Method and apparatus for multi-stage adaptive volume control
    1.
    发明授权
    Method and apparatus for multi-stage adaptive volume control 有权
    多级自适应音量控制的方法和装置

    公开(公告)号:US09099972B2

    公开(公告)日:2015-08-04

    申请号:US13509619

    申请日:2012-03-13

    IPC分类号: H03G3/00 H03G3/20 H04M1/60

    CPC分类号: H03G3/20 H04M1/6041

    摘要: A method and apparatus for adaptively controlling the audio output (122) of a communication device (114) according to the noise characteristics of the receiver listening environment (119). An output volume for the communication device (114) is set by a user (e.g., listener 118). The communication device (114) can intermittently sample ambient noise (116) of its environment (119). A minimum signal to noise threshold can be established for audio output (122). A total adjustment for the audio output (122) is established based on the ambient noise (116), the user set output volume, and the minimum signal to noise threshold. The total adjustment is a product of a software volume adjustment (230) and a hardware gain adjustment (240). The software volume adjustment (230) and the hardware gain adjustment (240) is adaptively applied when the communication device (114) outputs audio (122).

    摘要翻译: 一种用于根据接收机收听环境(119)的噪声特性自适应地控制通信设备(114)的音频输出(122)的方法和装置。 通信设备(114)的输出音量由用户(例如,听众118)设置。 通信设备(114)可以间歇地对其环境(119)的环境噪声(116)进行采样。 可以为音频输出(122)建立最小信号噪声阈值。 基于环境噪声(116),用户设定输出音量和最小信号噪声阈值来建立音频输出(122)的总体调整。 总体调整是软件音量调整(230)和硬件增益调整(240)的产物。 当通信设备(114)输出音频(122)时,自适应地应用软件音量调节(230)和硬件增益调整(240)。

    METHOD AND APPARATUS FOR MULTI-STAGE ADAPTIVE VOLUME CONTROL
    2.
    发明申请
    METHOD AND APPARATUS FOR MULTI-STAGE ADAPTIVE VOLUME CONTROL 有权
    用于多级自适应体积控制的方法和装置

    公开(公告)号:US20150016633A1

    公开(公告)日:2015-01-15

    申请号:US13509619

    申请日:2012-03-13

    IPC分类号: H03G3/20

    CPC分类号: H03G3/20 H04M1/6041

    摘要: A method and apparatus for adaptively controlling the audio output (122) of a communication device (114) according to the noise characteristics of the receiver listening environment (119). An output volume for the communication device (114) is set by a user (e.g., listener 118). The communication device (114) can intermittently sample ambient noise (116) of its environment (119). A minimum signal to noise threshold can be established for audio output (122). A total adjustment for the audio output (122) is established based on the ambient noise (116), the user set output volume, and the minimum signal to noise threshold. The total adjustment is a product of a software volume adjustment (230) and a hardware gain adjustment (240). The software volume adjustment (230) and the hardware gain adjustment (240) is adaptively applied when the communication device (114) outputs audio (122).

    摘要翻译: 一种用于根据接收机收听环境(119)的噪声特性自适应地控制通信设备(114)的音频输出(122)的方法和装置。 通信设备(114)的输出音量由用户(例如,听众118)设置。 通信设备(114)可以间歇地对其环境(119)的环境噪声(116)进行采样。 可以为音频输出(122)建立最小信号噪声阈值。 基于环境噪声(116),用户设定输出音量和最小信号噪声阈值来建立音频输出(122)的总体调整。 总体调整是软件音量调整(230)和硬件增益调整(240)的产物。 当通信设备(114)输出音频(122)时,自适应地应用软件音量调节(230)和硬件增益调整(240)。

    METHOD AND APPARATUS FOR REMOVING PERIODIC NOISE PULSES IN AN AUDIO SIGNAL
    3.
    发明申请
    METHOD AND APPARATUS FOR REMOVING PERIODIC NOISE PULSES IN AN AUDIO SIGNAL 有权
    用于在音频信号中移除周期性噪声脉冲的方法和装置

    公开(公告)号:US20080019538A1

    公开(公告)日:2008-01-24

    申请号:US11459379

    申请日:2006-07-24

    IPC分类号: H04B15/00

    摘要: A method for removing periodic noise pulses from a continuous audio signal generated in a pressurized air delivery system includes the steps of: detecting, in a time-windowed segment of the continuous audio signal generated in the pressurized air delivery system, a plurality of the periodic noise pulses having a pulse period and being representable in the form of a plurality of signal components combined by convolution; deconvolving the plurality of signal components to generate a plurality of deconvolved signal components; and removing at least a portion of the periodic noise pulses from the time-windowed segment of the continuous audio signal using the deconvolved signal components.

    摘要翻译: 一种用于从加压空气输送系统中产生的连续音频信号中去除周期性噪声脉冲的方法包括以下步骤:在加压空气输送系统中产生的连续音频信号的时间窗口段中检测多个周期性 噪声脉冲具有脉冲周期并且可以以通过卷积组合的多个信号分量的形式表示; 对所述多个信号分量进行解卷积以产生多个解卷积信号分量; 以及使用去卷积的信号分量从所述连续音频信号的时间窗口段去除所述周期性噪声脉冲的至少一部分。

    Speech recognition using unequally-weighted subvector error measures for determining a codebook vector index to represent plural speech parameters
    4.
    发明授权
    Speech recognition using unequally-weighted subvector error measures for determining a codebook vector index to represent plural speech parameters 有权
    使用不等权重子向量误差测量的语音识别,用于确定代码多个语音参数的码本矢量索引

    公开(公告)号:US06389389B1

    公开(公告)日:2002-05-14

    申请号:US09417371

    申请日:1999-10-13

    IPC分类号: G10L1508

    CPC分类号: G10L15/02 G10L15/10

    摘要: Quantization unit (108) comprises evaluator (120) and comparator (122) in signal processing for identifying an utterance in system (100). The evaluator (120) weights a first intermediate result of an operation on a first set of a plurality of speech parameters (104) differently than a second intermediate result of an operation on a second set of the plurality of speech parameters (104) in a weighted representation of the plurality of speech parameters (104). The comparator (122) employs the weighted representation of the plurality of speech parameters (104) to determine a vector index to represent the plurality of speech parameters (104). The quantization unit (108), in one example, can employ split vector quantization in conjunction with the weighted representation to determine a vector index to represent the plurality of speech parameters (104).

    摘要翻译: 量化单元(108)包括用于识别系统(100)中的话语的信号处理中的评估器(120)和比较器(122)。 评估器(120)对第一组多个语音参数(104)的操作的第一中间结果与在第一组多个语音参数(104)中的操作的第二中间结果不同地加权 多个语音参数(104)的加权表示。 比较器(122)使用多个语音参数(104)的加权表示来确定用于表示多个语音参数(104)的向量索引。 在一个示例中,量化单元(108)可以结合加权表示使用分割向量量化,以确定用于表示多个语音参数(104)的向量索引。

    Method, apparatus, and radio optimizing Hidden Markov Model speech
recognition
    5.
    发明授权
    Method, apparatus, and radio optimizing Hidden Markov Model speech recognition 失效
    方法,设备和无线电优化隐马尔可夫模型语音识别

    公开(公告)号:US5617509A

    公开(公告)日:1997-04-01

    申请号:US413146

    申请日:1995-03-29

    IPC分类号: G10L15/14 G10L9/00

    CPC分类号: G10L15/142

    摘要: In a statistical based speech recognition system, one of the key issues is the selection of the Hidden Markov Model that best matches a given sequence of feature observations. The problem is usually addressed by the calculation of the maximum likelihood, ML, state sequence by means of a Viterbi or other decoder. Noise or inadequate training can produce a ML sequence associated with a Hidden Markov Model other than the correct model. The method of the present invention provides improved robustness by combining the standard ML state sequence score (416) with an additional path score (418) derived from the dynamics of the ML score as a function of time. These two scores, when combined, form a hybrid metric (420) that, when used with the decoder, optimizes selection of the correct Hidden Markov Model (422).

    摘要翻译: 在基于统计的语音识别系统中,关键问题之一是选择与给定的特征观测序列最匹配的隐马尔可夫模型。 通常通过维特比或其他解码器的最大似然度ML,状态序列的计算来解决该问题。 噪音或训练不足可以产生与正确模型以外的隐马尔可夫模型相关的ML序列。 本发明的方法通过将标准ML状态序列得分(416)与作为时间的函数的ML得分的动力学导出的附加路径得分(418)组合来提供改进的鲁棒性。 当组合时,这两个分数形成混合度量(420),当与解码器一起使用时,优化选择正确的隐马尔可夫模型(422)。

    Method and apparatus for removing from an audio signal periodic noise pulses representable as signals combined by convolution
    6.
    发明授权
    Method and apparatus for removing from an audio signal periodic noise pulses representable as signals combined by convolution 有权
    用于从音频信号中去除周期性噪声脉冲的方法和装置,其作为通过卷积组合的信号可表示

    公开(公告)号:US07809559B2

    公开(公告)日:2010-10-05

    申请号:US11459379

    申请日:2006-07-24

    IPC分类号: G10L21/02 G10L19/00 H04B15/00

    摘要: A method for removing periodic noise pulses from a continuous audio signal generated in a pressurized air delivery system includes the steps of: detecting, in a time-windowed segment of the continuous audio signal generated in the pressurized air delivery system, a plurality of the periodic noise pulses having a pulse period and being representable in the form of a plurality of signal components combined by convolution; deconvolving the plurality of signal components to generate a plurality of deconvolved signal components; and removing at least a portion of the periodic noise pulses from the time-windowed segment of the continuous audio signal using the deconvolved signal components.

    摘要翻译: 一种用于从加压空气输送系统中产生的连续音频信号中去除周期性噪声脉冲的方法包括以下步骤:在加压空气输送系统中产生的连续音频信号的时间窗口段中检测多个周期性 噪声脉冲具有脉冲周期并且可以以通过卷积组合的多个信号分量的形式表示; 对所述多个信号分量进行解卷积以产生多个解卷积信号分量; 以及使用去卷积的信号分量从所述连续音频信号的时间窗口段去除所述周期性噪声脉冲的至少一部分。

    Method for detecting and attenuating inhalation noise in a communication system
    8.
    发明授权
    Method for detecting and attenuating inhalation noise in a communication system 有权
    在通信系统中检测和减弱吸入噪声的方法

    公开(公告)号:US07139701B2

    公开(公告)日:2006-11-21

    申请号:US10882452

    申请日:2004-06-30

    IPC分类号: G10L19/00

    摘要: A method for detecting and attenuating inhalation noise in a communication system coupled to a pressurized air delivery system, the method including the steps of: generating an inhalation noise model (912, 1012) based on inhalation noise; receiving an input signal (802) that includes inhalation noise; comparing (810) the input signal to the noise model to obtain a similarity measure; determining (854) a gain factor based on the similarity measure; and modifying (852) the input signal based on the gain factor, wherein the inhalation noise in the input signal is attenuated based on the gain factor.

    摘要翻译: 一种用于在耦合到加压空气输送系统的通信系统中检测和减弱吸入噪声的方法,所述方法包括以下步骤:基于吸入噪声产生吸入噪声模型(912,1012); 接收包括吸入噪声的输入信号(802); 将输入信号与噪声模型进行比较(810)以获得相似性度量; 基于相似性度量确定(854)增益因子; 以及基于所述增益因子来修改(852)所述输入信号,其中所述输入信号中的吸入噪声基于所述增益因子衰减。

    Method and apparatus for speech reconstruction in a distributed speech recognition system
    9.
    发明授权
    Method and apparatus for speech reconstruction in a distributed speech recognition system 有权
    分布式语音识别系统中语音重建的方法和装置

    公开(公告)号:US06633839B2

    公开(公告)日:2003-10-14

    申请号:US09775951

    申请日:2001-02-02

    IPC分类号: G10L1500

    摘要: In a distributed speech recognition system comprising a first communication device which receives a speech input (34), encodes data representative of the speech input, and transmits the encoded data and a second remotely-located communication device which receives the encoded data and compares the encoded data with a known data set, the device including a processor with a program which controls the processor to operate according to a method of reconstructing the speech input including the step of receiving encoded data including encoded spectral data and encoded energy data. The method further includes the step of decoding the encoded spectral data and encoded energy data to determine the spectral data and energy data. The method also includes the step of combining the spectral data and energy data to reconstruct the speech input.

    摘要翻译: 在包括接收语音输入( 34 )的第一通信设备的分布式语音识别系统中,对表示语音输入的数据进行编码,并将编码数据和第二远程 接收编码数据并将编码数据与已知数据集进行比较的装置,该装置包括具有程序的处理器,该程序控制处理器根据重构语音输入的方法进行操作,该方法包括接收编码数据的步骤 包括编码的光谱数据和编码的能量数据。 该方法还包括对编码的光谱数据和编码的能量数据进行解码以确定光谱数据和能量数据的步骤。 该方法还包括组合光谱数据和能量数据以重构语音输入的步骤

    Communication device and method for endpointing speech utterances
    10.
    发明授权
    Communication device and method for endpointing speech utterances 有权
    用于终止语音语音的通信设备和方法

    公开(公告)号:US06321197B1

    公开(公告)日:2001-11-20

    申请号:US09235952

    申请日:1999-01-22

    IPC分类号: G10L1504

    CPC分类号: G10L25/87

    摘要: A communication device capable of endpointing speech utterances includes a microprocessor (110) connected to communication interface circuitry (115), memory (120), audio circuitry (130), an optional keypad (140), a display (150), and a vibrator/buzzer (160). Audio circuitry (130) is connected to microphone (133) and speaker (135). Microprocessor (110) includes a speech/noise classifier and speech recognition technology. Microprocessor (110) analyzes a speech signal to determine speech waveform parameters within a speech acquisition window. Microprocessor (110) compares the speech waveform parameters to determine the start and end points of the speech utterance. Microprocessor (110) starts at a frame index based on the energy centroid of the speech utterance and analyzes the frames preceding and following the frame index to determine the endpoints. When a potential endpoint is identified, microprocessor (110) compares the cumulative energy to the total energy of the speech acquisition window to determine whether additional speech frames are present. Accordingly, gaps and pauses in the utterance will not result in an erroneous endpoint determination.

    摘要翻译: 能够终止语音话语的通信设备包括连接到通信接口电路(115),存储器(120),音频电路(130),可选小键盘(140),显示器(150)和振动器 /蜂鸣器(160)。 音频电路(130)连接到麦克风(133)和扬声器(135)。 微处理器(110)包括语音/噪声分类器和语音识别技术。 微处理器(110)分析语音信号以确定语音采集窗口内的语音波形参数。 微处理器(110)比较语音波形参数以确定语音话语的开始和结束点。 微处理器(110)基于语音话音的能量中心以帧索引开始,并且分析帧索引之前和之后的帧以确定端点。 当识别出潜在端点时,微处理器(110)将累积能量与语音获取窗口的总能量进行比较,以确定是否存在附加语音帧。 因此,话语中的间隙和暂停不会导致错误的端点确定。