公开(公告)号：JP2000187496A

公开(公告)日：2000-07-04

申请号：JP33892899

申请日：1999-11-30

Applicant: LUCENT TECHNOLOGIES INC

Inventor： CHOU WU ,  RECCHIONE MICHAEL CHARLES ,  ZHOU QIRU

IPC: G10L15/00 ,  G10L15/02 ,  G10L15/20 ,  G10L15/28

Abstract: PROBLEM TO BE SOLVED: To provide a method for automatic high degree voice recognition without a remarkable change to a secondary channel and a present standard by extracting plural voice characteristic signals from a received coding voice signal separately converging the received coding voice signal to an audio voice signal and applying them to a voice recognition system. SOLUTION: A hand set 201 generates a voice coder/parameter to transmit it to a radio base station 220 in response to a user input by utterance. In the radio base station 220, the received coding voice signal is provided on a path to be supplied to a public switch 230. Further, the coding voice signal received by the radio base station 220 is supplied to an automatic voice/speaker recognition (ASR) characteristic system 235 and an ASR system 240 arranged in the radio base station 220. In these systems, the decoded same coding display generating the voice signal is used as a substitute, and an ASR characteristic parameter is extracted with the ASR characteristic system 235 that the ASR system 240 uses.

公开(公告)号：DE69911723T2

公开(公告)日：2004-08-12

申请号：DE69911723

申请日：1999-11-23

Applicant: LUCENT TECHNOLOGIES INC

Inventor： CHOU WU ,  RECCHIONE MICHAEL CHARLES ,  ZHOU QIRU

IPC: G10L15/00 ,  G10L15/02 ,  G10L15/20 ,  G10L15/28 ,  G10L15/26

Abstract: Automatic Speech Recognition (ASR) is achieved in wireless communications systems in which reliable ASR feature vector sequences are derived at a base station directly from digitally transmitted speech coder parameters, with no additional processing or signal modification required at the originating handset. No secondary channel need be provided for the transmission of ASR feature vectors. In operating on received speech coder parameters prior to conversion to a voice signal the present system and methods avoid the lossy conversion process and associated voice distortion. Since the received voice parameters are error protected during transmission they are received with greater accuracy.

公开(公告)号：DE69911723D1

公开(公告)日：2003-11-06

申请号：DE69911723

申请日：1999-11-23

Applicant: LUCENT TECHNOLOGIES INC

Inventor： CHOU WU ,  RECCHIONE MICHAEL CHARLES ,  ZHOU QIRU

IPC: G10L15/00 ,  G10L15/02 ,  G10L15/20 ,  G10L15/28 ,  G10L15/26

Abstract: Automatic Speech Recognition (ASR) is achieved in wireless communications systems in which reliable ASR feature vector sequences are derived at a base station directly from digitally transmitted speech coder parameters, with no additional processing or signal modification required at the originating handset. No secondary channel need be provided for the transmission of ASR feature vectors. In operating on received speech coder parameters prior to conversion to a voice signal the present system and methods avoid the lossy conversion process and associated voice distortion. Since the received voice parameters are error protected during transmission they are received with greater accuracy.

公开(公告)号：AU5958599A

公开(公告)日：2000-06-01

申请号：AU5958599

申请日：1999-11-22

Applicant: LUCENT TECHNOLOGIES INC

Inventor： CHOU WU ,  RECCHIONE MICHAEL CHARLES ,  ZHOU QIRU

IPC: G10L15/00 ,  G10L15/02 ,  G10L15/20 ,  G10L15/28 ,  G10L9/14 ,  H04L12/16

Abstract: Automatic Speech Recognition (ASR) is achieved in wireless communications systems in which reliable ASR feature vector sequences are derived at a base station directly from digitally transmitted speech coder parameters, with no additional processing or signal modification required at the originating handset. No secondary channel need be provided for the transmission of ASR feature vectors. In operating on received speech coder parameters prior to conversion to a voice signal the present system and methods avoid the lossy conversion process and associated voice distortion. Since the received voice parameters are error protected during transmission they are received with greater accuracy.

公开(公告)号：CA2287025A1

公开(公告)日：2000-05-30

申请号：CA2287025

申请日：1999-10-20

Applicant: LUCENT TECHNOLOGIES INC

Inventor： ZHOU QIRU ,  RECCHIONE MICHAEL CHARLES ,  CHOU WU

IPC: G10L15/00 ,  G10L15/02 ,  G10L15/20 ,  G10L15/28 ,  G10L9/04

Abstract: Automatic Speech Recognition (ASR) is achieved in wireless communications systems in which reliable ASR feature vector sequences are derived at a base station directly from digitally transmitted speech coder parameters, with no additional processing or signal modification required at the originating handset. No secondary channel need be provided for the transmission of ASR feature vectors. In operating on received speech coder parameters prior to conversion to a voice signal the present system and methods avoid the lossy conversion process and associated voice distortion. Since the received voice parameters are error protected during transmission they are received with greater accuracy.