RU66103U1 - DEVICE FOR PROCESSING SPEECH INFORMATION FOR MODULATION OF INPUT VOICE SIGNAL BY ITS TRANSFORMATION INTO OUTPUT VOICE SIGNAL - Google Patents

Abstract

The device comprises an input device, an audio signal processing device, a control device, and a playback device. These devices are made in the form of a radio communication system. In this case, the input device is made in the form of a mobile communication terminal connected through the network of the global mobile communication system to the equipment of the cellular operator, which is connected to the server via the Internet. An audio signal processing device and a control device are installed on the server. The playback device is made in the form of a terminal connected via the Internet, the equipment of a cellular operator and the network of a global mobile communication system with a server. The device is designed to change the input voice signal, allows you to expand the functionality and enhance the gaming effect. 4 s.p. f-ly, 2 traits.

Description

The utility model relates to radio engineering and can be used as a telephone communication system for communicating between users in a game form.

A device is known for determining and correcting accent, which includes: (a) means for inputting unwanted speech images in which the aforementioned speech images are digitized, analyzed and stored in digital memory as a library of unwanted speech images; (b) means for inputting the correct speech patterns corresponding to the above unwanted speech patterns in which the above-mentioned correct speech patterns are digitized, analyzed and stored in digital memory in the form of a library of regular speech patterns; (c) means for actively recognizing incoming speech patterns, comparing the above recognized speech patterns with unwanted speech patterns stored in a digital memory as a library of unwanted speech patterns, and deleting and queuing for replacing unwanted speech patterns identified in the above incoming speech patterns images; (d) means for analyzing the aforementioned unwanted speech patterns identified in the incoming speech patterns and determining the correct speech patterns uniquely corresponding to them; and (e) means for replacing the aforementioned unwanted speech patterns identified in the incoming speech patterns with the aforementioned correct speech patterns that are unambiguously identified as corresponding to the aforementioned unwanted speech patterns, resulting in output speech patterns in which the aforementioned unwanted speech patterns removed and replaced with the correct speech patterns mentioned above. (Application for US patent No. 20070038455, G10L 13/00, publ. 15.02.2007).

In this device, the input audio signal is analyzed for the presence of predefined unwanted speech patterns, i.e. phonemes or phoneme groups that need correction, for example, representing a foreign accent. These unwanted images are then altered or completely replaced by pre-saved sound images, adjusted

on the tonality of the user's voice. The level of speech correction, i.e. the set of phonemes to be changed can be specified as needed. The device operates in two modes: the first is the training mode, i.e. saving unwanted phonemes and sound images to replace them, and the second - correction mode, i.e. in which the phoneme is modified based on the stored information. To implement this invention, computer-based software and hardware are used. The equipment, the principle of which is based on parallel signal processing, allows you to adjust the emphasis in real time with different levels of complexity, up to extremely complex systems for correcting various accents for several users, based on a multi-circuit architecture consisting of several microcircuits and boards.

The limitation of this device is the ability only to correct unwanted phonemes and the inability to regulate other speech characteristics, for example, changes in the timbre of the voice.

The closest is a voice information processing device for modulating an input voice signal by converting it into an output voice signal, comprising an input device configured to introduce an audio signal representing an input voice signal with a characteristic frequency spectrum, an audio signal processing device configured with a processor, providing a change in the frequency spectrum of the input voice signal, a database of parameters in which several sets of pa meters, each of which individually characterizes the change in the frequency spectrum by the processor, a control device that selects the desired set of parameters from the parameter database and adjusts the processor using the selected set of parameters, and a playback device configured to output an audio signal processed by the processor and representing a voice a signal with output characteristics of the frequency spectrum corresponding to the selected set of parameters (US Patent No. 5847303, G10H 1/36, publ. 12/08/1998).

This device converts the frequency range, which allows men to sing karaoke in a female voice and vice versa. In addition, the device allows you to sing a karaoke song in the voice of the selected professional singer / singer by changing the frequency spectrum. Thus, the device allows you to change the speech characteristics in accordance with the set in advance

preset parameters stored in the database of a computing device, such as a computer.

