A multi-example keyword detection method based on a multi-task neural network

A keyword detection and neural network technology, applied in the field of speech signal processing, can solve problems such as difficulty in obtaining good results, limited performance improvement of template matching methods, etc., and achieve the effect of improving detection performance and improving low resource conditions

Active Publication Date: 2018-09-14
TSINGHUA UNIV
View PDF5 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In actual application scenarios, text-based methods are difficult to achieve good results when dealing with languages ​​with scarce resources or dialects with a narrow range of use, or even unknown languages.
In this low-resour

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
  • A multi-example keyword detection method based on a multi-task neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The present invention proposes a multi-example keyword detection method based on a multi-task neural network. The preferred embodiments will be described in detail below in conjunction with the accompanying drawings.

[0031] figure 1 Shown is the flow chart of multi-example keyword detection based on multi-task neural network.

[0032] figure 1 The method described in specifically comprises the following steps:

[0033] Step 1: Train a bottleneck deep neural network (bottleneck-DNN) on a multilingual dataset. The multilingual data set is a Chinese-English mixed data set, and the 40-dimensional fbank feature and its first and second order differences are extracted from the data set audio (usually the first order difference is to calculate the difference between the next moment and the previous moment at the current moment , the second-order difference is to use the result of the first-order difference as the current sequence, and calculate the difference between th...

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 provides a multi-example keyword detection method based on a multi-task neural network, which belongs to the technical field of voice signal processing. The method comprises the steps of: training a bottleneck deep neural network on a multi-language data set; extracting fbank features from target data set audio frame by frame and extracting bottleneck features of the target data set;based on a training set, training an HMM model for each keyword by using the bottleneck features of the keywords, acquiring a frame-level station tag thereof and training a filler word model by usingthe bottleneck features of all non-keywords; performing multi-task DNN acoustic model training by using the bottleneck features; acquiring the acoustic score of test set audio and obtaining keyword detection results through Viterbi decoding. The multi-task technology can effectively improve low resource conditions and remarkably improve multi-example keyword detection performance.

Description

technical field [0001] The invention belongs to the technical field of speech signal processing, and in particular relates to a multi-example keyword detection method based on a multi-task neural network. Background technique [0002] Voice keyword detection technology, as one of the artificial intelligence technologies for processing massive audio data, provides a solution for people to quickly retrieve predefined keywords from massive voice data. At present, keyword detection can be divided into two categories according to different keyword retrieval objects: text-based keyword detection, keywords are given in the form of text; example-based keyword detection, keywords are given as speech fragments (sample ) form is given. In terms of algorithms, the mainstream technology of text keyword detection is based on LVCSR (Large Vocabulary Continuous Speech Recognition) and text matching; the mainstream technology of sample keyword detection is based on DTW (Dynamic Time Warping...

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
IPC IPC(8): G10L15/02G10L15/06G10L15/14G10L15/16
CPCG10L15/02G10L15/063G10L15/144G10L15/16
Inventor 张卫强杨建斌刘加
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
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap