Voice conversion model and training method thereof, and voice conversion method and system

A technology of voice conversion and training method, which is applied in speech analysis, speech synthesis, speech recognition and other directions, and can solve the problems such as the inability to quickly and effectively realize voice transformation.

Active Publication Date: 2021-09-24
南京硅语智能科技有限公司
View PDF8 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The embodiment of this application provides a voice conversion model and its training method, voice conversion method and sy...

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Voice conversion model and training method thereof, and voice conversion method and system
  • Voice conversion model and training method thereof, and voice conversion method and system
  • Voice conversion model and training method thereof, and voice conversion method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] Hereinafter, the present application will be described in detail with reference to the drawings and embodiments. It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

[0027] It should be noted that the terms "first" and "second" in the description and claims of the present application and the above drawings are used to distinguish similar objects, but not necessarily used to describe a specific sequence or sequence.

[0028] Such as figure 1 As shown, the embodiment of the present application provides a training method of a speech conversion model, the speech conversion model includes a classification network model and a voice change network model, and the method includes:

[0029] Step S102, using the first sample data to train the classification network model, wherein the first sample data includes the first audio and its corresponding first phoneme label,...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The embodiment of the invention provides a voice conversion model and a training method thereof, and a voice conversion method and system. The training method comprises steps that a classification network model is trained through employing first sample data, and the first sample data to comprise a first audio and a first phoneme label corresponding to the first audio, the classification network model comprises a convolutional neural network layer and a recurrent neural network layer; second sample data are inputted into the trained classification network model, a second phoneme label corresponding to a second audio is obtained, and the second sample data comprise the second audio; the second audio frequency and the corresponding second phoneme label are used for training a voice changing network model, and the voice changing network model comprises a generator, a time domain discriminator and a frequency domain discriminator.

Description

technical field [0001] The present application relates to the technical field of voice data processing, in particular, to a voice conversion model and its training method, voice conversion method and system. Background technique [0002] Voice transformation technology can transform the input audio of the source speaker into the timbre of the target speaker in a true and elegant manner. At present, the sound transformation in related technologies mainly adopts the following three forms: [0003] 1) A solution based on the combination of Automatic Speech Recognition (ASR for short) technology and Text To Speech (TTS for short) technology. First, the audio is recognized as text through the ASR model, and then the TTS model is used to output the text in the tone of the target speaker, so as to achieve the voice change effect. Due to the high error rate of ASR, for general audio input, errors in the ASR recognition process will cause a large number of wrong pronunciations when...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G10L13/08G10L15/02G10L15/06G10L15/08G10L15/16G10L15/26
CPCG10L15/02G10L15/063G10L15/08G10L15/16G10L15/26G10L13/08G10L2015/025
Inventor 司马华鹏毛志强龚雪飞
Owner 南京硅语智能科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap