc.). Also, the processor 110 may generate new voice information based on the changed voice portion and the remaining portions of the voice information.

Hereinafter, deletion, correction, and addition, which are types of changes to text information, will be described in more detail with reference to FIGS. 3 to 5 .

3 is a schematic flowchart of an operation of generating a voice when the type of text information change is “delete” according to an embodiment of the present disclosure.

According to an embodiment of the present disclosure, the processor 110 may obtain original audio (speech) to perform voice recognition (S10). Also, the processor 110 may obtain text information generated by voice recognition (S11). As an example, referring to FIG. 3 , the processor 110 may obtain text information such as “Open that chapter 8 today” as a result of speech recognition (STT). Also, the processor 110 may identify a text portion where a change occurs among text information (S12). Here, the change to the text information may be deleting a text part included in the text information. For example, the processor 110 may identify a text portion corresponding to “there, there” among text information when a change to delete a text portion corresponding to “there, there” occurs. For example, the processor 110 considers user input information for deleting a text portion included in the text information through a user interface (eg, deleting a text portion corresponding to “that there”), where a change in the text information occurs. Text parts can be identified.

In addition, the processor 110 may identify a voice part corresponding to the identified text part (eg, “that there”) among the voice information used for voice recognition. Also, the processor 110 may change the voice part associated with the identified voice part (S13). In this regard, the processor 110 may delete an audio portion corresponding to the deleted text portion. In one embodiment, an audio portion may be identified on a per audio token basis. In other words, the processor 110 may remove the audio token corresponding to the deleted text portion. Also, the processor 110 may generate new voice information based on the changed voice portion (deleted audio portion) and the remaining portions of the voice information (S14). For example, the processor 110 deletes the voice part changed from the original spoken voice of “Open that chapter 8 today”, “that”, and deletes the remaining parts of the voice information “open chapter 8 today”. New voice information corresponding to "Please" may be generated. That is, when the change to the text information is deletion, the processor 110 may generate new voice information by deleting an audio token corresponding to the deleted text part from the original audio file and concatenating the remaining audio tokens.

4 is a schematic flowchart of an operation of generating a voice when the type of text information change is “modification” according to an embodiment of the present disclosure.

According to an embodiment of the present disclosure, the processor 110 may obtain original audio (speech) to perform voice recognition (S20). Also, the processor 110 may acquire text information generated by voice recognition (S21). As an example, referring to FIG. 4 , the processor 110 may obtain text information such as “Open that chapter 8 today” as a result of speech recognition (STT).

Also, the processor 110 may identify a text portion where a change occurs among text information (S22). Here, the change to the text information may be to modify a text part included in the text information. In addition, the processor 110 may identify the text portion corresponding to "8" when a change in the text information to modify the text portion corresponding to "8" to the text corresponding to "9" occurs. For example, the processor 110 may change the text information in consideration of user input information (eg, user input information modified from "8" to "9") for modifying a text part included in the text information through a user interface. It is possible to identify the text part where the occurrence occurred.

Also, the processor 110 may change the voice part associated with the identified voice part (S23). In this regard, the processor 110 may modify the audio portion corresponding to the modified text portion in consideration of an adjacent audio portion of the audio portion corresponding to the modified text portion. Meanwhile, in the operation of modifying the audio portion corresponding to the corrected text portion, the processor 110 may perform an operation of modifying only the audio portion corresponding to the corrected text portion or ② an operation of correcting only the audio portion corresponding to the corrected text portion. Rather, the voice part associated with the identified voice part may be changed by applying any one of operations for modifying the extended speech part associated with the modified text part.

According to an embodiment of the present disclosure, ① in an operation of modifying only a voice part corresponding to a modified text part, the processor 110 may remove an audio token corresponding to the modified text part. For example, referring to FIG. 4 , the processor 110 may remove an audio token corresponding to “8”. Additionally, processor 110 may determine adjacent audio tokens of the removed audio token. In this case, the processor 110 may determine a predetermined number of tokens before and after the removed audio token as adjacent audio tokens. For example, the processor 110 determines n tokens before and after an audio token corresponding to “8”, n tokens preceding the audio token, n tokens following the audio token, and the like, as the adjacent audio tokens. can

Additionally, the processor 110 may detect acoustical characteristics of adjacent audio tokens. Here, the processor 110 may detect at least one characteristic of the adjacent audio token's gender, voice volume, tone, pitch, age, or emotional state. Also, the processor 110 may generate an audio token corresponding to the modified text part by reflecting sound characteristics of adjacent audio tokens. For example, the processor 110 may use text-to-speech synthesis (TSS) reflecting sound characteristics of adjacent audio tokens to generate “a new audio token corresponding to a part where the user has modified the STT result text”. In one embodiment, the processor 110 may generate an audio token corresponding to a “9” corresponding to the modified text portion by reflecting the sonic characteristics of the adjacent audio token. Since sound answer data (for example, it is assumed that the text is accurate because the user has not modified it) exists, voices can be synthesized more appropriately to the situation and more naturally if this is used.

Also, the processor 110 may generate new voice information based on the changed voice portion (audio token corresponding to the modified text portion) and the remaining portions of the voice information (S24). In other words, the processor 110 removes only the audio part corresponding to "8", which is the text part where the change occurred, from the text information, and synthesizes the voice corresponding to the modified text part, "9", at this time, the modified text part. New voice information may be generated by performing voice synthesis for "9" in consideration of sound characteristics of "today" and "jangeul", which are adjacent audio parts of the audio part corresponding to .

According to an embodiment of the present disclosure, in ② "operation of modifying the extended speech part associated with the modified text part (without modifying only the speech part corresponding to the modified text part)", the processor 110 performs the modified text part You can modify the extended audio part associated with. More specifically, the processor 110 may identify an extended text portion associated with the modified text portion. Here, the extended text part may correspond to a text part of a predetermined language unit or speech recognition unit including the modified text part. For reference, a language unit may include a word, a sub-word, a syllable, a grapheme, a consonant, and a vowel unit. Also, the voice recognition unit may include a voice chunk unit detected in a VAD step of voice recognition (STT). For example, if the text corresponding to "8" included in the text information is changed to the text corresponding to "9", "Chapter 8" associated with the text part corresponding to "8" is referred to as "extended text part". can be identified as In addition, "Chapter 9", which is an extended text portion in which corrections are reflected, may be identified as an "extended modified text portion".

Also, the processor 110 may remove one or more audio tokens corresponding to the extended text part. In addition, the processor 110 may select one or more pieces of audio corresponding to the extended text part based on a timestamp of voice information used for the voice recognition and a timestamp of text information generated by the voice recognition. tokens can be identified. For example, the processor 110 removes the audio token corresponding to "Chapter 8" corresponding to the extended text part based on the "timestamp of audio information" and "timestamp of text information". can do.

Additionally, the processor 110 may detect acoustical characteristics of adjacent audio tokens adjacent to the removed one or more audio tokens. Here, the processor 110 may detect at least one characteristic of the adjacent audio token's gender, voice volume, tone, pitch, age, or emotional state. In addition, the processor 110 may generate one or more new audio tokens corresponding to the “extended modified text portion” by reflecting sound characteristics of adjacent audio tokens. For example, the processor 110 may generate one or more new audio tokens corresponding to the "extended modified text part" using text-to-speech synthesis (TSS) reflecting sound characteristics of adjacent audio tokens. Referring to the example of FIG. 4 , the processor 110 may generate one or more new audio tokens corresponding to the extended modified text part “Chapter 9” by reflecting sound characteristics of adjacent audio tokens.

Also, the processor 110 may generate new voice information based on the changed voice portion (generated new audio token) and the remaining portions of the voice information (S24). In other words, the processor 110 identifies the extended text part "Chapter 8" for the text part "8" where a change has occurred in the text information, removes the audio part corresponding to "Chapter 8", Identify "Chapter 9", which is an extended text part in which the corrections (8 -> 9) are reflected, as an "extended modified text part", and reflect the sound characteristics of the audio part adjacent to the removed audio part, and the extension A new audio part corresponding to the modified text part "Chapter 9" can be synthesized. At this time, the voice for "Chapter 9" may be synthesized by reflecting the sound characteristics of "today" and "open".

