Unlock instant, AI-driven research and patent intelligence for your innovation.

An end-to-end multilingual continuous speech stream speech content recognition method and system

A technology of speech content and speech recognition model, which is applied in speech recognition, speech analysis, instruments, etc., can solve the problem of not being able to effectively improve the language differentiation of multilingual speech recognition systems, and achieve the effect of improving language differentiation

Active Publication Date: 2022-07-12
INST OF ACOUSTICS CHINESE ACAD OF SCI +1
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Existing speech content recognition methods cannot effectively improve the language discrimination of multilingual speech recognition systems

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
  • An end-to-end multilingual continuous speech stream speech content recognition method and system
  • An end-to-end multilingual continuous speech stream speech content recognition method and system
  • An end-to-end multilingual continuous speech stream speech content recognition method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0052] The present invention will now be further described with reference to the accompanying drawings.

[0053] like figure 1 As shown, the present invention provides an end-to-end multilingual continuous speech stream speech content recognition method, the method comprising:

[0054] Input the speech spectral features to be recognized into a pre-built deep neural network-based segment-level language classification model, and extract the sentence-level language state posterior probability distribution vector V according to the segment-level language classification model. l , obtain the language classification result of the corresponding language type; wherein, the language classification result of the corresponding language type is the sentence-level language state posterior probability distribution vector V l ; The speech spectral feature to be recognized is the frequency domain representation obtained by performing Fourier transform on the multilingual continuous speech st...

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 belongs to the technical field of network communication, and in particular relates to an end-to-end multilingual continuous speech stream speech content recognition method. The method includes: inputting the speech spectral features to be recognized into a pre-built segment-level language classification based on a deep neural network model, extract the sentence-level language state posterior probability distribution vector; input the speech spectral feature sequence to be recognized for each language type and the sentence-level language state posterior probability distribution vector into the pre-built multilingual speech recognition model, and output the corresponding Speech recognition results for language categories.

Description

technical field [0001] The invention belongs to the technical field of network communication and speech recognition, and in particular relates to an end-to-end multilingual continuous speech stream speech content recognition method and system. Background technique [0002] Currently, end-to-end recognition frameworks have been widely used in automatic speech recognition tasks. Since the end-to-end framework does not rely on pronunciation dictionaries in the process of building speech recognition systems, it is more flexible in the process of building speech recognition systems in new languages ​​as well as in multilingual speech recognition systems. Not only that, the end-to-end speech recognition model can directly model the mapping relationship between the sequence of acoustic features and the sequence of text modeling units. Compared with traditional speech recognition systems based on acoustic modeling and language modeling, the end-to-end framework unifies the process ...

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 Patents(China)
IPC IPC(8): G10L15/08G10L15/00G10L15/06G10L15/16
CPCG10L15/08G10L15/005G10L15/063G10L15/16
Inventor 徐及林格平刘丹阳万辛张鹏远李娅强刘发强颜永红
Owner INST OF ACOUSTICS CHINESE ACAD OF SCI