Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Voice production method based on deep convolutional generative adversarial network

A deep convolution and network technology, applied in speech analysis, speech recognition, instruments, etc., can solve problems such as lack of change, monotonous patterns, discriminators cannot correctly distinguish generated data and real data, etc., to achieve easy understanding and acceptance Effect

Active Publication Date: 2017-10-24
NANJING MEDICAL UNIV
View PDF5 Cites 83 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The generative confrontation network is a deep learning model that has become popular in recent years. It mainly uses tensorflow as a learning framework to train a generator G to generate realistic samples from random noise or latent variables, and at the same time train a discriminator Generator D is used to identify real data and generated data. Both are trained at the same time. G and D are used to form a dynamic "game process" until a Nash equilibrium is reached. The data generated by the generator is indistinguishable from real samples, and the discriminator cannot distinguish correctly. Generated and real data
Through the voice signal formed based on the generative confrontation network, it can overcome the shortcomings of current smart devices that can only speak according to a fixed voice library during man-machine dialogue, and the mode is monotonous and lacks change, which is not natural enough.

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 production method based on deep convolutional generative adversarial network
  • Voice production method based on deep convolutional generative adversarial network
  • Voice production method based on deep convolutional generative adversarial network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0107] A speech generation method based on deep convolution generation confrontation network, the flow chart of its main method is as follows figure 1 As shown, it specifically includes the following steps:

[0108] (1) Collect speech signal samples: randomly collect 1000 speech signals with the same content ("Hello") as speech training samples and real speech samples respectively;

[0109] (2) Preprocessing of speech signals: Preprocessing is performed on the 1000 ("Hello") speech signals collected in step 1. First, use Audacity software to edit 1000 ("Hello") voice signals, and filter out the voice parts and non-voice signal parts in the original collected waveforms that are beyond the editing range of the software; secondly, perform voice filtering processing: through the filtering algorithm Calculate the error signal, correlation coefficient, and voice difference vector at n times, calculate the weight coefficient vector at each time by an iterative method, adjust the wei...

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 invention discloses a voice production method based on a deep convolutional generative adversarial network. The steps comprise: (1) acquiring voice signal samples; (2) preprocessing the voice signal samples; (3) inputting the voice signal samples to a deep convolutional generative adversarial network; (4) training the input voice signals; (5) generating voice signals similar to real voice contents. A tensorflow is used as a learning framework, and a deep convolutional generative adversarial network algorithm is used to train large quantity of voice signals. A dynamic game process of a distinguishing network D and a generation network G in the deep convolutional generative adversarial network is used to finally generate a natural voice signal close to original learning contents. The method generates voice based on the deep convolutional generative adversarial network, and solves problems that an intelligent device is overly dependent on a fixed voice library to sound in a man-machine face-to-face communication process, and mode is monotonous and is lack of variations and is not natural enough.

Description

technical field [0001] The invention belongs to the technical field of speech generation, and in particular relates to a speech generation method based on a deep convolution generation confrontation network. Background technique [0002] The research of human-computer interaction technology is an important part of the field of computer technology research. Making smart devices have the function of "speaking", which plays a very important role in the real "face-to-face human-computer communication". With the help of voice generation systems, smart devices can already speak clearly and naturally, which is easy for ordinary users to understand and accept. Voice imitation is an important part of human-machine voice communication. On the one hand, it is necessary to establish a large number of voice databases in the early stage. On the other hand, it needs to extract and train the features of a large number of voice signals to finally generate natural voice signals close to the ...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G10L15/06G10L15/18G10L15/22G10L21/0208
CPCG10L15/063G10L15/18G10L15/22G10L21/0208
Inventor 王伟王翰林胡克魏天远张璐瑶高珊符凡刘政朱纯
Owner NANJING MEDICAL UNIV
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
Eureka Blog
Learn More
PatSnap group products