公开(公告)号：ES2371094T3

公开(公告)日：2011-12-27

申请号：ES07014802

申请日：2002-03-22

Applicant: QUALCOMM INC

Inventor： MALAYATH NARENDRANATH ,  DEJACO ANDREW P ,  CHANG CHIENCHUNG ,  JALIL SUHAIL ,  BI NING ,  GARUDADRI HARINATH

IPC: G10L15/06 ,  G10L15/10 ,  G10L15/12 ,  G10L15/14 ,  G10L15/16 ,  G10L17/04

Abstract: Un procedimiento para realizar el reconocimiento de voz que comprende: realizar el apareo de patrones de un primer segmento de voz de entrada con al menos una primera plantilla acústica de un modelo acústico (230, 232) independiente del orador, para producir al menos una plantilla de apareo de patrones de entrada y para determinar una clase de emisión vocal reconocida, en el cual la clase de emisión vocal es una palabra o segmento de habla específico; comparar dicha(s) plantilla(s) de apareo de patrones de entrada con una plantilla correspondiente asociada a al menos una segunda plantilla acústica proveniente del modelo acústico (234) del orador de la primera voz de entrada, la segunda plantilla acústica asociada a la clase de emisión vocal reconocida; y determinar si se actualiza o no dicha(s) segunda(s) plantilla(s) acústica(s), en donde dicha(s) segunda(s) plantilla(s) acústica(s) se actualiza(n) si dicha(s) plantilla(s) de apareo de patrones de entrada es (son) mejor(es) que la correspondiente plantilla asociada a dicha(s) segunda(s) plantilla(s) acústica(s).

公开(公告)号：BRPI0709263A2

公开(公告)日：2011-06-28

申请号：BRPI0709263

申请日：2007-03-29

Applicant: QUALCOMM INC

Inventor： REZNIK YURIY ,  LUDWIN ALBERT SCOTT ,  CHUNG HYUKJUNE ,  GARUDADRI HARINATH ,  SRINIVASAMURTHY NAVEEN B ,  SAGETONG PHOOM

IPC: G06F17/14 ,  H04N7/26

Abstract: Techniques for efficiently performing full and scaled transforms on data received via full and scaled interfaces, respectively, are described and comprise (1) performing a first transform on a block of first input values to obtain a block of first output values by scaling the block to obtain scaled input values, performing a scaled one-dimensional (1D) transform on each row of the block, and performing a scaled 1D transform on each column of the block; and (2) performing a second transform on a block of second input values to obtain a block of second output values by performing a scaled 1D transform on each row of the block, performing a scaled 1D transform on each column of the block, and scaling the block.

公开(公告)号：DE602005023983D1

公开(公告)日：2010-11-18

申请号：DE602005023983

申请日：2005-05-13

Applicant: QUALCOMM INC

Inventor： GARUDADRI HARINATH ,  SAGETONG PHOOM ,  NANDA SANJIV

IPC: H04N7/52 ,  H04B7/00 ,  H04B7/216 ,  H04L12/28 ,  H04L12/56 ,  H04L12/66 ,  H04L29/06 ,  H04N7/26 ,  H04W28/06 ,  H04W72/12 ,  H04W84/04 ,  H04W88/18

公开(公告)号：AT484157T

公开(公告)日：2010-10-15

申请号：AT05748133

申请日：2005-05-13

Applicant: QUALCOMM INC

Inventor： GARUDADRI HARINATH ,  SAGETONG PHOOM ,  NANDA SANJIV

IPC: H04N7/52 ,  H04B7/00 ,  H04B7/216 ,  H04L12/28 ,  H04L12/56 ,  H04L12/66 ,  H04L29/06 ,  H04N7/26 ,  H04W28/06 ,  H04W72/12 ,  H04W84/04 ,  H04W88/18

Abstract: Methods and apparatus are described for transmitting information units over a plurality of constant bit rate communication channel. The techniques include encoding the information units, thereby creating a plurality of data packets. The encoding is constrained such that the data packet sizes match physical layer packet sizes of the communication channel. The information units may include a variable bit rate data stream, multimedia data, video data, and audio data. The communication channels include CMDA channels, WCDMA, GSM channels, GPRS channels, and EDGE channels.

公开(公告)号：CA2427339C

公开(公告)日：2010-07-13

申请号：CA2427339

申请日：2001-10-25

Applicant: QUALCOMM INC

Inventor： GARUDADRI HARINATH

IPC: G10L15/10 ,  G10L17/00 ,  G10L15/02 ,  G10L15/20

Abstract: A method and system that improves voice recognition by improving the voice recognizer of a voice recognition system 10. Mu-law compression 20 of bark amplitudes is used to reduce the effect of additive noise and thus improve the accuracy of the voice recognition system. A-law compression 21 of bark amplitudes is used to improve the accuracy of the voice recognizer. Both mu-law compression 20 and mu-law expansion 22 can be used in the voice recognizer to improve the accuracy of the voice recognizer. Both A-law compression 21 and A-law expansion can be used in the voice recognizer to improve the accuracy of the voice recognizer.

