CN112562633A

CN112562633A - Singing synthesis method and device, electronic equipment and storage medium

Info

Publication number: CN112562633A
Application number: CN202011384883.2A
Authority: CN
Inventors: 顾宇
Original assignee: Beijing Youzhuju Network Technology Co Ltd
Current assignee: Beijing Youzhuju Network Technology Co Ltd
Priority date: 2020-11-30
Filing date: 2020-11-30
Publication date: 2021-03-26
Anticipated expiration: 2040-11-30
Also published as: CN112562633B

Abstract

The application discloses a singing synthesis method, a singing synthesis device, electronic equipment and a storage medium. The method comprises the following steps: acquiring song information to be synthesized, wherein the song information to be synthesized comprises a lyric text and melody information; obtaining the characteristics of a Mel filter bank and actual fundamental frequency information according to song information to be synthesized; and obtaining a sound waveform according to the characteristics of the Mel filter bank and the actual fundamental frequency information, and obtaining a synthesized song according to the sound waveform. The characteristics of the Mel filter bank and the actual fundamental frequency information are obtained through the song information to be synthesized, the characteristics of the Mel filter bank and the fundamental frequency information are combined to obtain the sound waveform, and the synthesized song is obtained according to the sound waveform, so that the fundamental frequency information is considered in the singing synthesis, the intonation quality of the synthesized song is guaranteed, and the singing synthesis requirement of a user is met.

Description

Singing synthesis method and device, electronic equipment and storage medium

Technical Field

The embodiments of the present disclosure relate to the field of data processing technologies, and in particular, to a singing synthesis method and apparatus, an electronic device, and a storage medium.

Background

Speech synthesis, also known as Text To Speech (TTS) technology, is capable of converting Text To Speech, i.e. converting Text information into audible sound information, relating To acoustics, phonetics, digital signal processing and computer science.

At present, when singing voice synthesis is carried out, an end-to-end voice synthesis system is generally adopted, so that the situation of inaccurate pitch usually exists in the singing synthesis process through the voice synthesis system, the quality of synthesized songs is influenced, and the experience effect of a user is reduced.

Disclosure of Invention

The embodiment of the disclosure provides a singing synthesis method and device, electronic equipment and a storage medium, so as to obtain a synthesized song with high accuracy and quality.

In a first aspect, an embodiment of the present disclosure provides a singing synthesis method, including:

acquiring song information to be synthesized, wherein the song information to be synthesized comprises a lyric text and melody information;

obtaining the characteristics of a Mel filter bank and actual fundamental frequency information according to song information to be synthesized;

and obtaining a sound waveform according to the characteristics of the Mel filter bank and the actual fundamental frequency information, and obtaining a synthesized song according to the sound waveform.

In a second aspect, an embodiment of the present disclosure further provides a singing synthesis apparatus, including:

the system comprises a song information acquisition module to be synthesized, a song information processing module and a song information processing module, wherein the song information to be synthesized comprises a lyric text and melody information;

the Mel filter bank characteristic and actual fundamental frequency information acquisition module is used for acquiring the Mel filter bank characteristic and the actual fundamental frequency information according to the song information to be synthesized;

and the singing synthesis module is used for obtaining a sound waveform according to the characteristics of the Mel filter bank and the actual fundamental frequency information and obtaining a synthesized song according to the sound waveform.

In a third aspect, an embodiment of the present disclosure further provides an electronic device, where the electronic device includes:

one or more processors;

a storage device for storing one or more programs,

when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement a method according to any embodiment of the present disclosure.

In a fourth aspect, embodiments of the present disclosure provide a computer-readable storage medium, on which a computer program is stored, which when executed by a processor, implements a method according to any of the embodiments of the present disclosure.

In the embodiment of the disclosure, the characteristics of the mel filter bank and the actual fundamental frequency information are obtained through the song information to be synthesized, and the characteristics of the mel filter bank and the fundamental frequency information are combined to obtain the sound waveform, so that the synthesized song is obtained according to the sound waveform, the fundamental frequency information is considered in the singing synthesis, the intonation quality of the synthesized song is ensured, and the singing synthesis requirement of a user is met.

Drawings

The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It should be understood that the drawings are schematic and that elements and features are not necessarily drawn to scale.

Fig. 1(a) is a flow chart of a singing synthesis method provided by an embodiment of the present disclosure;

FIG. 1(b) is a schematic diagram of melody information provided by an embodiment of the disclosure;

FIG. 1(c) is a schematic illustration of sound waveforms provided by an embodiment of the present disclosure;

FIG. 2 is a flowchart illustrating another method for generating a main melody according to an embodiment of the present disclosure;

fig. 3 is a schematic structural diagram of a singing synthesis apparatus provided in an embodiment of the present disclosure;

fig. 4 is a schematic structural diagram of an electronic device provided in an embodiment of the present disclosure.

Detailed Description

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.

It should be understood that the various steps recited in the method embodiments of the present disclosure may be performed in a different order, and/or performed in parallel. Moreover, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present disclosure is not limited in this respect.

The term "include" and variations thereof as used herein are open-ended, i.e., "including but not limited to". The term "based on" is "based, at least in part, on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Relevant definitions for other terms will be given in the following description.

It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.

It is noted that references to "a", "an", and "the" modifications in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that "one or more" may be used unless the context clearly dictates otherwise.

The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.

Example one

Fig. 1(a) is a flowchart of a singing synthesis method provided in an embodiment of the present disclosure, and this embodiment is applicable to a case of performing singing synthesis, and this method may be executed by a singing synthesis apparatus provided in an embodiment of the present disclosure, and this apparatus may be implemented in software and/or hardware, and may be generally integrated in a computer device. The method of the embodiment of the disclosure specifically comprises the following steps:

as shown in fig. 1(a), the method in the embodiments of the present disclosure may include the following steps:

step 101, acquiring song information to be synthesized.

Specifically, the song information to be synthesized in the embodiment includes a lyric text and melody information, where the melody information specifically refers to music information of the song, such as a note sequence. For example, the lyric text included in the acquired song information to be synthesized is "i love home", and the sequence of notes included is as shown in fig. 1 (b). In the embodiment, the example that each lyric corresponds to one note group, the note group includes at least one note is described, so that it can be determined that the lyric "me" corresponds to a quarter note

The 'love' corresponds to four

"ancestor" corresponds to two octant notes

The "nation" corresponds to the sixteenth note

. Of course, the embodiment is merely an example, and the specific contents of the lyric text and the melody information included in the song information to be synthesized are not limited.

Note that, in this embodiment, the pitch of each note can also be known from the note sequence, and in practical applications, the types of pitch include: do, Ri, Mi, Fa, Sol, La, Xi, and can be used to mark the location of notes on the radio spectrum, as shown in FIG. 1(b), the first note "

"corresponding pitch is Mi, second note"

"corresponding pitch of a soundIs Fa, third note "

"pitch of Sol, fourth note"

"pitch corresponding to Fa.

And 102, obtaining the characteristics of the Mel filter bank and the actual fundamental frequency information according to the song information to be synthesized.

Optionally, obtaining Mel-Filter banks characteristics and actual fundamental frequency information according to the song information to be synthesized may include: predicting song information to be synthesized through a pre-trained acoustic model to obtain characteristics of a Mel filter bank and fundamental frequency difference information; and acquiring preset base frequency information corresponding to the song information to be synthesized, and adding the preset base frequency information and the base frequency difference information to obtain actual base frequency information.

Optionally, before predicting song information to be synthesized through a pre-trained acoustic model to obtain mel filter bank characteristics and fundamental frequency difference information, the method further includes: acquiring first sample information, wherein the first sample information comprises sample song information, and a Mel filter bank characteristic and a fundamental frequency difference value corresponding to the sample song information; and training the acoustic model according to the first sample information to determine mapping parameters of the song information in the acoustic model, characteristics of the Mel filter bank and the fundamental frequency difference.

Specifically, in the embodiment, before predicting song information to be synthesized through a pre-trained acoustic model to obtain mel-filter bank characteristics and fundamental frequency difference information, the acoustic model needs to be trained first, in a specific training process, first sample information is obtained, the first sample information comprises sample song information and mel-filter bank characteristics and fundamental frequency differences corresponding to the sample song information, and the sample song information comprises sample lyric texts and sample melody information. The method for acquiring the characteristics of the mel filter bank and the fundamental frequency difference value in the first sample information is specifically as follows: because the voice corresponding to the sample song information and the theoretical fundamental frequency information corresponding to the voice are known, the characteristics of the sample Mel filter bank and the actual fundamental frequency information of the sample are obtained by extracting the characteristics of the voice information, and the fundamental frequency difference value is obtained by calculating the difference value between the actual fundamental frequency information and the theoretical fundamental frequency information. And training the acoustic model by using the sample song information, and the Mel filter bank characteristics and the fundamental frequency difference value corresponding to the sample song information, thereby determining the mapping parameters of the song information, the Mel filter bank characteristics and the fundamental frequency difference value in the acoustic model.

Optionally, after obtaining the mel filter bank feature and the fundamental frequency difference information by predicting the song information to be synthesized through a pre-trained acoustic model, the method further includes: adjusting the fundamental frequency difference information according to a user instruction to obtain adjusted fundamental frequency difference information; adding the preset fundamental frequency information and the fundamental frequency difference information to obtain actual fundamental frequency information, wherein the actual fundamental frequency information comprises the following steps: and adding the preset fundamental frequency information and the adjusted fundamental frequency difference information to obtain actual fundamental frequency information.

Specifically, in the embodiment, when the mel filter bank characteristics and the actual fundamental frequency information are obtained according to the song information to be synthesized, the adopted method specifically includes predicting the song information to be synthesized through a pre-trained acoustic model, obtaining the song information to be synthesized and the corresponding mel filter bank characteristics and fundamental frequency difference information based on the mapping parameters of the song information in the acoustic model and the mel filter bank characteristics and the fundamental frequency difference, and obtaining the actual fundamental frequency information by adding the preset fundamental frequency information and the fundamental frequency difference information because the preset fundamental frequency information corresponding to the song to be synthesized, namely the theoretical fundamental frequency information, can also be obtained under the condition that the song information is known. In addition, due to the adjustability of the fundamental frequency information, the fundamental frequency difference information can be adjusted according to a user instruction to obtain the adjusted fundamental frequency difference information, so that the preset fundamental frequency information and the adjusted fundamental frequency difference information can be added to obtain the implementation fundamental frequency information in the process of obtaining the actual fundamental frequency information.

It should be noted that, other factors are also involved in the model prediction process, such as time length, and under the condition that the song information is known, the singing time length can also be obtained according to the word number of the lyric text and the note contained in the melody information, and in the process of predicting the song information to be synthesized through the acoustic model, the accuracy of the predicted characteristics of the mel filter bank and the fundamental frequency difference information can be further ensured by adding the time length.

And 103, acquiring a sound waveform according to the characteristics of the Mel filter bank and the actual fundamental frequency information, and acquiring a synthesized song according to the sound waveform.

Optionally, obtaining the sound waveform according to the mel filter bank characteristic and the actual fundamental frequency information includes: and predicting actual fundamental frequency information and Mel filter bank characteristics through a pre-trained vocoder model to obtain a sound waveform.

Optionally, before predicting actual fundamental frequency information and mel filter bank characteristics through a pre-trained vocoder model to obtain a sound waveform, the method further includes: acquiring second sample information, wherein the second sample information comprises a sample sound waveform, and a Mel filter bank characteristic and periodic pulse information corresponding to the sample sound waveform; the vocoder model is trained based on the second sample information to determine mapping parameters of the sound waveform to Mel filter bank characteristics and periodic pulse information in the vocoder model.

Specifically, in this embodiment, before predicting actual fundamental frequency information and mel filter bank characteristics through a pre-trained vocoder model to obtain a sound waveform, the vocoder model needs to be trained first, and the specific training process is to obtain second sample information, where the second sample information includes a sample sound waveform, and mel filter bank characteristics and periodic pulse information corresponding to the sample sound waveform. The manner of obtaining the periodic pulse information and the mel filter bank characteristics in the second sample information is specifically as follows: since the sound waveform in the second sample information may specifically correspond to the speech in the first sample, the mel filter bank feature may specifically be obtained by performing feature extraction on the speech information in the first sample; the periodic pulse information may be, specifically, actual fundamental frequency information obtained by extracting the voice information in the first sample, and obtained by performing periodic transformation by the pulser. The vocoder model is trained by training a sample acoustic waveform and mel filter bank characteristics and periodic pulse information corresponding to the sample acoustic waveform to determine mapping parameters of the acoustic waveform and mel filter bank characteristics and periodic pulse information in the vocoder model.