According to an embodiment of the present disclosure, ① when a new voice is synthesized by an operation of modifying only a voice portion corresponding to a modified text portion, an audio portion corresponding to the corrected text portion may be very short. In this case, since the voice of the corresponding part may be awkward, the present disclosure applies an operation of modifying the extended voice part associated with the corrected text part (i.e., not modifying only the speech part corresponding to the corrected text part). , by performing an operation of newly generating a voice for a text unit larger than the modified text), it is possible to create a new voice that reflects the correction but has the same level of naturalness as the original voice. In addition, according to an embodiment of the present disclosure, since a new voice part corresponding to the extended text part is generated by reflecting sound characteristics of an adjacent audio part, a more natural voice equal to the original voice level can be generated.

5 is a schematic flowchart of an operation of generating a voice when the type of text information conversion is “additional” according to an embodiment of the present disclosure.

According to an embodiment of the present disclosure, the processor 110 may acquire original audio (speech) to perform voice recognition (S30). Also, the processor 110 may obtain text information generated by voice recognition (S31). As an example, referring to FIG. 5 , the processor 110 may obtain text information such as “Open that chapter 8 today” as a result of speech recognition (STT).

Also, the processor 110 may identify a text portion where a change occurs among text information (S32). Here, the change to the text information may be adding a text part included in the text information. In this regard, the processor 110 may create a new audio part corresponding to the new text part by considering an adjacent audio part corresponding to the text part adjacent to the position where the new text part is to be added. More specifically, the processor 110 may identify a text portion adjacent to a position where the new text portion is to be added. As an example, referring to FIG. 5 , when a change to add a text portion corresponding to “Come on” occurs, the processor 110 displays “Come on”, which is a text part adjacent to a position where “Come on” is to be added among text information. can be identified. For example, the processor 110 considers user input information (eg, adding a text part corresponding to “Come on”) to add a specific text from text information through a user interface, and the processor 110 considers the adjacent position where a new text part is to be added. Text parts can be identified. Additionally, the processor 110 may determine a contiguous audio token corresponding to the contiguous text portion. In one example, processor 110 may determine a contiguous audio token corresponding to the contiguous text portion “open”. Additionally, the processor 110 may detect the acoustic characteristics of the adjacent audio token. Here, the processor 110 may detect at least one characteristic of the adjacent audio token's gender, voice volume, tone, pitch, age, or emotional state. Also, the processor 110 may generate a new audio token corresponding to the new text part by reflecting sound characteristics of the adjacent audio token (S33). Also, the processor 110 may generate new voice information based on the changed voice portion (newly generated audio portion) and the remaining portions of the voice information (S34). For example, new audio information for "Come on, open that chapter 8 today" can be created by synthesizing the newly created audio part "Come on," and the remaining parts, "Open that chapter 8 today". can

6 is a flowchart of a method for generating voice according to an embodiment of the present disclosure.

The method of generating voice shown in FIG. 6 may be performed by the computing device 100 . Even if not mentioned in detail below, the above description of the computing device 100 may be equally applied to a description of a method for generating voice.

Referring to FIG. 6 , a method for generating voice according to an embodiment of the present disclosure includes obtaining text information generated by voice recognition (S110), and identifying a text portion where a change has occurred among the text information. (S120), identifying a voice part corresponding to the identified text part among the voice information used for voice recognition (S130), changing a voice part associated with the identified voice part (S140), and It may include generating new voice information based on the voice portion and the remaining voice portions of the voice information (S150). Also, the method for generating voice according to an embodiment of the present disclosure may be performed by the computing device 100 .

Step S110 is a step of obtaining text information generated by voice recognition.

The step S120 is a step of identifying a text portion where a change has occurred among the text information. Here, the change in the text information may include at least one of deleting a text part included in the text information, correcting a text part included in the text information, or adding a new text part to the text information. can include

The step S130 is a step of identifying a voice part corresponding to the identified text part among the voice information used for the voice recognition.

The step S140 is a step of changing a voice part associated with the identified voice part.

The step S150 is a step of generating new voice information based on the changed voice portion and the remaining voice portions of the voice information.

The steps mentioned in the foregoing description may be further divided into additional steps or combined into fewer steps, depending on the implementation of the present disclosure. Also, some steps may be omitted if necessary, and the order of steps may be changed.