The limitations of the device are: an audio signal can only be converted into a predefined audio signal, characterized by pre-stored parameters in the database; the impossibility of playing the changed sound signal at another point in space, because the device is intended only for use in karaoke, this device in real time can only be used by one user.

The task solved by the utility model is to increase the technical and operational characteristics.

The technical result that can be obtained by performing a utility model is an extension of functionality and an increase in the number of users; providing the ability to play the modified audio signal in real time, characterized by the transmitted parameters; ensuring the reproduction of the changed sound signal at a remote point in space and amplification due to this game effect, since The user who is listening to the modified sound is a person who is not inputting a voice input.

To solve the problem with achieving the specified technical result in a known device for processing speech information for modulating an input voice signal by converting it into an output voice signal containing an input device configured to input an audio signal representing an input voice signal with a characteristic frequency spectrum, device processing a sound signal made with a processor that provides a change in the frequency spectrum of the input voice signal , a parameter database in which several sets of parameters are stored, each of which individually characterizes the change in the frequency spectrum by the processor, a control device that selects the desired parameter set from the parameter database and adjusts the processor using the selected parameter set, and a playback device configured to outputting an audio signal processed by a processor and representing a voice signal with output characteristics of the frequency spectrum corresponding to the selected set of parameters, according to the claimed technical solution, said devices are made in the form of a radio communication system, while the input device is made in the form

a mobile communication terminal connected via a network of a global mobile communication system with the equipment of a cellular operator, which is connected to a server via the Internet, an audio signal processing device and a control device are installed on the server, and a playback device is designed as a terminal connected via the Internet, equipment mobile operator, a network of a global mobile communication system with a server.

Additional embodiments of the device are possible, in which it is advisable that:

- the terminal was made in the form of a mobile communication terminal;

- a telephone node was introduced, and the terminal was made in the form of a telephone connected to the equipment of a mobile operator through a telephone node;

- the database of parameters included at least one parameter, which is an audio signal with a characteristic frequency spectrum transmitted from a mobile communication terminal;

- the database of parameters included at least one parameter, which is an audio signal with a characteristic frequency spectrum corresponding to the background of the input voice signal - the sound of a passing train, metro, tree noise, street noise.

These advantages, as well as the features of this utility model are illustrated by the best option for its implementation with reference to the accompanying drawings.

Figure 1 depicts a functional diagram of the claimed device;

Figure 2 - block diagram of the algorithm of the server.

The device (Fig. 1) for processing speech information for modulating an input voice signal by converting it into an output voice signal comprises an input device 1 configured to introduce an audio signal representing an input voice signal with a characteristic frequency spectrum. The audio signal processing device 2 is made on the basis of a processor, providing a change in the frequency spectrum of the input voice signal. In the parameter database 3, several sets of parameters are stored, each of which individually characterizes the frequency spectrum change by the processor of the device 2. The control device 4 selects the desired parameter set from the parameter database 3 and adjusts the processor using the selected parameter set. The playback device 5 is configured to output an audio signal,

processed by the processor and representing a voice signal with the output characteristics of the frequency spectrum corresponding to the selected set of parameters.

Mentioned devices 1, 2, 4, 5 are made in the form of an extensive radio communication system. The input device 1 is made in the form of a mobile communication terminal connected via a network 6 of the global mobile communication system to the equipment 7 of the mobile operator, which is connected to the server 9 through the Internet 8. The audio signal processing device 2 and the control device 4 with the database 3 are installed on server 9. The playback device 5 is made in the form of a terminal connected via the Internet 8, equipment 7 of the mobile operator and network 6 of the global mobile communication system with server 9.

Playback device 5 - the terminal can be made in the form of a mobile communication terminal.

A telephone node 10 can be introduced, and a playback device 5, the terminal, can be made in the form of a telephone connected to the equipment 7 of the cellular operator via the telephone node 10.

The parameter database 3 may include at least one parameter representing an audio signal with a characteristic frequency spectrum transmitted from an input device 1 — a mobile communication terminal.

In addition, the database 3 of the parameter data may include at least one parameter, which is an audio signal with a characteristic frequency spectrum corresponding to the background of the input voice signal - the sound of a passing train, metro, tree noise, street noise.

