公开(公告)号：DE69905030D1

公开(公告)日：2003-02-27

申请号：DE69905030

申请日：1999-04-21

Applicant: IBM ,  IBM DEUTSCHLAND INFORMATIONSSY

Inventor： FISCHER VOLKER ,  GAO YUQING ,  PICHENY A ,  KUNZMANN SIEGFRIED

IPC: G10L15/07 ,  G10L15/06

公开(公告)号：AU2003293646A1

公开(公告)日：2004-07-14

申请号：AU2003293646

申请日：2003-10-31

Applicant: IBM

Inventor： FISCHER VOLKER ,  KUNZMANN SIEGFRIED

IPC: G10L15/20 ,  G10L15/22 ,  G10L15/26

Abstract: A method and respective system for operating a speech recognition system, in which a plurality of recognizer programs are accessible to be activated for speech recognition, and are combined on a per need basis in order to efficiently improve the results of speech recognition done by a single recognizer. In order to adapt such system to the dynamically changing acoustic conditions of various operating environments and to the particular requirements of running in embedded systems having only a limited computing power available, it is proposed to a) collect selection base data characterizing speech recognition boundary conditions, e.g. the speaker person and the environmental noise, etc., with sensor means, and b) using program-controlled arbiter means for evaluating the collected data, e.g., a decision engine including software mechanism and a physical sensor, to select the best suited recognizer or a combination thereof out of the plurality of available recognizers.

公开(公告)号：DE69517705D1

公开(公告)日：2000-08-03

申请号：DE69517705

申请日：1995-11-04

Applicant: IBM

Inventor： KUNZMANN SIEGFRIED ,  MOHR KARLHEINZ ,  BANDARA UPALI ,  LEWIS L

IPC: G10L15/183 ,  G10L15/197 ,  G10L15/00 ,  G10L15/22 ,  G10L15/28

Abstract: PCT No. PCT/EP95/04337 Sec. 371 Date Sep. 25, 1997 Sec. 102(e) Date Sep. 25, 1997 PCT Filed Nov. 4, 1995 PCT Pub. No. WO97/17694 PCT Pub. Date May 15, 1997In this speech recognition system, the size of the language model is reduced by discarding those n-grams that the acoustic part of the system can recognize most accurately without support from a language model. The n-grams can be discarded dynamically during the running of the system or during the build or setup-time of the system. Trigrams occurring infrequently in the text corpora are substituted for the discarded n-grams to increase the accuracy of the word recognitions.

公开(公告)号：PL335150A1

公开(公告)日：2000-03-13

申请号：PL33515099

申请日：1999-08-27

Applicant: IBM

Inventor： EMAM OSSAMA ,  KUNZMANN SIEGFRIED

IPC: G10L15/04 ,  G10L15/26 ,  G10L5/00

公开(公告)号：CA2507999C

公开(公告)日：2013-09-03

申请号：CA2507999

申请日：2003-10-31

Applicant: IBM

Inventor： FISCHER VOLKER ,  KUNZMANN SIEGFRIED

IPC: G10L15/20 ,  G10L15/22 ,  G10L15/26

Abstract: The present invention relates to a method and respective system for operating a speech recognition system, in which a plurality of recognizer programs are accessible to be activated for speech recognition, and are combined on a per need basis in order to efficiently improve the results of speech recognition done by a single recognizer. To adapt to dynamically changing acoustic conditions of various operating environments and to embedded systems having only a limited computing power available, it is proposed to a) collect (210,220,230,240) selection base data characterizing speech recognition boundary conditions, e.g. the speaker person and the environmental noise, etc., with sensor means, b) using (260) program-controlled arbiter means for evaluating the collected data, e.g., a decision engine including software mechanism and a physical sensor, to select (290) the best suited recognizer or a combination thereof out of the plurality of available recognizers.

公开(公告)号：DE602006002431D1

公开(公告)日：2008-10-09

申请号：DE602006002431

申请日：2006-05-05

Applicant: IBM

Inventor： KUNZMANN SIEGFRIED ,  FISCHER VOLKER

IPC: G10L13/06 ,  G06F17/30 ,  G10L15/22

公开(公告)号：CZ9903015A3

公开(公告)日：2000-06-14

申请号：CZ301599

申请日：1999-08-24

Applicant: IBM

Inventor： EMAN OSSAMA ,  KUNZMANN SIEGFRIED

IPC: G10L15/14

公开(公告)号：CA2203132A1

公开(公告)日：1997-05-05

申请号：CA2203132

申请日：1995-11-04

Applicant: IBM

Inventor： BANDARA UPALI ,  KUNZMANN SIEGFRIED ,  LEWIS BURN L ,  MOHR KARLHEINZ

IPC: G10L15/183 ,  G10L15/197 ,  G10L9/00 ,  G10L9/18

Abstract: Disclosed are a method and an apparatus for adapting, particularly reducing, the size of a language model, which comprises word n-grams, in a speech recognition system. The invention provides a mechanism to discard those n-grams for which the acoustic part of the system requires less support from the language model to recognize correctly. The proposed method is suitable for identifying those trigrams in a language model for the purpose of discarding during the built-time of the system. Provided is also another automatic classification scheme for words which allows the compression of a language model, but under retention of accuracy. Moreover it allows an efficient usage of sparsely available text corpora because even singleton trigrams are used when they are helpful. No additional software tools are needed to be developed because the main tool, the fast match scoring, is a module readily available in the known recognizers themselves. Further improvement of the method is accomplished by classification of words according to the common text in which they occur as far as they distinguish from each other acoustically. The invention opens the possibility to make speech recognition available in low-cost personal computers (PC's), even in portable computers like Laptops.

公开(公告)号：AT406648T

公开(公告)日：2008-09-15

申请号：AT06113577

申请日：2006-05-05

Applicant: IBM

Inventor： KUNZMANN SIEGFRIED ,  FISCHER VOLKER

IPC: G10L13/06 ,  G06F17/30 ,  G10L15/22

公开(公告)号：CA2507999A1

公开(公告)日：2004-07-08

申请号：CA2507999

申请日：2003-10-31

Applicant: IBM

Inventor： FISCHER VOLKER ,  KUNZMANN SIEGFRIED

IPC: G10L15/20 ,  G10L15/22 ,  G10L15/26

Abstract: The present invention relates to a method and respective system for operatin g a speech recognition system, in which a plurality of recognizer programs are accessible to be activated for speech recognition, and are combined on a per need basis in order to efficiently improve the results of speech recognition done by a single recognizer. To adapt to dynamically changing acoustic conditions of various operating environments and to embedded systems having only a limited computing power available, it is proposed to a) collect (210,220,230,240) selection base data characterizing speech recognition boundary conditions, e.g. the speaker person and the environmental noise, etc., with sensor means, b) using (260) program-controlled arbiter means for evaluating the collected data, e.g., a decision engine including software mechanism and a physical sensor, to select (290) the best suited recognizer or a combination thereof out of the plurality of available recognizers.