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

Recognition engines with complementary language models

A speech recognition and recognizer technology, applied in speech recognition, speech analysis, instruments, etc.

Inactive Publication Date: 2004-07-07
HUAWEI TECH CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Assuming the priming model is already reasonably good, but proper transposition would require a huge number of additional phrases and a considerable amount of processing

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
  • Recognition engines with complementary language models
  • Recognition engines with complementary language models
  • Recognition engines with complementary language models

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] Speech recognition systems, such as large vocabulary continuous speech recognition systems, typically use a collection of recognition models to recognize input patterns. For example, acoustic models and vocabularies can be used to recognize words, and language models can be used to improve basic recognition results. figure 1 A typical structure of a large vocabulary continuous speech recognition system 100 is shown [see L. Rabiner, B-H. Juang, "Fundamental of speech recognition", Prentice Hall 1993, pp. 434-454]. System 100 includes spectrum analysis subsystem 110 and cell matching subsystem 120 . The speech input signal (SIS) is analyzed spectrally and / or temporally in the spectral analysis subsystem 110 in order to compute characteristic vectors (observation vectors, OV). Typically, the speech signal is digitized (eg sampled at 6.67 kHz) and pre-processed eg by implementing pre-emphasis. For example, successive samples are aggregated (batched) into frames correspond...

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 huge vocabulary speech recognition system for recognizing a sequence of spoken words, having an input means for receiving a time-sequential input pattern representative of the sequence of spoken words. The system further includes a plurality of large vocabulary speech recognizers each being associated with a respective, different large vocabulary recognition model. Each of the recognition models is targeted to a specific part of the huge vocabulary. The system comprises a controller operative to direct the input pattern to a plurality of the speech recognizers and to select a recognized word sequence from the word sequences recognized by the plurality of speech recognizers.

Description

technical field [0001] The present invention relates to a large vocabulary recognition system for recognizing spoken word sequences, the system comprising: an input device for receiving a time-series input pattern representing a spoken word sequence; A large vocabulary speech recognizer that recognizes input patterns as word sequences in . Background technique [0002] US5819220 discloses a system for recognizing speech in an Internet environment. The system specifically targets the use of speech to access information resources on the World Wide Web (WWW). From the perspective of the problems encountered in the traditional speech recognition field, it is very difficult to establish a speech recognition system as a Web interface. Since users can virtually access any document on any topic, the main problem is that the system needs to support a huge vocabulary. Without supporting huge vocabularies, it is difficult to build proper recognition models such as language models fo...

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): G10L15/18G10L15/26G10L15/32
CPCG10L15/32G10L15/18G10L2015/228G10L15/34G10L15/183
Inventor E·特伦S·贝斯林M·乌尔里希
Owner HUAWEI TECH CO 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