Since the operation of devices 1, 2, 3, 4, 5 is described in detail in the closest analogue, the operation of the claimed device is described in more detail below.

The device operates (figure 1) as follows.

To solve the problem with the achievement of the specified technical result, the claimed device performs the following actions:

- receiving a call from the user of the device 1 - mobile communication terminal to equipment 7 through the network 6 of the global mobile communication system,

- receiving a call from the equipment 7 of the telecom operator by the remote server 9 via the Internet 8,

- the dialogue of the server 9 with the user of the device 1 through the menu, designed to find out the number of the mobile communication terminal in order to obtain a sample of the input voice signal of the user of the communication terminal indicating the number of the played user of the device 5 playback - mobile communication terminal or telephone,

- voice call of the user of device 1 with device number 5 to server 9 via network 6, equipment 7 of network 8 of the Internet,

- saving a sample of the input voice signal from the device 1 on the server 9,

- comparison in the database 3 of the data on the server 9 of the sample input voice signal with the desired output voice signal for the further formation of a set of parameters, converting the spectrum of the input voice signal,

- the formation of a set of parameters necessary for implementing changes in the frequency spectrum of the input audio signal of the user of the device 1, ensuring maximum similarity specified by the user of the device 1 of the output voice signal,

- a voice call of the played user of the device 5 with the number indicated by the user of the device 1 through the server 9 through the network 8 of the Internet, equipment 7 of the communication operator and network 6,

- voice connection of the user of the device 1 with the played by the user of the device 5 of the communication terminal through the server 9,

- changing the frequency spectrum of the input audio signal of the voice of the user of the device 1 using a set of parameters in real time and transmitting the modified output voice signal from the server 9 via the Internet 8 network, the equipment of the communication operator 7 and the network 6 to the device 5.

In addition, the database 3 of the parameters of the server 9 may include at least one parameter representing an audio signal with a characteristic frequency spectrum transmitted from the input device 1 - a mobile communication terminal. In this case, the specified voice sample is transmitted to the server 9 directly by the user of any device 1.

In addition, the database 3 of the parameters of the server 9 may include at least one parameter, which is an audio signal with a characteristic frequency spectrum corresponding to the background of the input voice signal - the sound of the passing

trains, metro, tree noise, street noise. This background can additionally be superimposed on the output voice signal transmitted to the device 5.

Consider a specific example of the implementation of the claimed technical solution, for example, when a given voice sample is transmitted directly to the server 9 by a user of a device 1.

The user of the device 1, by dialing the number of the server 9, registered on the equipment 7 of the communication operator, makes a voice call to the server 9, through the network 6 of the communication operator, equipment 7 of the communication operator and the Internet 8.

Immediately after the initialization of the voice communication channel using block 11 (Fig. 2) between the communication device 1 and server 3 on the remote server 3, the voice menu 12 starts to work.

The user of the device 1 hears through the speaker of the mobile communication terminal a description of the available menu items and information about the actions that must be done to select this menu item. For example: “In order to make a call to a subscriber to receive his voice sample, press the number 1, if you want to select a voice from the ones already recorded, then press the number 2”. To navigate through the menu items, device 1 — the mobile communication terminal supports tone dialing.

For further correction of the input audio signal, it is necessary to obtain a voice sample, which should be similar to the voice of any user of device 1.

For this, the user of the communication device 1 through the menu and tone dialing selects the desired menu item and control is transferred to the block 14 dialing. The user of the device 1 dials the number of the analyzed subscriber of the communication terminal 1. The number is entered in the federal format on the keyboard of the communication terminal 1 and transmitted in the form of tones via the network of the communication operator 2, the equipment of the communication operator 2 and the Internet to the remote server 3. Next, the number is checked for correctness and, if it is correct, the control of the communication terminal 1 is transferred to the unit 15 Obtaining the sample of the analyzed subscriber (AA), otherwise Block 14 Dialing requests the user of the device 1 to repeat the number entry.

Block 15 receiving sample AA asks the user of device 1 to utter an introductory phrase for a telephone call of the analyzed subscriber of any device 1 or device 5 of communication and informs that the record of the introductory phrase

will start after the signal, at the end of recording, the user should, for example, press "#". The introductory phrase may be as follows: "Hello, please call Lena on the phone."

After receiving the AA number from the dialing unit 14 and the introductory phrase, the AA sample receiving unit 15 initiates a voice call to the indicated AA number of the communication device 1 via the Internet 8, the equipment of the communication operator 7 and the network 6. In this case, the user of the communication device 1 can remain on the line and hears server 9 trying to get an AA voice sample.

If the voice call of the indicated AA number was not initialized, the remote server 9 retries the connection initialization attempt.

If the voice call of the indicated AA number was initialized, the remote server 9 loses the AA input phrase and the pre-recorded phrase in the database 3, which should trigger the AA response. The AA voice sample is recorded on the server 9 and the established voice communication channel is closed.

At the end of the communication session with AA, the server 9 through the menu asks the user of the device 1 confirmation that the communication was carried out precisely with the desired analyzed subscriber. If the answer is no, sample acquiring unit 15 returns control to the dialer 14.

Having received a sample of the sound wave of the voice of the analyzed subscriber, the sample receiving unit 15 of the sample AA extracts from it a sample of the voice of the analyzed subscriber. Voice sample is selected based on the analysis of the amplitude of the sound wave. The sample necessarily begins with zero amplitude, contains at least 5-6 spikes in amplitude, which corresponds to the pronunciation of 5-6 words and ends with a voice wave with an amplitude close to zero. Next, the control of the server 9 is transferred to the block 16 receiving the sample.

Block 16 receiving the sample plays the sample voice AA to the user of the device 1.

Next, the sample obtaining unit 16 asks the user of the device 1 to repeat the text of the voice sample AA and informs that the recording of the voice sample of the user of the device 1 will begin after the signal, at the end of the recording the user should press "#".

At the end of recording the sample voice of the user of the device 1, his voice sample is recorded on the server 9 for further analysis by block 17 of the formation of a set of parameters.

Block 17 forming a set of parameters compares the two samples obtained to form a set of parameters necessary for converting the sound wave of the voice of the user of the device 1 into a sound wave with a tonal coloring of the voice AA.

As a result of the analysis, the parameter set formation unit 17 generates a parameter set for changing the frequency spectrum, which is stored in the database 3 of the server 9 in the parameter set table and is marked as an “active parameter set” for further use by the conversation unit 21.

Next, the control of the server 9 is transferred to the block 12 of the menu. The user of the device 1 through the menu and tone dialing selects the menu item of the call of the played subscriber of the device 5, while the control of the remote server 9 is transferred to block 19 there is a set of parameters.

This block 19 checks if at the moment the set of parameters marked as active. If there is no such set of parameters, the user of device 1 is informed by playing a sound recording: “You have not yet selected a voice sample into which you want to convert your voice, select a voice sample and only after that select the menu item“ Call to played subscriber ”, which is not active a set of parameters, and server 9 control is transferred to the menu block 12. If the check showed that there is an active set of parameters, then the server 9 is transferred to the dialing unit 20.

The user of the device 1 then dials the number of the played subscriber of the device 5. The number is entered in the federal format on the keyboard of the mobile communication terminal and transmitted in the form of tones via the network 6, the equipment of the communication operator 7 and the Internet 8 to the server 9. Next, the number is checked for correctness and if it is correct, control of the device 1 is transferred to the conversation unit 21, otherwise the dialing unit 20 asks the user of the device 1 to repeat the number entry.

Having received the number of the played subscriber of the device 5, the conversation block 21 initiates a voice call of the specified number of the played subscriber of the device 5 via the Internet 8, equipment 7 of the communication operator and network 6. In this case, the user of the device 1 can remain on the line and hear server 9 trying to initiate communication with played by the subscriber of the device 5.

If the voice call initialization of the indicated number of the played subscriber of the device 5 did not occur, then the server 9 retries the connection initialization attempt, for example, two more times.

If the voice call initialization of the indicated number of the played subscriber of the device 5 has occurred, then the server 9 connects to the voice channel with the played subscriber of the device 5 of the user of the device 1, the sound processing device 2 and the control device 4 of the server 9 are turned on (Fig. 1), and when the pronunciation of any phrase by the user of device 1 when transmitting this sound wave to the played subscriber of device 5, its tonal coloring changes based on the active set of parameters of base 3 given s.