Optionally, before predicting actual fundamental frequency information and mel filter bank characteristics through a pre-trained vocoder model to obtain a sound waveform, the method further includes: the practical fundamental frequency information is subjected to periodic transformation through a pulser to obtain periodic pulse information; predicting actual fundamental frequency information and Mel filter bank characteristics through a pre-trained vocoder model to obtain a sound waveform, comprising: and predicting the periodic pulse information and the characteristics of the Mel filter bank through a pre-trained vocoder model to obtain a sound waveform.

Specifically, in the present embodiment, after obtaining the mel filter bank characteristic and the actual fundamental frequency information by predicting song information to be synthesized through the acoustic model, the pulser may first perform periodic transformation on the actual fundamental frequency information to obtain periodic pulse information, and in the present embodiment, when obtaining a sound waveform by predicting the periodic pulse information and the mel filter bank characteristic through a pre-trained vocoder, the adopted method is specifically: the periodic pulse information and the mel filter bank characteristics are predicted through a pre-trained vocoder model, and the sound waveform corresponding to the mel filter bank characteristics and the periodic pulse information is obtained based on the mapping parameters of the sound waveform, the mel filter bank characteristics and the periodic pulse information in the vocoder model, as shown in fig. 1(c), which is a schematic diagram of the sound waveform obtained through prediction by the vocoder model. Whereas in case the sound waveform is known, the synthesized song can be obtained directly. Therefore, in the embodiment, the song information to be synthesized including the lyric text and the melody information is sequentially processed through the acoustic model and the vocoder model, and the synthetic song corresponding to the song information to be synthesized is finally obtained, wherein the synthetic song is displayed in a voice form, that is, the process of voice synthesis is realized. And the fundamental frequency information is involved in the voice synthesis process, and the fundamental frequency information can be adjusted according to the user requirements in the synthesis process, so that the accuracy and quality of the synthesized song are higher.

Example two

Fig. 2 is a flowchart of another singing synthesis method provided in the second embodiment of the present disclosure, which may be combined with various alternatives in the foregoing embodiments, where after obtaining the sound waveform according to the mel-filter bank characteristics and the actual fundamental frequency information, and obtaining the synthesized song according to the sound waveform, the second embodiment of the present disclosure further includes: the synthesized song is detected.

As shown in fig. 2, the method of the embodiment of the present disclosure specifically includes:

step 201, acquiring the song information to be synthesized.

Step 202, obtaining the characteristics of the Mel filter bank and the actual fundamental frequency information according to the song information to be synthesized.

Optionally, obtaining the mel filter bank characteristics and the actual fundamental frequency information according to the song information to be synthesized may include: predicting song information to be synthesized through a pre-trained acoustic model to obtain Mel-Filter banks characteristics and fundamental frequency difference information; and acquiring preset base frequency information corresponding to the song information to be synthesized, and adding the preset base frequency information and the base frequency difference information to obtain actual base frequency information.

And step 203, obtaining a sound waveform according to the characteristics of the Mel filter bank and the actual fundamental frequency information, and obtaining a synthesized song according to the sound waveform.

Step 204, detecting the synthesized song.

After the synthetic song is obtained, the synthetic song is detected, specifically, whether the synthetic song can be played normally or whether abnormal conditions such as messy codes exist in the synthetic song are detected, and when the condition that the synthetic song cannot be played normally is determined through detection, the reason for the above conditions may be that communication connection is interrupted or hardware equipment fails. At the moment, the alarm can be given in time to prompt a user to overhaul the equipment in time.

In the embodiment of the disclosure, the characteristics of the mel filter bank and the actual fundamental frequency information are obtained through the song information to be synthesized, and the characteristics of the mel filter bank and the fundamental frequency information are combined to obtain the sound waveform, so that the synthesized song is obtained according to the sound waveform, the fundamental frequency information is considered in the singing synthesis, the intonation quality of the synthesized song is ensured, and the singing synthesis requirement of a user is met. And after the synthetic songs are obtained, the quality of the synthetic songs can be further ensured by detecting the synthetic songs.

EXAMPLE III

Fig. 3 is a schematic structural diagram of a singing synthesis apparatus provided in an embodiment of the present disclosure. The apparatus may be implemented in software and/or hardware and may generally be integrated in an electronic device performing the method. As shown in fig. 3, the apparatus may include:

a song information to be synthesized obtaining module 310, configured to obtain song information to be synthesized, where the song information to be synthesized includes a lyric text and melody information;

a mel filter bank characteristic and actual fundamental frequency information obtaining module 320, configured to obtain the mel filter bank characteristic and the actual fundamental frequency information according to the song information to be synthesized;

and the singing synthesis module 330 is configured to obtain a sound waveform according to the mel filter bank characteristics and the actual fundamental frequency information, and obtain a synthesized song according to the sound waveform.

