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

Methods and apparatus for automatic speech recognition

A technology of automatic speech recognition and grammar, which is applied in speech recognition, speech analysis, instruments, etc., and can solve problems such as caller annoyance

Inactive Publication Date: 2010-06-09
NUANCE COMM INC
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Having to repeat their input can also annoy callers

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
  • Methods and apparatus for automatic speech recognition
  • Methods and apparatus for automatic speech recognition
  • Methods and apparatus for automatic speech recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] Overview of Automatic Speech Recognition

[0028] Such as figure 1 The illustrated automatic speech recognition (ASR) system includes an input device 100, such as a conventional microphone or a telephone handset, an audio front end (AFE) 101 that receives input from the input device, a speech recognition engine 102 that receives input from the AFE, and connected Speech-response application 103 to the speech recognition engine. The application 103 defines a set of logical steps to be executed as part of the interaction between the user and the ASR system. The application 103 typically recognizes what input the user requires through user prompts. User prompts can be text strings displayed on the screen or audio clips played to the user. Speech-response applications use the results of the speech recognition engine to perform actions based on the input.

[0029] As a brief illustration, the following description refers to a possible account balance inquiry application. ...

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

An automatic speech recognition (ASR) system includes a speech-responsive application and a recognition engine. The ASR system generates user prompts to elicit certain spoken inputs, and the speech-responsive application performs operations when the spoken inputs are recognised. The recognition engine compares sounds within an input audio signal with phones within an acoustic model, to identify candidate matching phones. A recognition confidence score is calculated for each candidate matching phone, and the confidence scores are used to help identify one or more likely sequences of matching phones that appear to match a word within the grammar of the speech-responsive application. The per-phone confidence scores are evaluated against predefined confidence score criteria (for example, identifying scores below a 'low confidence' threshold) and the results of the evaluation are used to influence subsequent selection of user prompts. One such system uses confidence scores to select promptsfor targetted recognition training-encouraging input of sounds identified as having low confidence scores. Another system selects prompts to discourage input of sounds that were not easily recognised.

Description

technical field [0001] The present invention provides methods and apparatus for automatic speech recognition. Background technique [0002] An automatic speech recognition (ASR) system takes an audio signal as input and compares the input signal to known sounds (phonemes) and sound sequences (trajectories), usually from an acoustic model (AM), to identify words that appear to match spoken sequences of sounds . After one or more words corresponding to the input audio signal are recognized, the text or other machine-readable form of the recognized matching words is returned by the ASR to an application such as an interactive voice response (IVR) phone application. A confidence score may be returned with each apparently matching word, based on how closely the incoming speech segment fits the average probability distribution associated with the phonemes in the ASR system's acoustic model. Multiple possible words and their respective confidence scores can be returned for select...

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): G10L15/28G10L15/08G10L15/00
CPCG10L2015/085G10L15/08G10L2015/025
Inventor B·J·皮克林T·D·波尔特尼B·T·斯塔尼福德M·惠特伯恩
Owner NUANCE COMM INC
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