Method and system for speech recognition

A speech recognition, to-be-recognized technology, used in speech recognition, speech analysis, instruments, etc.

Active Publication Date: 2005-12-14
KONINKLIJKE PHILIPS ELECTRONICS NV
View PDF1 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, it still has the drawback that the user may again have to say the segment to be corrected sev

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
  • Method and system for speech recognition
  • Method and system for speech recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] figure 1 The illustrated embodiment of the speech recognition system 1 includes an input 14 to which a microphone 2 is connected via an amplifier 3 . The speech recognition system 1 also includes an output terminal 16 connected to the speaker 4 via the amplifier 5 to output speech signals. The microphone 2 and associated amplifier 3 and the loudspeaker 4 and associated amplifier 5 form part of an apparatus remote from the speech recognition system 1 and in communication with the speech recognition system 1 via a communication network, such as a telephone network.

[0029] The communication terminal also includes a keyboard 6 via which acoustic signals such as DTMF (Dual Tone Multi Frequency) signals can be generated; these signals can also be applied via a speech signal channel to the input 14 of the speech recognition system.

[0030] The speech signal S1 arriving at the input 14 from the microphone 2 via the amplifier 3 is converted by the speech recognition system 1...

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

A description is given of a speech recognition system in which a user's speech signal is analyzed to recognize speech information contained in the speech signal. During the test, the recognition results with the greatest possible matches are again converted into speech signals for output to the user for verification and correction. During analysis, a plurality of alternative recognition results are generated that match the speech signal to be recognized with the next highest probability. The output within the test procedure is performed in such a way that the user can interrupt the output in the event of an incorrect recognition of the result output. In this case, for the segment of the relevant recognition result output last before the interruption, each corresponding segment of the alternative recognition result is automatically output so that the user can select therefrom. Subsequently, the relevant segment in the provided recognition result is corrected according to the corresponding segment of the selected alternative recognition result. Finally, the test procedure is continued for the remaining subsequent segments of the speech signal to be recognized. A corresponding speech recognition system is also described.

Description

technical field [0001] The invention relates to a method for speech recognition, wherein a speech signal of a user is analyzed to recognize speech information contained in the speech signal, and the recognition result with the greatest possible match is reconverted into a speech signal during a test and Output to user for verification and / or correction. The present invention also relates to a speech recognition system comprising means for detecting a user's speech signal, comprising: speech recognition means for analyzing the detected speech signal to identify the speech information contained in the speech signal and determine the possible matching recognition results; and speech output means for converting the most likely recognition results into speech information again during the test and outputting it to the user for verification and / or correction. Background technique [0002] Speech recognition systems generally operate in such a way that the speech signal is first an...

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): G10L15/00G10L15/22G10L15/28
CPCG10L15/22G10L2015/225
Inventor A·库伊曼
Owner KONINKLIJKE PHILIPS ELECTRONICS NV
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