公开(公告)号：AU4801985A

公开(公告)日：1987-03-24

申请号：AU4801985

申请日：1985-09-03

Applicant: MOTOROLA INC

Inventor： BORTH DAVIS EDWARD ,  GERSON IRA ALAN ,  VILMUR RICHARD JOSEPH

IPC: H04M1/27 ,  G10L7/08

公开(公告)号：NO843498L

公开(公告)日：1984-09-03

申请号：NO843498

申请日：1984-09-03

Applicant: MOTOROLA INC

Inventor： GERSON IRA ALAN

IPC: G10L11/00 ,  G01R20060101 ,  G10L20060101 ,  G10L19/04 ,  G10L19/08 ,  H03H17/00 ,  H03H17/02 ,  H03H21/00 ,  H03K20060101 ,  H04B3/23 ,  H03K

公开(公告)号：FI843448A

公开(公告)日：1984-09-03

申请号：FI843448

申请日：1984-09-03

Applicant: MOTOROLA INC

Inventor： GERSON IRA ALAN

IPC: G10L11/00 ,  G01R20060101 ,  G10L20060101 ,  G10L19/04 ,  G10L19/08 ,  H03H17/00 ,  H03H17/02 ,  H03H21/00 ,  H03K20060101 ,  H04B3/23 ,  H03K

公开(公告)号：DK176383B1

公开(公告)日：2007-10-22

申请号：DK438189

申请日：1989-09-05

Applicant: MOTOROLA INC

Inventor： GERSON IRA ALAN

IPC: G10L11/00 ,  G10L19/12 ,  G10L15/02 ,  G10L19/00 ,  G10L19/04 ,  G10L19/08

Abstract: An improved excitation vector generation and search technique (FIG. 1) is described for a code-excited linear prediction (CELP) speech coder (100) using a codebook of excitation code vectors. A set of M basis vectors Vm(n) are used along with the excitation signal codewords (i) to generate the codebook of excitation vectors ui(n) according to a "vector sum" technique (120) of converting the selector codewords into a plurality of interim data signals, multiplying the set of M basis vectors by the interim data signals, and summing the resultant vectors to produce the set of 2M codebook vectors. The entire codebook of 2M possible excitation vectors is efficiently searched by using the vector sum generation technique with the M basis vectors-without ever having to generate and evaluate each of the 2M code vectors themselves. Furthermore, only M basis vectors need to be stored in memory (114), as opposed to all 2M code vectors.

公开(公告)号：AU675389B2

公开(公告)日：1997-01-30

申请号：AU2104095

申请日：1995-03-21

Applicant: MOTOROLA INC

Inventor： KARAALI ORHAN ,  CORRIGAN GERALD EDWARD ,  GERSON IRA ALAN

IPC: G06F15/18 ,  G06N3/00 ,  G10L13/00 ,  G10L13/08

Abstract: Text may be converted to audible signals, such as speech, by first training a neural network 106 using recorded audio messages 204. To begin the training, the recorded audio messages are converted into a series of audio frames 205 having a fixed duration 213. Then, each audio frame is assigned a phonetic representation 203 and a target acoustic representation 208, where the phonetic representation 203 is a binary word that represents the phone and articulation characteristics of the audio frame, while the target acoustic representation 208 is a vector of audio information such as pitch and energy. After training, the neural network 106 is used in conversion of text into speech. First, text that is to be convened is translated to a series of phonetic frames 401 of the same form as the phonetic representations 208 and having the fixed duration 213. Then the neural network produces acoustic representations in response to context descriptions 207 that include some of the phonetic frames 401. The acoustic representations are then converted into a speech wave form by a synthesizer 107.

公开(公告)号：HK40596A

公开(公告)日：1996-03-15

申请号：HK40596

申请日：1996-03-07

Applicant: MOTOROLA INC

Inventor： GERSON IRA ALAN ,  LINDSLEY BRETT LOUIS

IPC: G10L11/00 ,  G10L15/00 ,  G10L15/02 ,  G10L5/00

Abstract: The present invention describes a method and arrangement for reducing a sequence of initial frames into a reduced set of representative frames by combining the initial frames into a plurality of representative frames, the combining process including generating a distortion measure associated with each representative frame and comparing each distortion measure to a distortion threshold. From these representative frames, a set of mutually exclusive frames is determined to minimize the number of representative frames, whereby each representative frame in the set represents a unique set of contiguous initial frames and has an associated distortion measure which does not exceed the distortion threshold.

