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

Deep long-term and short-term memory recurrent neural network acoustic model establishing method based on selective attention principles

A recurrent neural network, long-term and short-term memory technology, applied in speech analysis, speech recognition, instruments, etc., can solve problems such as inability to meet practical performance

Active Publication Date: 2015-06-10
TSINGHUA UNIV
View PDF5 Cites 56 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, most recognition systems are still very sensitive to changes in the acoustic environment, especially under the interference of cross-talk noise (two or more people talking at the same time) and cannot meet the requirements of practical performance.

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
  • Deep long-term and short-term memory recurrent neural network acoustic model establishing method based on selective attention principles
  • Deep long-term and short-term memory recurrent neural network acoustic model establishing method based on selective attention principles
  • Deep long-term and short-term memory recurrent neural network acoustic model establishing method based on selective attention principles

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] The following describes the implementation of the present invention in detail with reference to the drawings and embodiments.

[0021] The present invention uses the deep long-short-term memory loop neural network acoustic model based on the selective attention principle to realize continuous speech recognition. However, the model and method provided by the present invention are not limited to continuous speech recognition, and can also be any method and device related to speech recognition.

[0022] The present invention mainly includes the following steps:

[0023] The first step is to build a deep long and short-term memory loop neural network based on the selective attention principle

[0024] Such as figure 1 As shown, input 101 and input 102 are the voice signal input x at time t and t-1 t And x t-1 (t∈[1,T], T is the total time length of the speech signal); the long and short-term memory loop neural network at time t consists of attention gate 103, input gate 104, forget...

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

Disclosed is a deep long-term and short-term memory recurrent neural network acoustic model establishing method based on selective attention principles. According to the deep long-term and short-term memory recurrent neural network acoustic model establishing method based on the selective attention principles, attention gate units are added inside a deep long-term and short-term memory recurrent neural network acoustic model to represent instantaneous function change of auditory cortex neurons; the gate units are different in other gate units in that the other gate units are in one-to-one correspondence with time series, while the attention gate units represent short-term plasticity effects and accordingly have intervals in the time series; through the neural network acoustic model obtained by training mass voice data containing Cross-talk noise, robustness feature extraction of the Cross-talk noise and establishment of robust acoustic models can be achieved; the aim of improving the robustness of the acoustic models can be achieve by inhibiting influence of non-target flow on feature extraction. The deep long-term and short-term memory recurrent neural network acoustic model establishing method based on the selective attention principles can be widely applied to multiple voice recognition-related machine learning fields of speaker recognition, keyword recognition, man-machine interaction and the like.

Description

Technical field [0001] The invention belongs to the field of audio technology, and particularly relates to a method for constructing a deep long-short-term memory loop neural network acoustic model based on the selective attention principle. Background technique [0002] With the rapid development of information technology, speech recognition technology has the conditions for large-scale commercialization. At present, speech recognition mainly uses continuous speech recognition technology based on statistical models, and its main goal is to find the word sequence with the highest probability through a given speech sequence. The task of a continuous speech recognition system based on a statistical model is to find the word sequence with the highest probability according to a given speech sequence, which usually includes the construction of acoustic models and language models and their corresponding search and decoding methods. With the rapid development of acoustic models and lan...

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): G10L15/02G10L15/06
CPCG10L15/02G10L15/06
Inventor 杨毅孙甲松
Owner TSINGHUA 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