Optionally, on the basis of the above technical solution, the mel filter bank feature and actual fundamental frequency information obtaining module includes:

the first acquisition submodule is used for predicting song information to be synthesized through a pre-trained acoustic model to obtain the characteristics of a Mel filter bank and fundamental frequency difference information;

and the second acquisition submodule is used for acquiring preset base frequency information corresponding to the song information to be synthesized and adding the preset base frequency information and the base frequency difference information to obtain actual base frequency information.

Optionally, on the basis of the above technical solution, the apparatus further includes a fundamental frequency difference information obtaining module, configured to adjust the fundamental frequency difference information according to a user instruction, and obtain adjusted fundamental frequency difference information;

and the second acquisition submodule is used for adding the preset fundamental frequency information and the adjusted fundamental frequency difference information to obtain actual fundamental frequency information.

Optionally, on the basis of the above technical solution, the singing synthesis module is configured to predict actual fundamental frequency information and mel filter bank characteristics through a pre-trained vocoder model to obtain a sound waveform.

Optionally, on the basis of the above technical solution, the apparatus further includes a periodic pulse information obtaining module, configured to: the practical fundamental frequency information is subjected to periodic transformation through a pulser to obtain periodic pulse information;

and the singing synthesis module is used for predicting periodic pulse information and characteristics of a Mel filter bank through a pre-trained vocoder model to obtain a sound waveform.

Optionally, on the basis of the above technical solution, the apparatus further includes a first training module, configured to obtain first sample information, where the first sample information includes sample song information, and a mel filter bank characteristic and a fundamental frequency difference value corresponding to the sample song information;

and training the acoustic model according to the first sample information to determine mapping parameters of the song information in the acoustic model, characteristics of the Mel filter bank and the fundamental frequency difference.

Optionally, on the basis of the above technical solution, the apparatus further includes a second training module, configured to obtain second sample information, where the second sample information includes a sample sound waveform, and mel filter bank features and periodic pulse information corresponding to the sample sound waveform;

the vocoder model is trained based on the second sample information to determine mapping parameters of the sound waveform to Mel filter bank characteristics and periodic pulse information in the vocoder model.

The singing synthesis device provided by the embodiment of the disclosure is the same as the singing synthesis method provided by the embodiments, the technical details which are not described in detail in the embodiments of the disclosure can be referred to the embodiments, and the embodiments of the disclosure have the same beneficial effects as the embodiments.

Example four

Referring now to FIG. 4, a block diagram of an electronic device 400 suitable for use in implementing embodiments of the present disclosure is shown. The electronic device in the embodiment of the present disclosure may be a device corresponding to a backend service platform of an application program, and may also be a mobile terminal device installed with an application program client. In particular, the electronic device may include, but is not limited to, a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (personal digital assistant), a PAD (tablet computer), a PMP (portable multimedia player), a vehicle-mounted terminal (e.g., a car navigation terminal), etc., and a stationary terminal such as a digital TV, a desktop computer, etc. The electronic device shown in fig. 4 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.

As shown in fig. 4, electronic device 400 may include a processing device (e.g., central processing unit, graphics processor, etc.) 401 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)402 or a program loaded from a storage device 408 into a Random Access Memory (RAM) 403. In the RAM 403, various programs and data necessary for the operation of the electronic apparatus 400 are also stored. The processing device 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input/output (I/O) interface 405 is also connected to bus 404.

Generally, the following devices may be connected to the I/O interface 405: input devices 406 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; an output device 407 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 408 including, for example, tape, hard disk, etc.; and a communication device 409. The communication means 409 may allow the electronic device 400 to communicate wirelessly or by wire with other devices to exchange data. While fig. 4 illustrates an electronic device 400 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided.

In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a non-transitory computer readable medium, the computer program containing program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication device 409, or from the storage device 408, or from the ROM 402. The computer program performs the above-described functions defined in the methods of the embodiments of the present disclosure when executed by the processing device 401.

It should be noted that the computer readable medium in the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer readable signal medium may comprise a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.

In some embodiments, the clients, servers may communicate using any currently known or future developed network Protocol, such as HTTP (HyperText Transfer Protocol), and may interconnect with any form or medium of digital data communication (e.g., a communications network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network.