According to an embodiment of the present disclosure, a computer readable medium storing a data structure is disclosed.

Data structure can refer to the organization, management, and storage of data that enables efficient access and modification of data. Data structure may refer to the organization of data to solve a specific problem (eg, data retrieval, data storage, data modification in the shortest time). A data structure may be defined as a physical or logical relationship between data elements designed to support a specific data processing function. A logical relationship between data elements may include a connection relationship between user-defined data elements. A physical relationship between data elements may include an actual relationship between data elements physically stored in a computer-readable storage medium (eg, a persistent storage device). The data structure may specifically include a set of data, a relationship between data, and a function or command applicable to the data. Through an effectively designed data structure, a computing device can perform calculations while using minimal resources of the computing device. Specifically, the computing device can increase the efficiency of operation, reading, insertion, deletion, comparison, exchange, and search through an effectively designed data structure.

The data structure can be divided into a linear data structure and a non-linear data structure according to the shape of the data structure. A linear data structure may be a structure in which only one data is connected after one data. Linear data structures may include lists, stacks, queues, and decks. A list may refer to a series of data sets in which order exists internally. The list may include a linked list. A linked list may be a data structure in which data are connected in such a way that each data is connected in a single line with a pointer. In a linked list, a pointer can contain information about connection to the next or previous data. A linked list can be expressed as a singly linked list, a doubly linked list, or a circular linked list depending on the form. A stack can be a data enumeration structure that allows limited access to data. A stack can be a linear data structure in which data can be processed (eg, inserted or deleted) at only one end of the data structure. The data stored in the stack may be a LIFO-Last in First Out (Last in First Out) data structure. A queue is a data listing structure that allows limited access to data, and unlike a stack, it can be a data structure (FIFO-First in First Out) in which data stored later comes out later. A deck can be a data structure that can handle data from either end of the data structure.

The nonlinear data structure may be a structure in which a plurality of data are connected after one data. The non-linear data structure may include a graph data structure. A graph data structure can be defined as a vertex and an edge, and an edge can include a line connecting two different vertices. A graph data structure may include a tree data structure. The tree data structure may be a data structure in which one path connects two different vertices among a plurality of vertices included in the tree. That is, it may be a data structure that does not form a loop in a graph data structure.

Throughout this specification, computational model, neural network, network function, and neural network may be used interchangeably. Hereinafter, a neural network is unified and described. The data structure may include a neural network. And the data structure including the neural network may be stored in a computer readable medium. The data structure including the neural network may also include preprocessed data for processing by the neural network, data input to the neural network, weights of the neural network, hyperparameters of the neural network, data obtained from the neural network, activation function associated with each node or layer of the neural network, and neural network It may include a loss function for learning of . A data structure including a neural network may include any of the components described above. That is, the data structure including the neural network includes preprocessed data for processing by the neural network, data input to the neural network, weights of the neural network, hyperparameters of the neural network, data obtained from the neural network, activation function associated with each node or layer of the neural network, and neural network. It may be configured to include all or any combination thereof, such as a loss function for learning of . In addition to the foregoing configurations, the data structure comprising the neural network may include any other information that determines the characteristics of the neural network. In addition, the data structure may include all types of data used or generated in the computational process of the neural network, but is not limited to the above. A computer readable medium may include a computer readable recording medium and/or a computer readable transmission medium. A neural network may consist of a set of interconnected computational units, which may generally be referred to as nodes. These nodes may also be referred to as neurons. A neural network includes at least one or more nodes.

The data structure may include data input to the neural network. A data structure including data input to the neural network may be stored in a computer readable medium. Data input to the neural network may include training data input during a neural network learning process and/or input data input to a neural network that has been trained. Data input to the neural network may include pre-processed data and/or data subject to pre-processing. Pre-processing may include a data processing process for inputting data to a neural network. Accordingly, the data structure may include data subject to pre-processing and data generated by pre-processing. The foregoing data structure is only an example, and the present disclosure is not limited thereto.

