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

Speech recognition method and device

A speech recognition and speech signal technology, applied in speech recognition, speech analysis, instruments, etc., can solve problems such as easy confusion and poor recognition performance, and achieve the effect of reducing decoding paths, improving accuracy, and increasing decoding speed

Active Publication Date: 2019-05-31
BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, based on the state modeling method, in the process of speech recognition, when recognizing between two pronunciation units, it is easy to be confused and the recognition performance is poor.

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
  • Speech recognition method and device
  • Speech recognition method and device
  • Speech recognition method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] Embodiments of the present invention are described in detail below, examples of which are shown in the drawings, wherein the same or similar reference numerals designate the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary only for explaining the present invention and should not be construed as limiting the present invention.

[0023] In the description of the present invention, it should be understood that the term "plurality" refers to two or more than two; sex.

[0024] The speech recognition method and device according to the embodiments of the present invention will be described below with reference to the accompanying drawings.

[0025] A speech recognition method, comprising the following steps: receiving a speech signal; decoding the speech signal according to a pre-established acoustic model, a language model and a decoding network, and dynamically ad...

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 present disclosure provides a speech recognition method and device. The method includes: receiving a speech signal; decoding the speech signal according to an acoustic model, a language model and a decoding network established in advance, and dynamically adding a blank unit in a decoding process to obtain an optimum decoding path with the added blank unit, in which the acoustic model is obtained based on connectionist temporal classification training, the acoustic model includes basic pronunciation units and the blank unit, and the decoding network includes a plurality of decoding paths consisting of the basic pronunciation units; and outputting the optimum decoding path as a recognition result of the speech signal.

Description

technical field [0001] The invention relates to the technical field of voice recognition, in particular to a voice recognition method and device. Background technique [0002] Most of the traditional speech recognition technologies are based on state modeling speech recognition models for speech recognition. For example, speech recognition is performed based on a Hidden Markov Model (Hidden Markov Model; hereinafter referred to as: HMM). HMM can be regarded as a double stochastic process in mathematics: one is to use the Markov chain with finite number of states to simulate the implicit random process of the statistical characteristics of the speech signal, and the other is to use the Markov chain with each A stochastic process of a state-associated sequence of observations. In this modeling method, a phoneme or a syllable is considered to be divided into multiple states without physical meaning, and then a discrete or continuous Gaussian model or a deep learning model is ...

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): G10L15/06G10L19/008G10L15/26
CPCG10L15/06G10L15/063G10L15/26G10L19/008G10L2015/0631G10L15/08G10L15/14G10L15/183G10L15/02
Inventor 钱胜潘复平
Owner BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD