公开(公告)号：US06574596B2

公开(公告)日：2003-06-03

申请号：US09248513

申请日：1999-02-08

申请人： Ning Bi ,  Chienchung Chang ,  Harinath Garudadri ,  Andrew P. Dejaco

发明人： Ning Bi ,  Chienchung Chang ,  Harinath Garudadri ,  Andrew P. Dejaco

IPC分类号： G10L1504

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 third predefined relationships may advantageously be linear relationships.

摘要翻译： 用于捕获话语的语音识别拒绝方案包括接受发音的步骤，将N最佳算法应用于话语或拒绝话语。 如果在一个或多个最接近的比较结果之间存在关于存储的单词的一个或多个最接近的比较结果与一个或多个最接近的比较结果之间的一个或多个差异以及话语和语音的一个或多个其他比较结果之间存在第一预定义关系， 一个或多个其他存储的字。 如果在一个或多个最接近的比较结果与一个或多个最接近的比较结果与一个或多个其他比较结果之间的一个或多个差异存在第二预定关系，那么将N最佳算法应用于话语。 如果一个或多个最接近的比较结果与一个或多个最接近的比较结果与一个或多个其它比较结果之间的一个或多个差异存在第三预定关系，那么话语被拒绝。 一个或多个其它比较结果中的一个可以有利地是用于话语和另一个存储词的下一个最接近的比较结果。 第一，第二和第三预定关系可以有利地是线性关系。

公开(公告)号：US06434519B1

公开(公告)日：2002-08-13

申请号：US09356861

申请日：1999-07-19

申请人： Sharath Manjunath ,  Andrew P. Dejaco ,  Arasanipalai K. Ananthapadmanabhan ,  Pengjun Huang ,  Eddie Lun Tik Choy

发明人： Sharath Manjunath ,  Andrew P. Dejaco ,  Arasanipalai K. Ananthapadmanabhan ,  Pengjun Huang ,  Eddie Lun Tik Choy

IPC分类号： G10L1914

CPC分类号： G10L19/0208 ,  G10L19/10

摘要： A method and apparatus for identifying frequency bands to compute linear phase shifts between frame prototypes in a speech coder includes partitioning the frequency spectrum of a prototype of a frame by dividing the frequency spectrum into segments, assigning one or more bands to each segment, and establishing, for each segment, a set of bandwidths for the bands. The bandwidths may be fixed and uniformly distributed in any given segment. The bandwidths may be fixed and non-uniformly distributed in any segment. The bandwidths may be variable and non-uniformly distributed in any given segment.

摘要翻译： 用于识别用于计算语音编码器中的帧原型之间的线性相移的频带的方法和装置包括：通过将频谱划分成段，将一个或多个频带分配给每个分段来建立帧的原型的频谱，并建立 ，对于每个段，一组带宽的带宽。 带宽可以是固定的，并且均匀分布在任何给定的段中。 带宽可以是固定的，并且不均匀地分布在任何段中。 带宽可以是可变的，并且不均匀地分布在任何给定的段中。

公开(公告)号：US06324509B1

公开(公告)日：2001-11-27

申请号：US09246414

申请日：1999-02-08

申请人： Ning Bi ,  Chienchung Chang ,  Andrew P. Dejaco

发明人： Ning Bi ,  Chienchung Chang ,  Andrew P. Dejaco

IPC分类号： G10L1504

CPC分类号： G10L25/87 ,  G10L2025/786

摘要： An apparatus for accurate endpointing of speech in the presence of noise includes a processor and a software module. The processor executes the instructions of the software module to compare an utterance with a first signal-to-noise-ratio (SNR) threshold value to determine a first starting point and a first ending point of the utterance. The processor then compares with a second SNR threshold value a part of the utterance that predates the first starting point to determine a second starting point of the utterance. The processor also then compares with the second SNR threshold value a part of the utterance that postdates the first ending point to determine a second ending point of the utterance. The first and second SNR threshold values are recalculated periodically to reflect changing SNR conditions. The first SNR threshold value advantageously exceeds the second SNR threshold value.

摘要翻译： 用于在存在噪声的情况下准确地终止语音的装置包括处理器和软件模块。 处理器执行软件模块的指令，以将话语与第一信噪比（SNR）阈值进行比较，以确定话音的第一起始点和第一个终点。 然后，处理器与第二SNR阈值比较发声的一部分，该部分在第一起始点之前确定发音的第二起始点。 然后，处理器还与第二SNR阈值比较后续第一个终点的话语的一部分，以确定话语的第二个终点。 周期性地重新计算第一和第二SNR阈值以反映改变的SNR条件。 第一SNR阈值有利地超过第二SNR阈值。

公开(公告)号：US20090281796A1

公开(公告)日：2009-11-12

申请号：US12501196

申请日：2009-07-10

申请人： Khaled H. El-Maleh ,  Arasanipalai K. Ananthapadmanabhan ,  Andrew P. Dejaco

发明人： Khaled H. El-Maleh ,  Arasanipalai K. Ananthapadmanabhan ,  Andrew P. Dejaco

IPC分类号： G10L19/14

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.

摘要翻译： 如果传输介质或目标终端用窄带约束构成，则宽带语音信号必须转换为窄带语音信号。 典型的宽带至窄带转换方法是使用低通滤波器和下采样器消除3400Hz以上的频率。 然而，该方法产生消声语音，因为所得到的窄带信号具有平坦的频率响应。 这里呈现了增强宽带到窄带转换信号的声学质量的方法和装置。 带宽切换滤波器用于强调宽带信号的中等频率部分，使得所得到的窄带信号具有非平坦频谱。

公开(公告)号：US07184954B1

公开(公告)日：2007-02-27

申请号：US09260709

申请日：1999-03-01

申请人： Paul E. Jacobs ,  Andrew P. Dejaco

发明人： Paul E. Jacobs ,  Andrew P. Dejaco

IPC分类号： G10L21/02

CPC分类号： G10L19/005 ,  G10L25/69 ,  H03M13/00

摘要： A speech signal is decoded by a vocoder and the reconstructed speech samples are provided to a decoded frame check unit. The decoded frame check unit examines the energy of the reconstructed speech and compares the energy of the reconstructed speech to a range of acceptable energy values. If the energy is not within the range of energy values, a frame erasure is declared and the decoded frame is prevented from being to the speaker in the telephone. In the exemplary implementation, the speech is reconstructed by a vocoder which includes a postfilter which in turn includes automatic gain control. The automatic gain control element of a post filter includes a means for measuring the energy of the decoded speech data. This measured energy is used by the decoded frame check unit to decide whether to provide the decoded data to the user or to declare a frame erasure. This implementation reduces the amount of additional hardware necessary to implement the present invention.

摘要翻译： 语音信号由声码器解码，并且将重构的语音样本提供给解码帧校验单元。 解码帧检查单元检查重构语音的能量，并将重构语音的能量与可接受的能量值的范围进行比较。 如果能量不在能量值的范围内，则声明帧擦除，并且防止解码的帧被发送到电话中的扬声器。 在示例性实现中，语音由包括后置滤波器的声码器重构，后置滤波器又包括自动增益控制。 后置滤波器的自动增益控制元件包括用于测量解码语音数据的能量的装置。 被测量的能量由解码帧检查单元使用以决定是否向用户提供解码的数据或者声明帧擦除。 该实现减少了实现本发明所需的附加硬件的数量。

公开(公告)号：US06260009B1

公开(公告)日：2001-07-10

申请号：US09249060

申请日：1999-02-12

申请人： Andrew P. Dejaco

发明人： Andrew P. Dejaco

IPC分类号： G10L2100

CPC分类号： G10L19/12 ,  G10L19/173

摘要： A method and apparatus for CELP-based to CELP-based vocoder packet translation. The apparatus includes a formant parameter translator and an excitation parameter translator. The formant parameter translator includes a model order converter and a time base converter. The method includes the steps of translating the formant filter coefficients of the input packet from the input CELP format to the output CELP format and translating the pitch and codebook parameters of the input speech packet from the input CELP format to the output CELP format. The step of translating the formant filter coefficients includes the steps of converting the model order of the formant filter coefficients from the model order of the input CELP format to the model order of the output CELP format and converting the time base of the resulting coefficients from the input CELP format time base to the output CELP format time base.

摘要翻译： 一种用于基于CELP的基于CELP的声码器分组转换的方法和装置。 该装置包括共振峰参数转换器和激励参数转换器。 共振峰参数转换器包括模型顺序转换器和时基转换器。 该方法包括以下步骤：将输入分组的共振峰滤波器系数从输入CELP格式转换为输出CELP格式，并将输入语音分组的音调和码本参数从输入CELP格式转换为输出CELP格式。 翻译共振峰滤波器系数的步骤包括将共振峰滤波器系数的模型顺序从输入CELP格式的模型顺序转换为输出CELP格式的模型阶数的步骤，并将所得系数的时基从 输入CELP格式时基输出CELP格式时基。

公开(公告)号：US20080312917A1

公开(公告)日：2008-12-18

申请号：US12190524

申请日：2008-08-12

申请人： Arasanipalai K. Ananthapadmanabhan ,  Sharath Manjunath ,  Pengjun Huang ,  Eddie-Lun Tik Choy ,  Andrew P. Dejaco

发明人： Arasanipalai K. Ananthapadmanabhan ,  Sharath Manjunath ,  Pengjun Huang ,  Eddie-Lun Tik Choy ,  Andrew P. Dejaco

IPC分类号： G10L19/00

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.

摘要翻译： 用于预测量化浊音的方法和装置包括参数发生器和量化器。 参数发生器被配置为从诸如有声语音的预测语音的帧中提取参数，并且将提取的信息变换为频域表示。 量化器被配置为从当前帧的参数中减去先前帧的参数的加权和。 量化器被配置为量化差值。 可以添加原型提取器以首先提取要由参数发生器处理的音调周期原型。

公开(公告)号：US06519479B1

公开(公告)日：2003-02-11

申请号：US09283340

申请日：1999-03-31

申请人： Harinath Garudadri ,  Andrew P. Dejaco

发明人： Harinath Garudadri ,  Andrew P. Dejaco

IPC分类号： H04M100

CPC分类号： H04M1/271 ,  G10L15/22 ,  G10L2015/0638 ,  H04M1/56 ,  H04M1/57 ,  H04M3/4938

摘要： A spoken user interface for speech-enabled devices includes a processor and a set of software instructions that are executable by the processor and stored in nonvolatile memory. A user of the speech-enabled device is prompted to enter a voice tag associated with an entry in a call history of the speech-enabled device. The call history includes lists of incoming and outgoing email messages, and incoming and outgoing telephone calls. The user is prompted to enter a voice tag after associated with a telephone number or email address in the call history after a user-selected number of telephone calls has been sent from the speech-enabled device to that telephone number, or has been sent from the telephone with that telephone number to the speech-enabled device, or after a user-selected number of email messages has been sent from the speech-enabled device to that email address, or has been sent from that email address to the speech-enabled device. The user may populate a phonebook of the speech-enabled device with email addresses by sending an email message to the speech-enabled device from a computer and including additional email addresses in the To: field and/or the CC: field of the email message.

摘要翻译： 用于支持语音的设备的口语用户界面包括可由处理器执行并存储在非易失性存储器中的处理器和一组软件指令。 提示启用语音的设备的用户输入与启用语音的设备的呼叫历史中的条目相关联的语音标签。 呼叫历史包括传入和传出电子邮件消息的列表，以及呼入和拨出电话呼叫。 在用户选择的电话号码从已启用语音的设备发送到该电话号码之后，用户被提示输入与呼叫历史中的电话号码或电子邮件地址相关联的语音标签，或已从 具有该电话号码的电话到启用语音的设备，或者在用户选择的电子邮件数量已经从启用语音的设备发送到该电子邮件地址之后，或者已经从该电子邮件地址发送到支持语音的设备 设备。 用户可以通过从计算机发送电子邮件消息给启用语音的设备，并且在电子邮件消息中的To：字段和/或CC：字段中包括额外的电子邮件地址来填充具有电话地址的语音设备的电话簿 。

公开(公告)号：US06324503B1

公开(公告)日：2001-11-27

申请号：US09356860

申请日：1999-07-19

申请人： Sharath Manjunath ,  Andrew P. Dejaco

发明人： Sharath Manjunath ,  Andrew P. Dejaco

IPC分类号： G10L2102

CPC分类号： G10L19/005

摘要： A method and apparatus for providing feedback from the decoder to the encoder to improve performance in a predictive speech coder under frame erasure conditions includes notifying an encoder in a receiving speech coder if a decoder in the receiving speech coder fails to receive a frame transmitted by an encoder in a transmitting speech coder. A modified packet is transmitted from the encoder in the receiving speech coder to a decoder in the transmitting speech coder in response to the notification. The decoder in the transmitting speech coder notifies the encoder in the transmitting speech coder when the modified packet is received. The encoder in the transmitting speech coder then encodes a packet with a modified encoding format. The modified encoding format may be either a low-memory encoding format or a memoryless encoding format. The modified packet may have an erasure indicator bit set to a digital value of one.

摘要翻译： 一种用于在帧擦除条件下提供来自解码器到编码器的反馈以改善预测语音编码器中的性能的方法和装置，包括：如果接收语音编码器中的解码器未能接收到由 编码器在传输语音编码器中。 响应于通知，修改的分组从接收语音编码器中的编码器发送到发送语音编码器中的解码器。 发送语音编码器中的解码器在接收到修改的分组时通知发送语音编码器中的编码器。 然后，发送语音编码器中的编码器对具有修改的编码格式的分组进行编码。 修改的编码格式可以是低内存编码格式或无记忆编码格式。 修改的分组可以具有设置为数字值1的擦除指示符比特。

公开(公告)号：US08660840B2

公开(公告)日：2014-02-25

申请号：US12190524

申请日：2008-08-12

申请人： Arasanipalai K. Ananthapadmanabhan ,  Sarath Manjunath ,  Pengjun Huang ,  Eddie-Lun Tik Choy ,  Andrew P. Dejaco

发明人： Arasanipalai K. Ananthapadmanabhan ,  Sarath Manjunath ,  Pengjun Huang ,  Eddie-Lun Tik Choy ,  Andrew P. Dejaco

IPC分类号： G06F15/00 ,  G10L21/00 ,  G10L21/02 ,  G10L19/00

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.

摘要翻译： 用于预测量化浊音的方法和装置包括参数发生器和量化器。 参数发生器被配置为从诸如有声语音的预测语音的帧中提取参数，并且将提取的信息变换为频域表示。 量化器被配置为从当前帧的参数中减去先前帧的参数的加权和。 量化器被配置为量化差值。 可以添加原型提取器以首先提取要由参数发生器处理的音调周期原型。