公开(公告)号：US06778955B2

公开(公告)日：2004-08-17

申请号：US10265640

申请日：2002-10-08

申请人： Xinde Li ,  Yuri Sokolov ,  Hans Kunov

发明人： Xinde Li ,  Yuri Sokolov ,  Hans Kunov

IPC分类号： G10L2102

CPC分类号： A61B5/121 ,  G10L21/02 ,  G10L21/0232 ,  G10L21/06

摘要： A system and method for use in a real time system and for processing a signal with a low signal-to-noise ratio (SNR). The system comprises a model for modeling an expected signal and a filter that uses the model for filtering the signal. The filter is used for generating a prediction of the signal and an error variance matrix. The system further comprises an adaptive element for modifying the error variance matrix such that the bandwidth of the filter is widened, wherein the filter behaves like an adaptive filter.

摘要翻译： 一种用于实时系统并用于处理具有低信噪比（SNR）的信号的系统和方法。 该系统包括用于对期望信号建模的模型和使用该模型对该信号进行滤波的滤波器。 滤波器用于产生信号的预测和误差方差矩阵。 该系统还包括用于修改误差方差矩阵的自适应元件，使得滤波器的带宽变宽，其中滤波器的行为像自适应滤波器。

公开(公告)号：US06778954B1

公开(公告)日：2004-08-17

申请号：US09572232

申请日：2000-05-17

申请人： Moo-young Kim ,  Sang-ryong Kim ,  Nam-soo Kim

发明人： Moo-young Kim ,  Sang-ryong Kim ,  Nam-soo Kim

IPC分类号： G10L2102

CPC分类号： G10L21/0208

摘要： A speech enhancement method, including the steps of: (a) segmenting an input speech signal into a plurality of frames and transforming each frame signal into a signal of the frequency domain; (b) computing the signal-to-noise ratio of a current frame, and computing signal-to-noise ratio of a frame immediately preceding the current frame; (c) computing the predicted signal-to-noise ratio of the current frame which is predicted based on the preceding frame and computing the speech absence probability using the signal-to-noise ratio and predicted signal-to-noise ratio of the current frame; (d) correcting the two signal-to-noise ratios obtained in the step (b) based on the speech absence probability computed in the step (c); (e) computing the gain of the current frame with the two corrected signal-to-noise ratios obtained in the step (d), and multiplying the speech spectrum of the current frame by the computed gain; (f) estimating the noise and speech power for the next frame to calculate the predicted signal-to-noise ratio for the next frame, and providing the predicted signal-to-noise ratio for the next frame as the predicted signal-to-noise ratio of the current frame for the step (c); and (g) transforming the result spectrum of the step (e) into a signal of the time domain. The noise spectrum is estimated in speech presence intervals based on the speech absence probability, as well as in speech absence intervals, and the predicted SNR and gain are updated on a per-channel basis of each frame according to the noise spectrum estimate, which in turn improves the speech spectrum in various noise environments.

摘要翻译： 一种语音增强方法，包括以下步骤：（a）将输入语音信号分割为多个帧，并将每个帧信号变换成频域的信号; （b）计算当前帧的信噪比，以及计算紧邻当前帧之前的帧的信噪比; （c）计算基于前一帧预测的当前帧的预测信噪比，并使用当前帧的信噪比和预测信噪比来计算语音缺失概率 ; （d）基于步骤（c）中计算出的语音缺失概率来校正在步骤（b）中获得的两个信噪比; （e）利用步骤（d）中获得的两个校正的信噪比来计算当前帧的增益，并将当前帧的语音频谱乘以所计算的增益; （f）估计下一帧的噪声和语音功率，以计算下一帧的预测信噪比，并将下一帧的预测信噪比作为预测信噪比 步骤（c）的当前帧的比率; 和（g）将步骤（e）的结果谱变换成时域的信号。 基于语音不存在概率以及在无语音间隔中的语音存在间隔中估计噪声频谱，并且根据噪声频谱估计在每帧的每个信道的基础上更新预测的SNR和增益。 转动改善了各种噪音环境中的语音频谱。

公开(公告)号：US06768979B1

公开(公告)日：2004-07-27

申请号：US09282809

申请日：1999-03-31

申请人： Xavier Menéndez-Pidal ,  Miyuki Tanaka ,  Ruxin Chen

发明人： Xavier Menéndez-Pidal ,  Miyuki Tanaka ,  Ruxin Chen

IPC分类号： G10L2102

CPC分类号： G10L21/0208 ,  F16J15/43 ,  G10L15/02 ,  G10L21/0264 ,  G11B19/2009

摘要： The noise suppressor utilizes statistical characteristics of the noise signal to attenuate amplitude values of the noisy speech signal that have a probability of containing noise. In one embodiment, the noise suppressor utilizes an attenuation function having a shape determined in part by a noise average and a noise standard deviation. In a further embodiment, the noise suppressor also utilizes an adaptive attenuation coefficient that depends on signal-to-noise conditions in the speech recognition system.