公开(公告)号：CA2161540A1

公开(公告)日：1995-11-09

申请号：CA2161540

申请日：1995-03-21

Applicant: MOTOROLA INC

Inventor： KARAALI ORHAN ,  CORRIGAN GERALD EDWARD ,  GERSON IRA ALAN

IPC: G06F15/18 ,  G06N3/00 ,  G10L13/00 ,  G10L13/08

Abstract: Text may be converted to audible signals, such as speech, by first training a neural network 106 using recorded audio messages 204. To begin the training, the recorded audio messages are converted into a series of audio frames 205 having a fixed duration 213. Then, each audio frame is assigned a phonetic representation 203 and a target acoustic representation 208, where the phonetic representation 203 is a binary word that represents the phone and articulation characteristics of the audio frame, while the target acoustic representation 208 is a vector of audio information such as pitch and energy. After training, the neural network 106 is used in conversion of text into speech. First, text that is to be convened is translated to a series of phonetic frames 401 of the same form as the phonetic representations 208 and having the fixed duration 213. Then the neural network produces acoustic representations in response to context descriptions 207 that include some of the phonetic frames 401. The acoustic representations are then converted into a speech wave form by a synthesizer 107.

公开(公告)号：DE3853294D1

公开(公告)日：1995-04-13

申请号：DE3853294

申请日：1988-08-24

Applicant: MOTOROLA INC

Inventor： GERSON IRA ALAN ,  LINDSLEY BRETT LOUIS

IPC: G10L15/28 ,  G10L15/00 ,  G10L15/22 ,  H04M1/00 ,  H04M1/27 ,  H04M1/60 ,  H04M9/08 ,  H04Q7/38 ,  H04B1/46 ,  G10L9/06

Abstract: A reliable method for terminating a telephone call is disclosed using a specific sequence of steps performed by hands-free control system. The invention requires that the call terminating command sequence be recognized as: two separate speech utterances (e.g., TERMINATE (158) and CONVERSATION (158)); in proper sequence (e.g. TERMINATE first, then CONVERSATION) with a maximum pause time interval (124) between the end of the first utterance and the start of the second utterance (e.g., 300 milliseconds) and which meet predefined speech recognition matching criteria (110). Moreover, the present invention provides the user with a procedure to continue the telephone call in progress should the speech recognizer make a false recognition or if the user did not intend to speak the proper command. As a result, present invention enables a user to disconnect a telephone call by voice command with a high degree of reliability, even under high ambient noise conditions.

公开(公告)号：DE3688749T2

公开(公告)日：1993-11-11

申请号：DE3688749

申请日：1986-12-22

Applicant: MOTOROLA INC

Inventor： BORTH DAVID EDWARD ,  GERSON IRA ALAN ,  VILMUR RICHARD JOSEPH ,  LINDSLEY BRETT LOUIS

IPC: G10L13/00 ,  G10L19/02 ,  G10L5/00

公开(公告)号：DE3688747D1

公开(公告)日：1993-08-26

申请号：DE3688747

申请日：1986-12-18

Applicant: MOTOROLA INC

Inventor： GERSON IRA ALAN ,  LINDSLEY BRETT LOUIS

IPC: G10L11/00 ,  G10L15/00 ,  G10L15/02 ,  G10L5/00

Abstract: The present invention describes a method and arrangement for reducing a sequence of initial frames into a reduced set of representative frames by combining the initial frames into a plurality of representative frames, the combining process including generating a distortion measure associated with each representative frame and comparing each distortion measure to a distortion threshold. From these representative frames, a set of mutually exclusive frames is determined to minimize the number of representative frames, whereby each representative frame in the set represents a unique set of contiguous initial frames and has an associated distortion measure which does not exceed the distortion threshold.