专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

EP1374223B1 VOICE RECOGNITION SYSTEM USING IMPLICIT SPEAKER ADAPTATION 有权
标题翻译：语音识别系统使用隐含的说话人自适应
公开(公告)号：EP1374223B1
公开(公告)日：2007-09-05
申请号：EP02725288.1
申请日：2002-03-22
申请人： QUALCOMM INCORPORATED
发明人： MALAYATH, Narendranath , DEJACO, Andrew, P. , CHANG, Chienchung , JALIL, Suhail , BI, Ning , GARUDADRI, Harinath
IPC分类号： G10L15/06 , G10L15/14 , G10L15/12
CPC分类号： G10L15/142 , G10L15/07 , G10L15/10 , G10L15/12 , G10L15/144 , G10L15/32
摘要： A voice recognition (VR) system is disclosed that utilizes a combination of speaker independent (SI) (230 and 232) and speaker dependent (SD) (234) acoustic models. At least one SI acoustic model (230 and 232) is used in combination with at least one SD acoustic model (234) 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 ore more SD acoustic models (234). The hybrid VR system then uses the updated SD acoustic models (234) in combination with the at least one SI acoustic model (230 and 232) to provide improved VR performance during VR testing.

2. 发明授权

EP1368979B1 MOBILE COMMUNICATIONS USING WIDEBAND TERMINALS ALLOWING TANDEM-FREE OPERATION 有权
标题翻译：移动通信在宽带终端操作的应用程序，而级联编码ALLOW
公开(公告)号：EP1368979B1
公开(公告)日：2006-07-26
申请号：EP02721402.2
申请日：2002-03-15
申请人： QUALCOMM INCORPORATED
发明人： DEJACO, Andrew, P. , EL-MALEH, Khaled
IPC分类号： H04Q7/30
CPC分类号： H04W88/181
摘要： A call setup procedure is presented to permit vocoder bypass, which will allow the transmission of wideband speech packets between wideband terminals over narrowband transmission constraints. In addition, methods and apparatus are presented that allow the conversion between a wideband tandem-free operation, a narrowband tandem-free operation, and a standard tandem operation.

3. 发明公开

EP1354416A2 ENHANCED CONVERSION OF WIDEBAND SIGNALS TO NARROWBAND SIGNALS 有权
标题翻译：宽带SIGNALS作者窄带信号改进的转化
公开(公告)号：EP1354416A2
公开(公告)日：2003-10-22
申请号：EP02705910.4
申请日：2002-01-23
申请人： QUALCOMM INCORPORATED
发明人： EL-MALEH, Khaled, H. , ANANTHAPADMANABHAN, Arasanipalai, K. , DEJACO, Andrew, P.
IPC分类号： H04B1/00
CPC分类号： G10L21/038 , G10L19/26
摘要： Wideband speech signals must be converted to narrowband speech signals if the transmission medium or the destination terminal is constructed with narrowband constraints. A typical wideband-to-narrowband conversion method is the elimination of frequencies above 3400 Hz using a low pass filter and a down sampler. However, this method produces a muffled speech sound since the resulting narrowband signal has a flat frequency response. Methods and apparatus are presented herein to enhance the acoustic quality of a wideband-to-narrowband converted signal. A bandwidth switching filter is used to emphasize a mid-range frequency portion of the wideband signal so that the resulting narrowband signal has a non-flat frequency spectrum.

4. 发明公开

EP1279167A1 METHOD AND APPARATUS FOR PREDICTIVELY QUANTIZING VOICED SPEECH 有权
标题翻译：方法和装置发声语音信号的预测量化
公开(公告)号：EP1279167A1
公开(公告)日：2003-01-29
申请号：EP01927283.0
申请日：2001-04-20
申请人： QUALCOMM INCORPORATED
发明人： ANANTHAPADMANABHAN, Arasanipalai, K. , MANJUNATH, Sharath , HUANG, Pengjun , CHOY, Eddie-Lun, Tik , DEJACO, Andrew, P.
IPC分类号： G10L19/08 , G10L19/02
CPC分类号： G10L19/04 , G10L19/0204 , G10L19/032 , G10L19/08 , G10L19/097 , G10L19/26 , G10L25/12
摘要： A method and apparatus for predictively quantizing voiced speech includes a parameter generator and a quantizer. The parameter generator is configured to extract parameters from frames of predictive speech such as voiced speech, and to transform the extracted information to a frequency-domain representation. The quantizer is configured to subtract a weighted sum of the parameters for previous frames from the parameter for the current frame. The quantizer is configured to quantize the difference value. A prototype extractor may be added to first extract a pitch period prototype to be processed by the parameter generator.

5. 发明公开

EP1159735A1 VOICE RECOGNITION REJECTION SCHEME 有权
标题翻译：舍弃处理过程在语音识别
公开(公告)号：EP1159735A1
公开(公告)日：2001-12-05
申请号：EP00914513.7
申请日：2000-02-04
申请人： QUALCOMM Incorporated
发明人： BI, Ning , CHANG, Chienchung , GARUDADRI, Harinath , DEJACO, Andrew, P.
IPC分类号： G10L15/10 , G10L15/22
CPC分类号： G10L15/10 , G10L15/22
摘要： A voice recognition rejection scheme for capturing an utterance includes the steps accepting the utterance, applying an N-best algorithm to the utterance, or rejecting the utterance. The utterance is accepted if a first predefined relationship exists between one or more closest comparison results for the utterance with respect to a stored word and one or more differences between the one or more closest comparison results and one or more other comparison results between the utterance and one or more other stored words. An N-best algorithm is applied to the utterance if a second predefined relationship exists between the one or more closest comparison results and the one or more differences between the one or more closest comparison results and the one or more other comparison results. The utterance is rejected if a third predefined relationship exists between the one or more closest comparison results and the one or more differences between the one or more closest comparison results and the one or more other comparison results. One of the one or more other comparison results may advantageously be a next-closest comparison result for the utterance and another store word. The first, second, and an third predefined relationship may advantageously be linear relationships.

6. 发明公开

EP1151431A1 METHOD AND APPARATUS FOR TESTING USER INTERFACE INTEGRITY OF SPEECH-ENABLED DEVICES 有权
标题翻译：方法和装置完整性的测试接口语音控制器件
公开(公告)号：EP1151431A1
公开(公告)日：2001-11-07
申请号：EP00914515.2
申请日：2000-02-04
申请人： QUALCOMM Incorporated
发明人： DEJACO, Andrew, P. , WALTERS, Richard, P. , GARUDADRI, Harinath
IPC分类号： G10L15/22 , G10L15/00
CPC分类号： G10L15/01 , G10L15/22
摘要： An apparatus for testing user interface integrity of speech-enabled devices includes a processor (102) and a storage medium (104) coupled to the processor (102). A set of voiced utterances is stored in the storage medium (104). 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.

7. 发明公开

EP0806032A1 METHOD AND APPARATUS FOR DETECTION AND BYPASS OF TANDEM VOCODING 失效
标题翻译：方法和设备进行检测和串列逃税语音编码
公开(公告)号：EP0806032A1
公开(公告)日：1997-11-12
申请号：EP96904513.0
申请日：1996-01-25
申请人： QUALCOMM INCORPORATED
发明人： WEAVER, Lindsay, A., Jr. , LAM, S., Katherine , JACOBS, Paul, E. , GARDNER, Willima, R. , DEJACO, Andrew, P. , SIH, Gilbert, C.
IPC分类号： G10L11 , G10L19 , H04B7 , H04B14 , H04Q11 , H04W88
CPC分类号： H04W88/181 , G10L19/16
摘要： A first remote vocoder (15) receives analog voice (170) and produces packetized vocoder data (190) which is transmitted over a wireless link (20). A first local vocoder (35) receives the packetized vocoder data (190) from the wireless link (20). The first local vocoder (35) converts the packetized data (190) to a multibit PCM output (120). The first local vocoder (35) also adds a detection code to one of the least significant bits (LSB) of the PCM output (210). The first local vocoder (35) passes the PCM signal (210) to the PSTN (40). The first local vocoder (210) also receives PCM input (120) over the PSTN (40). The first local vocoder (35) constantly monitors the least significant bit of the PCM input (120) for a detection code indicating that a second local vocoder (55) is connected at the receiving end. If the first local vocoder (35) detects the detection code from the second local vocoder (55), it begins to substitute packetized data and a redundancy check for a second one of the LSB's of the outgoing PCM (210). The first local vocoder (35) also begins to monitor the second one of the LSB's of the incoming PCM (120). If the redundancy check indicates that valid packetized data has been received, the first local vocoder (35) stops converting the PCM output (120) into packetized data and simply passes the packetized data on the second one of the LSB's to the first remote vocoder (15) as packets (100). If at any time the redundancy check fails and the detection code is not detected, the first local vocoder (35) returns to converting the incoming PCM (190) to packetized data. In this way, the tandem vocoding arrangement is avoided.

8. 发明授权

EP1210767B1 METHOD AND APPARATUS FOR AUTOMATICALLY ADJUSTING SPEAKER AND MICROPHONE GAINS WITHIN A MOBILE TELEPHONE 有权
标题翻译：方法和设备增援麦克风和扬声器放大器的便携式电话机自动调整
公开(公告)号：EP1210767B1
公开(公告)日：2007-07-11
申请号：EP00921542.7
申请日：2000-03-29
申请人： QUALCOMM INCORPORATED
发明人： GUPTA, Samir , MAURO, Anthony, P. , DEJACO, Andrew, P.
IPC分类号： H03G3/32
CPC分类号： H03G3/32 , H04M1/6008 , H04M1/6016
摘要： The mobile telephone (100) is provided with the capability for automatically adjusting the gain of a microphone (102) of the telephone (100) based upon the detected noise level in which the cellular telephone (100) is operated. As the noise level increases, the gain of the microphone (102) is automatically decreased, thereby compensating for the natural tendency of telephone (100) users to speak more loudly in noisy environments. In the exemplary embodiment, the cellular telephone (100) includes a digital signal processor (110) configured or programmed to apply the detected noise level to look-up tables (116, 118) relating various noise levels to appropriate speaker (104) and microphone (102) gain levels. Also, in the exemplary embodiment, the mobile telephone (100) includes a speaker (104) and the gain of the speaker (104) is adjusted to incrase in response to an increase in the background noise level. A method of automatically adjusting the gain of speaker (104) in a wireless communications device (100) includes the steps of obtaining a digital value representing the available headroom, estimating the background noise level, and adjusting the volume based on the background noise estimate and the available headroom. Thus, for example, the need for manual volume control buttons on a cellular telephone (100) is eliminated.

9. 发明授权

EP1224663B1 A PREDICTIVE SPEECH CODER USING CODING SCHEME SELECTION PATTERNS TO REDUCE SENSITIVITY TO FRAME ERRORS 有权
标题翻译：与方式选择KODIERUNGSSHEMAPRÄDIKTIONSSPRACHKODIERER用于减少敏感性帧出错
公开(公告)号：EP1224663B1
公开(公告)日：2006-11-22
申请号：EP00978283.0
申请日：2000-10-26
申请人： QUALCOMM INCORPORATED
发明人： MANJUNATH, Sharath , DEJACO, Andrew, P. , ANANTHAPADMANABHAN, Arasanipalai, K. , CHOY, Eddie, Lun, Tik
IPC分类号： G10L19/14
CPC分类号： G10L19/18 , G10L19/02
摘要： A method and apparatus for using coding scheme selection patterns in a predictive speech coder to reduce sensitivity to frame error conditions includes a speech coder configured to select from among various predictive coding modes. After a predefined number of speech frames have been predictively coded, the speech coder codes one frame with a nonpredictive coding mode or a mildly predictive coding mode. The predefined number of frames can be determined in advance from the subjective standpoint of a listener. The predefined number of frames may be varied periodically. An average coding bit rate may be maintained for the speech coder by ensuring that an average coding bit rate is maintained for each successive pattern, or group, of predictively coded speech frames including at least one nonpredictively coded or mildly predictively coded speech frame.

10. 发明授权

EP1159732B1 ENDPOINTING OF SPEECH IN A NOISY SIGNAL 有权
标题翻译：语言终点法测定噪声信号
公开(公告)号：EP1159732B1
公开(公告)日：2005-11-23
申请号：EP00907221.6
申请日：2000-02-08
申请人： QUALCOMM INCORPORATED
发明人： BI, Ning , CHANG, Chienchung , DEJACO, Andrew, P.
IPC分类号： G10L11/02
CPC分类号： G10L25/87 , G10L2025/786

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式