摘要翻译： 噪声抑制器利用噪声信号的统计特性来衰减具有包含噪声的概率的噪声语音信号的振幅值。 在一个实施例中，噪声抑制器利用具有部分由噪声平均值和噪声标准偏差确定的形状的衰减函数。 在另一实施例中，噪声抑制器还利用取决于语音识别系统中的信噪比条件的自适应衰减系数。

公开(公告)号：US06718298B1

公开(公告)日：2004-04-06

申请号：US09690402

申请日：2000-10-17

申请人： Rupinder Judge

发明人： Rupinder Judge

IPC分类号： G10L2102

CPC分类号： G10L19/012 ,  H04M1/656

摘要： Speech recording is effected in a GSM phone handset (100) by storing in a memory (116) speech frames during the presence of speech, one or more SID frames during the absence of speech, and data representative of the duration of the absence of speech. In this way memory (116) does not store silent speech frames, and utilisation of memory space is therefore particularly efficient. In addition, items such as a voice activity detector and a comfort noise estimator, which are already provided in the handset as part of the GSM system, are “re-used” by the invention, thereby making efficient use of already-provided hardware/software.

摘要翻译： 通过在语音存在期间存储在存储器（116）中的语音帧，在不存在语音期间存在一个或多个SID帧，以及表示语音不存在的持续时间的数据，在GSM电话手机（100）中进行语音记录 。 以这种方式，存储器（116）不存储静音语音帧，因此存储空间的利用特别有效。 此外，作为GSM系统的一部分已经提供在手机中的诸如语音活动检测器和舒适噪声估计器的项目被本发明“重用”，从而有效地利用已经提供的硬件/ 软件。

公开(公告)号：US06493665B1

公开(公告)日：2002-12-10

申请号：US09154662

申请日：1998-09-18

申请人： Huan-Yu Su ,  Yang Gao

发明人： Huan-Yu Su ,  Yang Gao

IPC分类号： G10L2102

CPC分类号： G10L19/005 ,  G10L19/002 ,  G10L19/012 ,  G10L19/08 ,  G10L19/083 ,  G10L19/09 ,  G10L19/10 ,  G10L19/12 ,  G10L19/125 ,  G10L19/18 ,  G10L19/265 ,  G10L21/0364 ,  G10L2019/0005 ,  G10L2019/0007 ,  G10L2019/0011

摘要： A multi-rate speech coded supports a plurality of encoding bit rate modes by adaptively selecting encoding bit rate modes to match communication channel restrictions. In higher bit rate encoding modes, an accurate representation of speech through CELP (code excited linear prediction) and other associated modeling parameters are generated for higher quality decoding and reproduction. To support lower bit rate encoding modes, a variety of techniques are applied many of which involve the classification of the input signal. For each bit rate mode selected, pluralities of fixed or innovation subcodebooks are selected for use in generating innovation vectors. The fixed codebook contains pulse subcodebooks and noise-like subcodebooks. To assist in selection of one of the subcodebooks, an adaptive weighting approach is applied in a searching procedure wherein residual classification and various parameters are used to generate a weighting function that is used to favor one subcodebook over another. The pulse subcodebooks are favored to code pulse-like residuals, while the noise-like subcodebooks are favored to code noise-like residuals. The classification may involve identification of noise-like residuals, while the various parameters may comprise pitch correlation, signal to noise ratio, and average to peak ratio. Favoring involves an adjustment to a weighting factor applied to the subcodebooks.

摘要翻译： 通过自适应地选择编码比特率模式以匹配通信信道限制，多速率语音编码支持多种编码比特率模式。 在较高的比特率编码模式中，通过CELP（码激励线性预测）和其他相关联的建模参数的语音的精确表示被生成用于更高质量的解码和再现。 为了支持较低比特率编码模式，应用了许多技术，其中许多技术涉及输入信号的分类。 对于所选择的每个比特率模式，选择多个固定或创新子码本来用于产生创新向量。 固定码本包含脉冲子码本和类噪声子码。 为了帮助选择一个子码本，在搜索过程中应用自适应加权方法，其中使用残差分类和各种参数来产生用于有利于一个子码本的加权函数。 脉冲子码本有利于编码类似脉冲的残差，而类似噪声的子代码则有利于编码类似噪声的残差。 该分类可以涉及噪声类残差的识别，而各种参数可以包括音调相关性，信噪比和平均峰值比。 喜好涉及到适用于子码本的加权因子的调整。

