-
公开(公告)号:ES2286014T3
公开(公告)日:2007-12-01
申请号:ES00914513
申请日:2000-02-04
Applicant: QUALCOMM INC
Inventor: BI NING , CHANG CHIENCHUNG , GARUDADRI HARINATH , DEJACO ANDREW P
Abstract: Un procedimiento de captura de una unidad de habla en un sistema (10) de reconocimiento de voz, que comprende las etapas de: comparar (18) la unidad de habla con una primera palabra almacenada para generar una primera puntuación; comparar (18) la unidad de habla con una segunda palabra almacenada para generar una segunda puntuación; y determinar (18) una diferencia entre la primera puntuación y la segunda puntuación; procesar (20) la unidad de habla basándose en la primera puntuación y la diferencia determinada por: comparar la primera puntuación con un primer valor umbral de pendiente y rechazar la unidad de habla si la primera puntuación es mayor que el primer valor umbral de pendiente; en caso contrario, comparar la primera puntuación con un segundo valor umbral de pendiente y aplicar un algoritmo N-best para verificar la unidad de habla si la primera puntuación es mayor que el segundo valor umbral de pendiente; en caso contrario, aceptar la unidad de habla; en el que el primer y segundovalor umbral de pendiente varían con la diferencia determinada.
-
公开(公告)号:CA2644505A1
公开(公告)日:2007-10-11
申请号:CA2644505
申请日:2007-03-29
Applicant: QUALCOMM INC
Inventor: SAGETONG PHOOM , GARUDADRI HARINATH , SRINIVASAMURTHY NAVEEN B , LUDWIN ALBERT SCOTT , CHUNG HYUKJUNE , REZNIK YURIY
IPC: G06F17/14
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:DK1374223T3
公开(公告)日:2007-10-08
申请号:DK02725288
申请日:2002-03-22
Applicant: QUALCOMM INC
Inventor: MALAYATH NARENDRANATH , JALIL SUHAIL , DEJACO ANDREW P , CHANG CHIENCHUNG , BI NING , GARUDADRI HARINATH
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
-
54.
公开(公告)号:MXPA06013211A
公开(公告)日:2007-03-01
申请号:MXPA06013211
申请日:2005-05-13
Applicant: QUALCOMM INC
Inventor: GARUDADRI HARINATH , SAGETONG PHOOM , NANDA SANJE
IPC: H04L12/00 , H04B7/00 , H04B7/216 , H04L12/28 , H04L12/56 , H04L12/66 , H04L29/06 , H04N7/26 , H04W28/06 , H04W72/12 , H04W84/04 , H04W88/18
Abstract: Se describen los metodos y aparatos para mejorar la transmision de informacion en canales de comunicacion inalambrica; estas tecnicas incluyen determina los canales de comunicacion disponibles para transmitir la informacion y determinar los tamanos posibles del paquete de capa fisica de los canales disponibles; se divide una unidad de informacion en partes en donde se selecciona el tamano de las partes para que coincidan con uno de los tamanos del paquete de capa fisica de los canales de comunicacion disponibles; otro aspecto es dividir la informacion en un numero de porciones que corresponda al numero de transmisiones que ocurren durante el intervalo de unidad de informacion y asignar cada division a una transmision correspondiente; pueden utilizarse las tecnicas para varios tipos de informacion, tal como datos multimedia, flujos de datos de velocidad de bit variable, o datos de audio; pueden utilizarse tambien las tecnicas con varios en las interfaces aereas, tal como el Sistema Global de Comunicacion Movil (GSM), Servicio de Radio de Paquete General (GPRS), Entorno GSM de Datos Mejorado (EDGE), o normas basadas en CDMA, tales como TIA/EIA-95-B (IS-95), TIA/EIA-98-C (IS-98), IS2000, HRPD, cdma2000, CDMA de Banda Ancha (WCDMA), y otras.
-
55.
公开(公告)号:MXPA06013193A
公开(公告)日:2007-02-14
申请号:MXPA06013193
申请日:2005-05-13
Applicant: QUALCOMM INC
Inventor: GARUDADRI HARINATH , HSU RAYMOND T-S , SAGETONG PHOOM
IPC: H04L29/00 , H04B7/00 , H04B7/216 , H04L12/00 , H04L12/28 , H04L12/56 , H04L12/66 , H04L29/06 , H04N7/26 , H04W28/06 , H04W72/12 , H04W84/04 , H04W88/18
Abstract: Se describen metodos y aparatos para mejorar la transmision de datos de multimedia sobre canales de comunicacion inalambrica; estas tecnicas incluyen determinar un tamano de paquete de capa fisica del sistema de comunicacion alambica y determinar un tamano maximo de un titulo comprimido; entonces, dividir una unidad de informacion, en donde el tamano de las particiones son seleccionadas de tal forma que despues que una particion es codificada y el titulo comprimido es el tamano del paquete de capa fisica, o menos; las tecnicas se pueden utilizar para varios tipos de informacion, tales como datos de multimedia, corrientes variables de datos de bit corrientes de video, corriente de teleconferencia de video o voz sobre IP; tambien se pueden utilizar las tecnicas con varias interfaces aereas, tales como, Sistema Global para Comunicacion Movil (GSM), Servicio General de Radio Paquete (GPRS), Ambiente mejorado GSN de datos (EDGE), o estandares basados en CDMA, tales como TIA/EIA-95-B, TIA/EIA-98-C (IS-98), IS2000, HDRP, CDMA2000, CDMA de banda ancha (WCDMA) y otros.
-
公开(公告)号:AT344959T
公开(公告)日:2006-11-15
申请号:AT01968568
申请日:2001-09-05
Applicant: QUALCOMM INC
Inventor: QI YINGYONG , BI NING , GARUDADRI HARINATH
Abstract: A method and system that combines voice recognition engines and resolves differences between the results of individual voice recognition engines using a mapping function. Speaker independent voice recognition engines and speaker-dependent voice recognition engines are combined. Hidden Markov Model (HMM) engines and Dynamic Time Warping (DTW) engines are combined.
-
公开(公告)号:CA2566126A1
公开(公告)日:2005-12-01
申请号:CA2566126
申请日:2005-05-13
Applicant: QUALCOMM INC
Inventor: GARUDADRI HARINATH , NANDA SANJIV , SAGETONG PHOOM
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.
-
58.
公开(公告)号:CA2566124A1
公开(公告)日:2005-12-01
申请号:CA2566124
申请日:2005-05-13
Applicant: QUALCOMM INC
Inventor: GARUDADRI HARINATH , SAGETONG PHOOM , NANDA SANJIE
IPC: H04L12/28 , H04B7/00 , H04B7/216 , 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:AU2003225235A1
公开(公告)日:2003-11-17
申请号:AU2003225235
申请日:2003-04-29
Applicant: QUALCOMM INC
Inventor: GARUDADRI HARINATH , SIVADAS SUNIL , HERMANSKY HYNEK , MORGAN NELSON H , WOOTERS CHARLES C , ADAMI ANDRE GUSTAVO , ORTUZAR MARIA CARMEN BENITEZ , BURGET LUKAS , DUPONT STEPHANE N , GREZL FRANTISEK , JAIN PRATIBHA , KAJAREKAR SACHIN , MOTLICEK PETR
Abstract: A distributed voice recognition system and method for obtaining acoustic features and speech activity at multiple frequencies by extracting high frequency components thereof on a device, such as a subscriber station and transmitting them to a network server having multiple stream processing capability, including cepstral feature processing, MLP nonlinear transformation processing, and multiband temporal pattern architecture processing. The features received at the network server are processed using all three streams, wherein each of the three streams provide benefits not available in the other two, thereby enhancing feature interpretation. Feature extraction and feature interpretation may operate at multiple frequencies, including but not limited to 8 kHz, 11 kHz, and 16 kHz.
-
公开(公告)号:HK1043233A1
公开(公告)日:2002-09-06
申请号:HK02103186
申请日:2002-04-29
Applicant: QUALCOMM INC
Inventor: DEJACO ANDREW P , WALTERS RICHARD P , GARUDADRI HARINATH
Abstract: An apparatus for testing user interface integrity of speech-enabled devices includes a processor and a storage medium coupled to the processor. A set of voiced utterances is stored in the storage medium. A software module is executed by the processor to determine a state of the voice recognizer and provide a response to the voice recognizer in accordance with the determined state. The response may be to produce at least one voiced utterance in accordance with the state. The apparatus may be acoustically coupled to the voice recognizer. The apparatus may also, or in the alternative, be electrically coupled by a cable to the voice recognizer. The set of voiced utterances may include multiple sets of voiced utterances, each set having been spoken by a different person. The set of voiced utterances may also, or in the alternative, include multiple sets of voiced utterances, each set of voiced utterances having been spoken under different background noise conditions. The software module may also be executable to monitor the performance of the voice recognizer.
-
-
-
-
-
-
-
-
-