The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device.

The computer readable medium carries one or more programs which, when executed by the electronic device, cause the internal processes of the electronic device to perform: acquiring song information to be synthesized, wherein the song information to be synthesized comprises a lyric text and melody information; obtaining the characteristics of a Mel filter bank and actual fundamental frequency information according to the song information to be synthesized; and obtaining a sound waveform according to the characteristics of the Mel filter bank and the actual fundamental frequency information, and obtaining a synthesized song according to the sound waveform.

Computer program code for carrying out operations for the present disclosure may be written in any combination of one or more programming languages, including but not limited to an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in the embodiments of the present disclosure may be implemented by software or hardware. Where the name of an element does not in some cases constitute a limitation on the element itself.

The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), systems on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), and the like.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

According to one or more embodiments of the present disclosure, [ example 1 ] there is provided a singing synthesis method comprising:

obtaining the characteristics of a Mel filter bank and actual fundamental frequency information according to the song information to be synthesized;

According to one or more embodiments of the present disclosure, [ example 2 ] there is provided the method of example 1, the obtaining of mel-filter bank features and actual fundamental frequency information from the song information to be synthesized, comprising:

predicting the song information to be synthesized through a pre-trained acoustic model to obtain the characteristics of the Mel filter bank and the fundamental frequency difference information;

and acquiring preset fundamental frequency information corresponding to the song information to be synthesized, and adding the preset fundamental frequency information and the fundamental frequency difference information to obtain the actual fundamental frequency information.

According to one or more embodiments of the present disclosure, [ example 3 ] there is provided the method of example 2, further comprising, after predicting the song information to be synthesized by a pre-trained acoustic model to obtain the mel-filter bank characteristics and fundamental frequency difference information:

adjusting the fundamental frequency difference information according to a user instruction to obtain adjusted fundamental frequency difference information;

the adding the preset fundamental frequency information and the fundamental frequency difference information to obtain the actual fundamental frequency information includes:

and adding the preset fundamental frequency information and the adjusted fundamental frequency difference information to obtain the actual fundamental frequency information.

According to one or more embodiments of the present disclosure, [ example 4 ] there is provided the method of example 1, the obtaining a sound waveform according to the mel filter bank features and the actual fundamental frequency information, comprising:

and predicting the actual fundamental frequency information and the characteristics of the Mel filter bank through a pre-trained vocoder model to obtain the sound waveform.

According to one or more embodiments of the present disclosure, [ example 5 ] there is provided the method of example 4, before the obtaining the sound waveform by predicting the actual fundamental frequency information and the mel-filter bank characteristics through a pre-trained vocoder model, further comprising:

carrying out periodic transformation on the actual fundamental frequency information through a pulser to obtain periodic pulse information;

the predicting the actual fundamental frequency information and the mel filter bank characteristics through a pre-trained vocoder model to obtain the sound waveform comprises the following steps:

and predicting the periodic pulse information and the characteristics of the Mel filter bank through a pre-trained vocoder model to obtain the sound waveform.

According to one or more embodiments of the present disclosure, [ example 6 ] there is provided the method of example 2, before predicting the song information to be synthesized by a pre-trained acoustic model to obtain the mel-filter bank characteristics and fundamental frequency difference information, further comprising:

acquiring first sample information, wherein the first sample information comprises sample song information, and a Mel filter bank characteristic and a fundamental frequency difference value corresponding to the sample song information;

and training the acoustic model according to the first sample information to determine mapping parameters of the song information, the characteristics of the Mel filter bank and the fundamental frequency difference in the acoustic model.

According to one or more embodiments of the present disclosure, [ example 7 ] there is provided the method of example 4, before the obtaining the sound waveform by predicting the actual fundamental frequency information and the mel-filter bank characteristics through a pre-trained vocoder model, further comprising:

acquiring second sample information, wherein the second sample information comprises a sample sound waveform, and a Mel filter bank characteristic and periodic pulse information corresponding to the sample sound waveform;

and training the vocoder model according to the second sample information to determine the mapping parameters of the sound waveform, the characteristics of the Mel filter bank and the periodic pulse information in the vocoder model.

According to one or more embodiments of the present disclosure, [ example 8 ] there is provided a singing synthesis apparatus comprising:

the system comprises a song information acquisition module to be synthesized, a song information acquisition module and a song information synthesis module, wherein the song information to be synthesized comprises a lyric text and melody information;

a Mel filter bank characteristic and actual fundamental frequency information obtaining module, which is used for obtaining the Mel filter bank characteristic and the actual fundamental frequency information according to the song information to be synthesized;

According to one or more embodiments of the present disclosure, [ example 9 ] there is provided the apparatus of example 8, the mel-filter bank feature and actual fundamental frequency information acquisition module comprising:

the first obtaining submodule is used for predicting the song information to be synthesized through a pre-trained acoustic model to obtain the characteristics of the Mel filter bank and the fundamental frequency difference information;

and the second acquisition submodule is used for acquiring preset fundamental frequency information corresponding to the song information to be synthesized and adding the preset fundamental frequency information and the fundamental frequency difference information to obtain the actual fundamental frequency information.

According to one or more embodiments of the present disclosure, [ example 10 ] there is provided the apparatus of example 9, further comprising a fundamental frequency difference information obtaining module, configured to adjust the fundamental frequency difference information according to a user instruction, and obtain adjusted fundamental frequency difference information;

the second obtaining sub-module is configured to add the preset fundamental frequency information and the adjusted fundamental frequency difference information to obtain the actual fundamental frequency information.

According to one or more embodiments of the present disclosure, [ example 11 ] there is provided the apparatus of example 8, the singing synthesis module to obtain the sound waveform by predicting the actual fundamental frequency information and the mel-filter bank features through a pre-trained vocoder model.

According to one or more embodiments of the present disclosure, [ example 12 ] there is provided the apparatus of example 11, further comprising a periodic pulse information acquisition module to: carrying out periodic transformation on the actual fundamental frequency information through a pulser to obtain periodic pulse information;

and the singing synthesis module is used for predicting the periodic pulse information and the characteristics of the Mel filter bank through a pre-trained vocoder model to obtain the sound waveform.

According to one or more embodiments of the present disclosure, [ example 13 ] there is provided the apparatus of example 9, further comprising a first training module, configured to obtain first sample information, where the first sample information includes sample song information, and mel-filter bank features and fundamental frequency difference values corresponding to the sample song information;

According to one or more embodiments of the present disclosure, [ example 14 ] there is provided the apparatus of example 11, further comprising a second training module configured to obtain second sample information, wherein the second sample information includes a sample sound waveform, and mel filter bank characteristics and periodic pulse information corresponding to the sample sound waveform;

According to one or more embodiments of the present disclosure, [ example 15 ] there is provided an electronic device comprising:

one or more processors;

a storage device for storing one or more programs,

when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-7.

According to one or more embodiments of the present disclosure, [ example 16 ] there is provided a storage medium containing computer executable instructions, having stored thereon a computer program, characterized in that the program, when executed by a processor, implements the method according to any one of claims 1-7.

The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the disclosure herein is not limited to the particular combination of features described above, but also encompasses other embodiments in which any combination of the features described above or their equivalents does not depart from the spirit of the disclosure. For example, the above features and (but not limited to) the features disclosed in this disclosure having similar functions are replaced with each other to form the technical solution.

Further, while operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are included in the above discussion, these should not be construed as limitations on the scope of the disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination.

Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.

Claims

1. A singing synthesis method, comprising:

2. The method of claim 1, wherein obtaining Mel filter bank characteristics and actual fundamental frequency information from the song information to be synthesized comprises:

3. The method according to claim 2, wherein after obtaining the mel-filter bank feature and the fundamental frequency difference information by predicting the song information to be synthesized through a pre-trained acoustic model, the method further comprises:

4. The method of claim 1, wherein obtaining a sound waveform from the mel filter bank features and the actual fundamental frequency information comprises:

5. The method of claim 4, wherein before the predicting the actual fundamental frequency information and the Mel filterbank features by a pre-trained vocoder model to obtain the sound waveform, further comprising:

6. The method of claim 2, wherein before the obtaining the mel-filter bank characteristic and the fundamental frequency difference information by predicting the song information to be synthesized through the pre-trained acoustic model, the method further comprises:

7. The method of claim 4, wherein before the predicting the actual fundamental frequency information and the Mel filterbank features by a pre-trained vocoder model to obtain the sound waveform, further comprising:

8. A singing synthesis apparatus, comprising:

9. An electronic device, characterized in that the electronic device comprises:

one or more processors;

a storage device for storing one or more programs,

10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1 to 7.