Thus, the effect of talking in a different voice to the user of the device 1 with the played subscriber of the device 5 is achieved.

Also, the user of the device 1 within the framework of the claimed device for drawing can use the menu to select a sample of the voice previously stored in the database 3 of the server 9. These can be samples of the voices of famous people, singers, etc. The user of the device 1 can also, for example, sing, an excerpt of a song, and like the work of the closest analogue, an excerpt of a song can be transmitted to the played subscriber of the device 5.

The selection of samples of famous people is carried out by transferring control of the server 9 from the block 22 of the voice selection block 23 of the menu (figure 2). The voice selection unit 22 receives control of the server 9 when the user of the device 1 selects the menu item “Selecting a Saved Voice” of the menu unit 12.

The user of the device 1 can listen through the dynamics of his mobile communication terminal to the list of voices previously available for selection and information about the actions that need to be done to select this menu item.

After the user of device 1 selects one of the previously saved voices, control of the remote server 9 is transferred to block 24 — setting a set of parameters.

The parameter set installation unit 24 marks the previously saved parameter set corresponding to the voice selected by the user, active, and transfers server control 9 to the menu block 12.

The logical unit 25 to end the call when the connection of the server 9 with the device 1 is disconnected transfers control of the server 9 to the call termination unit 26, which ends the message session of the server 9 with the equipment 7 of the communication operator via the Internet 8.

At the end of the communication session with the played subscriber of device 5, the remote server 9 can make a repeated call to the played subscriber of device 5 to avoid misunderstandings and plays a pre-recorded phrase informing that the previous call was a rally.

Thus, the claimed device can significantly expand the functionality of the closest analogue and simultaneously change both the transmitted speech and singing. The device allows you to play the modified sound signal in real time, characterized by the transmitted parameters, for example, of any analyzed subscriber, and not only those that are previously stored in the database 3 data. In addition, the device allows you to enhance the game effect, since listening to the output sound signal is carried out by a person who is not aware of the rally.

The claimed device is new because it is not known to use the combination of its essential features in any one technical solution, and the addition of the closest analogue with new connections, and the implementation of its individual devices in the form of specific design solutions allows you to create a radio communication system that ensures the achievement of a new qualitative and quantitative technical result.

The most successfully claimed voice information processing device for modulating an input voice signal by converting it into an output voice signal is industrially applicable in GSM cellular communication systems.

Claims (5)

1. A voice information processing device for modulating an input voice signal by converting it into an output voice signal, comprising an input device configured to introduce an audio signal representing an input voice signal with a characteristic frequency spectrum, an audio signal processing device configured with a processor providing changing the frequency spectrum of the input voice signal, a database of parameters in which several sets of parameters are stored, each of which x individually characterizes the change in the frequency spectrum by the processor, a control device that selects the desired set of parameters from the parameter database and configures the processor of the audio signal processing device using the selected set of parameters, and a playback device configured to output an audio signal processed by the processor and representing a voice a signal with output characteristics of the frequency spectrum corresponding to the selected set of parameters, characterized in that the aforementioned devices are made in the form of a radio communication system, wherein the input device is made in the form of a mobile communication terminal connected via a global mobile communication system network to the equipment of a mobile operator, which is connected to the server via the Internet, an audio signal processing device, and a database control device installed on the server, and the playback device is made in the form of a terminal connected via the Internet, the equipment of the mobile operator and the network of the global system mobile th communication with the server. 2. The device according to claim 1, characterized in that the terminal is made in the form of a mobile communication terminal. 3. The device according to claim 1, characterized in that the telephone node is introduced, and the terminal is made in the form of a telephone connected to the equipment of the cellular operator via the telephone node. 4. The device according to claim 1, characterized in that the parameter database includes at least one parameter, which is an audio signal with a characteristic frequency spectrum transmitted from a mobile communication terminal. 5. The device according to claim 1, characterized in that the parameter database includes at least one parameter representing an audio signal with a characteristic frequency spectrum corresponding to the background of the input voice signal — the sound of a passing train, metro, tree noise, street noise.