The data structure may include the weights of the neural network. (In this specification, weights and parameters may be used in the same meaning.) Also, a data structure including weights of a neural network may be stored in a computer readable medium. A neural network may include a plurality of weights. The weight may be variable, and may be changed by a user or an algorithm in order to perform a function desired by the neural network. For example, when one or more input nodes are interconnected by respective links to one output node, the output node is set to a link corresponding to values input to input nodes connected to the output node and respective input nodes. A data value output from an output node may be determined based on the weight. The foregoing data structure is only an example, and the present disclosure is not limited thereto.

As a non-limiting example, the weights may include weights that are varied during neural network training and/or weights for which neural network training has been completed. The variable weight in the neural network learning process may include a weight at the time the learning cycle starts and/or a variable weight during the learning cycle. The weights for which neural network learning has been completed may include weights for which learning cycles have been completed. Accordingly, the data structure including the weights of the neural network may include a data structure including weights that are variable during the neural network learning process and/or weights for which neural network learning is completed. Therefore, it is assumed that the above-described weights and/or combinations of weights are included in the data structure including the weights of the neural network. The foregoing data structure is only an example, and the present disclosure is not limited thereto.

The data structure including the weights of the neural network may be stored in a computer readable storage medium (eg, a memory or a hard disk) after going through a serialization process. Serialization can be the process of converting a data structure into a form that can be stored on the same or another computing device and later reconstructed and used. A computing device may serialize data structures to transmit and receive data over a network. The data structure including the weights of the serialized neural network may be reconstructed on the same computing device or another computing device through deserialization. The data structure including the weights of the neural network is not limited to serialization. Furthermore, the data structure including the weights of the neural network is a data structure for increasing the efficiency of operation while minimizing the resource of the computing device (for example, B-Tree, Trie, m-way search tree, AVL tree, Red-Black Tree). The foregoing is only an example and the present disclosure is not limited thereto.

The data structure may include hyper-parameters of the neural network. Also, the data structure including the hyperparameters of the neural network may be stored in a computer readable medium. A hyperparameter may be a variable variable by a user. Hyperparameters include, for example, learning rate, cost function, number of learning cycle iterations, weight initialization (eg, setting the range of weight values to be targeted for weight initialization), hidden unit number (eg, the number of hidden layers and the number of nodes in the hidden layer). The foregoing data structure is only an example, and the present disclosure is not limited thereto.

7 is a simplified and general schematic diagram of an exemplary computing environment in which embodiments of the present disclosure may be implemented.

Although the present disclosure has been described above as being generally embodied by a computing device, those skilled in the art will understand that the present disclosure may be combined with computer-executable instructions and/or other program modules that may be executed on one or more computers and/or may be implemented in hardware and software. It will be appreciated that it can be implemented as a combination.

Generally, program modules include routines, programs, components, data structures, etc. that perform particular tasks or implement particular abstract data types. In addition, those skilled in the art will understand that the methods of the present disclosure can be applied to single-processor or multiprocessor computer systems, minicomputers, mainframe computers as well as personal computers, handheld computing devices, microprocessor-based or programmable consumer electronics, and the like ( It will be appreciated that each of these may be implemented with other computer system configurations, including those that may be operative in connection with one or more associated devices.

The described embodiments of the present disclosure may also be practiced in distributed computing environments where certain tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.

Computers typically include a variety of computer readable media. Computer readable media can be any medium that can be accessed by a computer, including volatile and nonvolatile media, transitory and non-transitory media, removable and non-transitory media. Includes removable media. By way of example, and not limitation, computer readable media may include computer readable storage media and computer readable transmission media. Computer readable storage media are volatile and nonvolatile media, transitory and non-transitory, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. includes media Computer readable storage media may include RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital video disk (DVD) or other optical disk storage device, magnetic cassette, magnetic tape, magnetic disk storage device or other magnetic storage device. device, or any other medium that can be accessed by a computer and used to store desired information.

A computer readable transmission medium typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism. Including all information delivery media. The term modulated data signal means a signal that has one or more of its characteristics set or changed so as to encode information within the signal. By way of example, and not limitation, computer readable transmission media includes wired media such as a wired network or direct-wired connection, and wireless media such as acoustic, RF, infrared, and other wireless media. Combinations of any of the above are also intended to be included within the scope of computer readable transmission media.

An exemplary environment 1100 implementing various aspects of the present disclosure is shown including a computer 1102, which includes a processing unit 1104, a system memory 1106, and a system bus 1108. do. System bus 1108 couples system components, including but not limited to system memory 1106 , to processing unit 1104 . Processing unit 1104 may be any of a variety of commercially available processors. Dual processor and other multiprocessor architectures may also be used as the processing unit 1104.

System bus 1108 may be any of several types of bus structures that may additionally be interconnected to a memory bus, a peripheral bus, and a local bus using any of a variety of commercial bus architectures. System memory 1106 includes read only memory (ROM) 1110 and random access memory (RAM) 1112 . A basic input/output system (BIOS) is stored in non-volatile memory 1110, such as ROM, EPROM, or EEPROM, and is a basic set of information that helps transfer information between components within computer 1102, such as during startup. contains routines. RAM 1112 may also include high-speed RAM, such as static RAM, for caching data.

The computer 1102 may also include an internal hard disk drive (HDD) 1114 (eg, EIDE, SATA) - the internal hard disk drive 1114 may also be configured for external use within a suitable chassis (not shown). Yes—a magnetic floppy disk drive (FDD) 1116 (e.g., for reading from or writing to a removable diskette 1118), and an optical disk drive 1120 (e.g., a CD-ROM) for reading disc 1122 or reading from or writing to other high capacity optical media such as DVDs). The hard disk drive 1114, magnetic disk drive 1116, and optical disk drive 1120 are connected to the system bus 1108 by a hard disk drive interface 1124, magnetic disk drive interface 1126, and optical drive interface 1128, respectively. ) can be connected to The interface 1124 for external drive implementation includes at least one or both of USB (Universal Serial Bus) and IEEE 1394 interface technologies.

These drives and their associated computer readable media provide non-volatile storage of data, data structures, computer executable instructions, and the like. In the case of computer 1102, drives and media correspond to storing any data in a suitable digital format. Although the description of computer readable media above refers to HDDs, removable magnetic disks, and removable optical media such as CDs or DVDs, those skilled in the art can use zip drives, magnetic cassettes, flash memory cards, cartridges, etc. It will be appreciated that other tangible media readable by the computer, such as the like, may also be used in the exemplary operating environment and any such media may include computer executable instructions for performing the methods of the present disclosure.

A number of program modules may be stored on the drive and RAM 1112, including an operating system 1130, one or more application programs 1132, other program modules 1134, and program data 1136. All or portions of the operating system, applications, modules and/or data may also be cached in RAM 1112. It will be appreciated that the present disclosure may be implemented in a variety of commercially available operating systems or combinations of operating systems.

A user may enter commands and information into the computer 1102 through one or more wired/wireless input devices, such as a keyboard 1138 and a pointing device such as a mouse 1140. Other input devices (not shown) may include a microphone, IR remote control, joystick, game pad, stylus pen, touch screen, and the like. Although these and other input devices are often connected to the processing unit 1104 through an input device interface 1142 that is connected to the system bus 1108, a parallel port, IEEE 1394 serial port, game port, USB port, IR interface, may be connected by other interfaces such as the like.

A monitor 1144 or other type of display device is also connected to the system bus 1108 through an interface such as a video adapter 1146. In addition to the monitor 1144, computers typically include other peripheral output devices (not shown) such as speakers, printers, and the like.

Computer 1102 may operate in a networked environment using logical connections to one or more remote computers, such as remote computer(s) 1148 via wired and/or wireless communications. Remote computer(s) 1148 may be a workstation, computing device computer, router, personal computer, handheld computer, microprocessor-based entertainment device, peer device, or other common network node, and generally includes It includes many or all of the components described for, but for simplicity, only memory storage device 1150 is shown. The logical connections shown include wired/wireless connections to a local area network (LAN) 1152 and/or a larger network, such as a wide area network (WAN) 1154 . Such LAN and WAN networking environments are common in offices and corporations and facilitate enterprise-wide computer networks, such as intranets, all of which can be connected to worldwide computer networks, such as the Internet.