公开(公告)号：AT443316T

公开(公告)日：2009-10-15

申请号：AT05025989

申请日：2002-03-22

Applicant: QUALCOMM INC

Inventor： MALAYATH NARENDRANATH ,  DEJACO ANDREW P ,  CHANG CHIENCHUNG ,  JALIL SUHAIL ,  NING BI ,  GARUDADRI HARINATH

IPC: G10L15/06 ,  G10L15/10 ,  G10L15/12 ,  G10L15/14 ,  G10L15/16 ,  G10L17/04

Abstract: A voice recognition (VR) system is disclosed that utilizes a combination of speaker independent (SI) and speaker dependent (SD) acoustic models. At least one SI acoustic model is used in combination with at least one SD acoustic model to provide a level of speech recognition performance that at least equals that of a purely SI acoustic model. The disclosed hybrid SI/SD VR system continually uses unsupervised training to update the acoustic templates in the one or more SD acoustic models. The hybrid VR system then uses the updated SD acoustic models in combination with the at least one SI acoustic model to provide improved VR performance during VR testing

公开(公告)号：AT426988T

公开(公告)日：2009-04-15

申请号：AT05748216

申请日：2005-05-13

Applicant: QUALCOMM INC

Inventor： GARUDADRI HARINATH ,  SAGETONG PHOOM ,  HSU RAYMOND

IPC: H04L29/06 ,  H04B7/00 ,  H04B7/216 ,  H04L12/28 ,  H04L12/56 ,  H04L12/66 ,  H04N7/26 ,  H04W28/06 ,  H04W72/12 ,  H04W84/04 ,  H04W88/18

Abstract: Methods and apparatus are described for transmitting information units over a plurality of constant bit rate communication channel. The techniques include encoding the information units, thereby creating a plurality of data packets. The encoding is constrained such that the data packet sizes match physical layer packet sizes of the communication channel. The information units may include a variable bit rate data stream, multimedia data, video data, and audio data. The communication channels include CMDA channels, WCDMA, GSM channels, GPRS channels, and EDGE channels.

公开(公告)号：HK1117260A1

公开(公告)日：2009-01-09

申请号：HK08104363

申请日：2008-04-17

Applicant: QUALCOMM INC

Inventor： MALAYATH NARENDRANATH ,  DEJACO ANDREW P ,  CHANG CHIENCHUNG ,  JALIL SUHAIL ,  BI NING ,  GARUDADRI HARINATH

IPC: G10L15/06 ,  G10L15/10 ,  G10L15/12 ,  G10L15/14 ,  G10L15/16 ,  G10L17/04

Abstract: A voice recognition (VR) system is disclosed that utilizes a combination of speaker independent (SI) and speaker dependent (SD) acoustic models. At least one SI acoustic model is used in combination with at least one SD acoustic model to provide a level of speech recognition performance that at least equals that of a purely SI acoustic model. The disclosed hybrid SI/SD VR system continually uses unsupervised training to update the acoustic templates in the one or more SD acoustic models. The hybrid VR system then uses the updated SD acoustic models in combination with the at least one SI acoustic model to provide improved VR performance during VR testing

公开(公告)号：DE602004010081D1

公开(公告)日：2007-12-27

申请号：DE602004010081

申请日：2004-03-23

Applicant: QUALCOMM INC

Inventor： GARUDADRI HARINATH ,  RAMCHANDRAN KANNAN

IPC: H04N7/26 ,  H03M13/29 ,  H04N7/66 ,  H04N19/895

Abstract: According to one aspect of the present invention, a method and apparatus is provided in which input data (e.g., input video data) is encoded in accordance with a first coding standard (e.g., MPEG-4) to generate encoded data. The input data is also encoded based on a reconstruction of the input data to generate encoded side information associated with the input data. The encoded data are transmitted to a destination (e.g., a decoding subsystem) over a first channel and the encoded side information are transmitted to the destination over a second channel. The encoded data and the encoded side information are decoded and combined at the destination to generate output data.

公开(公告)号：BRPI0510952A

公开(公告)日：2007-11-20

申请号：BRPI0510952

申请日：2005-05-13

Applicant: QUALCOMM INC

Inventor： GARUDADRI HARINATH ,  SAGETONG PHOOM ,  HSU RAYMOND T-S

IPC: H04L29/06 ,  H04B7/00 ,  H04B7/216 ,  H04L12/28 ,  H04L12/56 ,  H04L12/66 ,  H04N7/26 ,  H04W28/06 ,  H04W72/12 ,  H04W84/04 ,  H04W88/18

Abstract: Methods and apparatus are described for transmitting information units over a plurality of constant bit rate communication channel. The techniques include encoding the information units, thereby creating a plurality of data packets. The encoding is constrained such that the data packet sizes match physical layer packet sizes of the communication channel. The information units may include a variable bit rate data stream, multimedia data, video data, and audio data. The communication channels include CMDA channels, WCDMA, GSM channels, GPRS channels, and EDGE channels.