公开(公告)号：WO2007106758A2

公开(公告)日：2007-09-20

申请号：PCT/US2007063751

申请日：2007-03-12

Applicant: MOTOROLA INC ,  ISAAC EMAD S ,  ROKUSEK DANIEL S ,  SRENGER EDWARD

Inventor： ISAAC EMAD S ,  ROKUSEK DANIEL S ,  SRENGER EDWARD

IPC: G10L19/00

CPC classification number: G10L15/22

Abstract: A method of providing information storage by means of Automatic Speech Recognition through a communication device of a vehicle comprises establishing a voice communication between an external source and a user of the vehicle, receiving information from the external source, processing the received information using an Automatic Speech Recognition unit in the vehicle and storing the recognized speech in textual form for future retrieval or use.

Abstract translation: 通过车辆的通信装置通过自动语音识别提供信息存储的方法包括建立外部源与车辆用户之间的语音通信，从外部源接收信息，使用自动语音处理所接收的信息 将识别单元存储在车辆中，并将识别的语音存储为文本形式，以供将来检索或使用。

公开(公告)号：EP0764319A4

公开(公告)日：1998-12-30

申请号：EP96910297

申请日：1996-01-29

Applicant: MOTOROLA INC

Inventor： KUSHNER WILLIAM M ,  SRENGER EDWARD ,  HARTMAN MATTHEW A

IPC: G10L15/14 ,  G10L9/00

CPC classification number: G10L15/142

Abstract: In a statistical based speech recognition system, one of the key issues is the selection of the Hidden Markov Model that best matches a given sequence of feature observations. The problem is usually addressed by the calculation of the maximum likelihood, ML, state sequence by means of a Viterbi or other decoder. Noise or inadequate training can produce an ML sequence associated with a Hidden Markov Model other than the correct model. The method of the present invention provides improved robustness by combining the standard ML state sequence score (416) with an additional path core (418) derived from the dynamics of the ML score as a function of time. These two scores, when combined, form a hybrid metric (420) that, when used with the decoder, optimizes selection of the correct Hidden Markov Model (422).