Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Modeling method as well as method and device for acquiring acoustic model

An acoustic model and acquisition method technology, applied in the field of acoustic model acquisition and modeling method, can solve the problems of long training period, unreusable modeling process and data, and high cost, so as to overcome the sparse training data and realize fast model custom effects

Active Publication Date: 2019-05-10
ALIBABA GRP HLDG LTD
View PDF7 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] Solution (2) is currently the main modeling solution based on user-defined voice wake-up, which has a higher wake-up rate and a lower false wake-up rate, and can better meet the actual needs of users; but the disadvantages of this solution are: For new wake-up words generated by different user-defined wake-up words or different wake-up word scenarios (such as different systems or products), the modeling process and data cannot be reused, and new wake-up words need to be rebuilt every time. Therefore, the cost of this scheme is high, and the required training period is long; and this scheme requires a large number of wake-up word samples as training data, and there may be a problem of insufficient training data

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
  • Modeling method as well as method and device for acquiring acoustic model
  • Modeling method as well as method and device for acquiring acoustic model
  • Modeling method as well as method and device for acquiring acoustic model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0059] Embodiment 1. A method for acquiring an acoustic model, which is applied to voice wake-up model processing, such as figure 1 As shown, including steps S110-S130:

[0060] S110. Acquire a basic model, the basic model is obtained by performing context-independent CI modeling and context-dependent CD modeling on the training data, wherein CD modeling is used for the training data in the aggregation state, and CD modeling is used for the training data of a single phoneme CI modeling;

[0061] S120. For a given wake-up word, select an output layer node corresponding to the wake-up word from the output layer nodes in the CD part of the basic model;

[0062] S130. Build a model with the output layer node corresponding to the wake-up word and the rest of the basic model to obtain an acoustic model corresponding to the wake-up word.

[0063] In this embodiment, in the basic model obtained by modeling, the output layer node includes at least two parts: a CD part and a CI part. ...

Embodiment 2

[0149] Embodiment 2. An acoustic model acquisition device, which is applied to voice wake-up model processing, includes: a processor and a memory;

[0150] The memory is used to save the program for obtaining the acoustic model; when the program for obtaining the acoustic model is read and executed by the processor, the following operations are performed:

[0151] Obtain a basic model, the basic model is obtained by performing context-independent CI modeling and context-dependent CD modeling on the training data, wherein CD modeling is used for the training data in the aggregation state, and CI is used for the training data of the single phone mold;

[0152] For a given wake-up word, in the output layer node of the CD part of the basic model, determine the output layer node corresponding to the wake-up word;

[0153] The output layer node corresponding to the wake-up word is used to construct a model with the rest of the basic model to obtain an acoustic model corresponding t...

Embodiment 3

[0165] Embodiment 3. An acquisition device for an acoustic model, which is applied to voice wake-up model processing, such as Image 6 shown, including:

[0166] The obtaining module 61 is used to obtain the basic model, the basic model is obtained by performing context-independent CI modeling and context-dependent CD modeling on the training data, wherein CD modeling is used in the training data of the aggregation state, and the single-phone The training data of is modeled by CI;

[0167] The clipping module 62 is used to select the output layer node corresponding to the wake-up word from the output layer nodes in the CD part of the basic model for a given wake-up word;

[0168] The construction module 63 is configured to construct a model by combining the output layer node corresponding to the wake-up word with the rest of the basic model to obtain an acoustic model corresponding to the wake-up word.

[0169] In an implementation manner, the output layer node corresponding...

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 application provides a modeling method as well as a method and device for acquiring an acoustic model, which are applied to voice wake-up model processing, wherein the method for acquiring the acoustic model comprises the steps of: acquiring a basic model, wherein the basic model is obtained by carrying out context-independent CI modeling and context-dependent CD modeling on training data, theCD modeling is adopted for the training data in an aggregated state, and the CI modeling is adopted for the training data with monophonemes; for a given wake-up word, determining an output layer nodecorresponding to the wake-up word in output layer nodes of a CD part of the basic model; and modeling the output layer node corresponding to the wake-up word and a remaining part in the basic model to obtain the acoustic model corresponding to the wake-up word. According to the application, keywords can be rapidly customized with low cost, and the shortage of the training data can be avoided.

Description

technical field [0001] The invention relates to the field of speech recognition, in particular to a modeling method, an acoustic model acquisition method and a device. Background technique [0002] Voice wake-up is widely used in smart home and Internet of Things devices. Users can start the device by speaking a pre-customized wake-up word. [0003] There are currently two voice wake-up solutions: [0004] (1) Only standard automatic speech recognition technology is used, and wake-up words and other speech words are modeled without distinction, usually context independent (CI) modeling. [0005] The advantage of this scheme is that the same set of models can be quickly applied to different wake-up word scene requirements, and has great advantages in saving resources and rapid commercialization; but its disadvantages are also obvious: the modeling of this scheme does not highlight Wake-up words, so that during the recognition process, wake-up words have similar scores to ot...

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): G10L15/06G10L15/14G10L15/22
CPCY02D30/70
Inventor 姚海涛高杰
Owner ALIBABA GRP HLDG LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com