When used in a LAN networking environment, computer 1102 connects to local network 1152 through wired and/or wireless communication network interfaces or adapters 1156. Adapter 1156 may facilitate wired or wireless communications to LAN 1152, which also includes a wireless access point installed therein to communicate with wireless adapter 1156. When used in a WAN networking environment, computer 1102 may include a modem 1158, be connected to a communicating computing device on WAN 1154, or establish communications over WAN 1154, such as over the Internet. have other means. A modem 1158, which may be internal or external and a wired or wireless device, is connected to the system bus 1108 through a serial port interface 1142. In a networked environment, program modules described for computer 1102, or portions thereof, may be stored on remote memory/storage device 1150. It will be appreciated that the network connections shown are exemplary and other means of establishing a communication link between computers may be used.

Computer 1102 is any wireless device or entity that is deployed and operating in wireless communication, eg, printers, scanners, desktop and/or portable computers, portable data assistants (PDAs), communication satellites, wireless detectable tags associated with It operates to communicate with arbitrary equipment or places and telephones. This includes at least Wi-Fi and Bluetooth wireless technologies. Thus, the communication may be a predefined structure as in conventional networks or simply an ad hoc communication between at least two devices.

Wi-Fi (Wireless Fidelity) makes it possible to connect to the Internet without wires. Wi-Fi is a wireless technology, such as a cell phone, that allows such devices, eg, computers, to transmit and receive data both indoors and outdoors, i.e. anywhere within coverage of a base station. Wi-Fi networks use a radio technology called IEEE 802.11 (a, b, g, etc.) to provide secure, reliable, and high-speed wireless connections. Wi-Fi can be used to connect computers to each other, to the Internet, and to wired networks (using IEEE 802.3 or Ethernet). Wi-Fi networks can operate in the unlicensed 2.4 and 5 GHz radio bands, for example, at 11 Mbps (802.11a) or 54 Mbps (802.11b) data rates, or in products that include both bands (dual band) .

Those skilled in the art will understand that information and signals may be represented using any of a variety of different technologies and techniques. For example, data, instructions, instructions, information, signals, bits, symbols and chips that may be referenced in the above description are voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields s or particles, or any combination thereof.

Those skilled in the art will understand that the various illustrative logical blocks, modules, processors, means, circuits, and algorithm steps described in connection with the embodiments disclosed herein are electronic hardware, (for convenience) , may be implemented by various forms of program or design code (referred to herein as software) or a combination of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the particular application and the design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

Various embodiments presented herein may be implemented as a method, apparatus, or article of manufacture using standard programming and/or engineering techniques. The term article of manufacture includes a computer program, carrier, or media accessible from any computer-readable storage device. For example, computer-readable storage media include magnetic storage devices (eg, hard disks, floppy disks, magnetic strips, etc.), optical disks (eg, CDs, DVDs, etc.), smart cards, and flash memory devices (eg, EEPROM, cards, sticks, key drives, etc.), but are not limited thereto. Additionally, various storage media presented herein include one or more devices and/or other machine-readable media for storing information.

It is to be understood that the specific order or hierarchy of steps in the processes presented is an example of example approaches. Based upon design priorities, it is to be understood that the specific order or hierarchy of steps in the processes may be rearranged within the scope of this disclosure. The accompanying method claims present elements of the various steps in a sample order, but are not meant to be limited to the specific order or hierarchy presented.

The description of the presented embodiments is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art of this disclosure, and the general principles defined herein may be applied to other embodiments without departing from the scope of this disclosure. Thus, the present disclosure is not to be limited to the embodiments presented herein, but is to be interpreted in the widest scope consistent with the principles and novel features presented herein.

Claims (15)

A method of generating speech, performed by a computing device, comprising:
obtaining text information generated by voice recognition;
identifying a text portion where a change occurs among the text information;
identifying a voice portion corresponding to the identified text portion among voice information used for voice recognition;
changing a speech portion associated with the identified speech portion; and
generating new voice information based on the changed voice portion and the remaining voice portions of the voice information;
including,
Changing a speech part associated with the identified speech part comprises:
identifying an extended text portion including the changed text portion based on a voice unit detected in a voice activity detection (VAD) process of the voice recognition; and
changing a voice part corresponding to the extended text part among the voice information;
including,
method.
According to claim 1,
Changes to the text information,
deleting a text portion included in the text information;
modifying a text portion included in the text information; or
adding a new text part to the text information;
including at least one of
method.
According to claim 2,
When the change to the text information is to delete a text part included in the text information, the changing step comprises:
deleting an audio portion corresponding to the deleted text portion;
including,
method.
According to claim 2,
When the change to the text information is to modify a text part included in the text information, the changing step includes:
modifying an audio portion corresponding to the modified text portion, taking into account an adjacent audio portion of the audio portion corresponding to the modified text portion;
including,
method.
According to claim 4,
The step of modifying an audio portion corresponding to the modified text portion,
removing an audio token corresponding to the modified text portion;
determining adjacent audio tokens of the audio token;
detecting acoustic properties of the adjacent audio token; and
generating a new audio token corresponding to the modified text portion by reflecting sound characteristics of the adjacent audio token;
including,
method.
According to claim 5,
Determining adjacent audio tokens of the audio token comprises:
determining a predetermined number of tokens before and after the audio token as adjacent audio tokens;
including,
method.
According to claim 5,
Detecting the acoustic characteristics of the adjacent audio tokens comprises:
Detecting at least one characteristic of the adjacent audio token's gender, voice loudness, tone, pitch, age, or emotional state.
method.
According to claim 2,
When the change to the text information is to modify a text part included in the text information, the changing step includes:
modifying an extended audio portion associated with the modified text portion;
containing
method.
According to claim 8,
Modifying the extended audio portion associated with the modified text portion comprises:
identifying an expanded text portion associated with the modified text portion;
removing one or more audio tokens corresponding to the expanded text portion;
determining adjacent audio tokens of the one or more audio tokens;
detecting acoustic properties of the adjacent audio token; and
generating one or more new audio tokens corresponding to the extended text portion by reflecting sound characteristics of the adjacent audio tokens;
including,
method.
delete According to claim 9,
The step of removing one or more audio tokens corresponding to the extended text portion comprises:
identifying one or more audio tokens corresponding to the extended text portion based on timestamps of voice information utilized for the voice recognition and timestamps of text information generated by the voice recognition; and
removing the one or more audio tokens identified above;
including,
method.
According to claim 2,
When the change to the text information is to add a new text part to the text information, the changing step comprises:
generating a new audio portion corresponding to the new text portion by considering an adjacent audio portion corresponding to an adjacent text portion at a position where the new text portion is to be added;
including,
method.
According to claim 12,
The step of generating a new audio part corresponding to the new text part,
identifying an adjacent text portion at which the new text portion is to be added;
determining a contiguous audio token corresponding to the contiguous text portion;
detecting acoustic properties of the adjacent audio token; and
generating a new audio token corresponding to the new text portion by reflecting sound characteristics of the adjacent audio token;
including,
method.
A computer program stored on a computer-readable storage medium, which, when executed in one or more processors, causes the one or more processors to perform the following operations for generating speech, the operations comprising:
obtaining text information generated by voice recognition;
identifying a text portion where a change has occurred among the text information;
identifying a voice part corresponding to the identified text part among voice information used for the voice recognition;
changing a speech portion associated with the identified speech portion; and
Generating new voice information based on the changed voice portion and the remaining voice portions of the voice information
including,
The operation of changing the speech part associated with the identified speech part,
identifying an extended text part including the text part where the change occurs, based on the speech unit detected in the voice recognition VAD process; and
changing a voice part corresponding to the extended text part among the voice information;
including,
A computer program stored on a computer readable storage medium.
A computing device for generating speech, comprising:
at least one processor; and
Memory
including,
The at least one processor,
acquire text information generated by speech recognition;
identifying a text portion where a change occurs among the text information;
identifying a voice part corresponding to the identified text part among voice information used for the voice recognition;
change a speech portion associated with the identified speech portion; and
configured to generate new voice information based on the changed voice portion and the remaining voice portions of the voice information;
Changing the speech part associated with the identified speech part,
identifying an extended text part including the text part where the change occurs, based on the speech unit detected in the voice recognition VAD process; and
changing a voice part corresponding to the extended text part among the voice information;
including,
Device.

Images