公开(公告)号：US06363345B1

公开(公告)日：2002-03-26

申请号：US09252874

申请日：1999-02-18

申请人： Joseph Marash ,  Baruch Berdugo

发明人： Joseph Marash ,  Baruch Berdugo

IPC分类号： G10L2102

CPC分类号： G10L25/78 ,  G10L21/0208

摘要： A threshold detector precisely detects the positions of the noise elements, even within continuous speech segments, by determining whether frequency spectrum elements, or bins, of the input signal are within a threshold set according to current and future minimum values of the frequency spectrum elements. In addition, the threshold is continuously set and initiated within a predetermined period of time. The estimate magnitude of the input audio signal is obtained using a multiplying combination of the real and imaginary part of the input in accordance with the higher and lower values between the real and imaginary part of the signal. In order to further reduce instability of the spectral estimation, a two-dimensional smoothing is applied to the signal estimate using neighboring frequency bins and an exponential average over time. A filter multiplication effects the subtraction thereby avoiding phase calculation difficulties and effecting full-wave rectification which further reduces artifacts. Since the noise elements are determined within continuous speech segments, the noise is canceled from the audio signal nearly continuously thereby providing excellent noise cancellation characteristics. Residual noise reduction reduces the residual noise remaining after noise cancellation. Implementation may be effected in various noise canceling schemes including adaptive beamforming and noise cancellation using computer program applications installed as software or hardware.

摘要翻译： 阈值检测器通过确定输入信号的频谱元素是否在根据频谱元素的当前和未来最小值设置的阈值内，甚至在连续语音段内精确地检测噪声元素的位置。 此外，阈值在预定时间段内被连续地设置和启动。 根据信号的实部和虚部之间的较高和较低值，使用输入的实部和虚部的相乘组合来获得输入音频信号的估计幅度。 为了进一步减少频谱估计的不稳定性，使用相邻频率仓和随时间的指数平均值对信号估计应用二维平滑。 滤波器乘法实现减法，从而避免相位计算困难，并实现全波整流，进一步减少伪像。 由于在连续语音段内确定了噪声要素，所以几乎连续地从音频信号中消除噪声，从而提供优异的噪声消除特性。 残余噪声降低降低噪声消除后剩余的残留噪声。 实现可以在各种噪声消除方案中实现，包括使用安装为软件或硬件的计算机程序应用的自适应波束形成和噪声消除。

公开(公告)号：US06266633B1

公开(公告)日：2001-07-24

申请号：US09218565

申请日：1998-12-22

申请人： Alan Lawrence Higgins ,  Steven F. Boll ,  Jack E. Porter

发明人： Alan Lawrence Higgins ,  Steven F. Boll ,  Jack E. Porter

IPC分类号： G10L2102

CPC分类号： G10L21/0208

摘要： A method for performing noise suppression and channel equalization of a noisy voice signal comprising the steps of sampling the noisy voice signal at a predetermined sampling rate fs; segmenting the sampled voice signal into a plurality of frames having a predetermined number of samples per frame, over a predetermined temporal window; generating an N-point spectral sample representation of each of the sample signal frames; determining the magnitude of each of the N-point spectral samples and generating a histogram of the energy associated with each of the N-point spectral samples at a particular frequency; detecting a peak amplitude of the histogram which corresponds to a noise threshold Nf associated with the particular frequency; determining a channel frequency response Cf associated with the particular frequency by determining a geometric mean over all the spectral samples having magnitude exceeding the noise threshold Nf; subtracting from each of the magnitudes of the N point spectral samples the noise threshold Nf to provide a noise suppressed sample sequence; applying blind deconvolution to the noise suppressed samples; transforming the deconvolved noise suppressed sampled sequence to a temporal representation; shifting the temporal sample sequence in time by a predetermined amount; and adding the time shifted temporal samples over a period corresponding to the predetermined temporal window to provide a suppressed noise voice signal.

摘要翻译： 一种用于对噪声声音信号执行噪声抑制和信道均衡的方法，包括以预定采样率fs对噪声语音信号进行采样的步骤; 在预定的时间窗口上将采样的语音信号分割成具有每帧预定数量的采样的多个帧; 产生每个采样信号帧的N点频谱采样表示; 确定每个N点频谱样本的大小，并且产生与特定频率处的每个N点频谱样本相关联的能量的直方图; 检测对应于与特定频率相关联的噪声阈值Nf的直方图的峰值幅度; 通过确定具有超过噪声阈值Nf的幅度的所有频谱样本的几何平均来确定与特定频率相关联的信道频率响应Cf; 从N点频谱样本的每个幅度中减去噪声阈值Nf以提供噪声抑制采样序列; 对噪声抑制样本应用盲解卷积; 将解卷积噪声抑制采样序列变换为时间表示; 将时间采样序列在时间上移动预定量; 以及在与预定时间窗口相对应的时间段内添加时移采样，以提供抑制噪声语音信号。

公开(公告)号：US06826528B1

公开(公告)日：2004-11-30

申请号：US09691878

申请日：2000-10-18

申请人： Duanpei Wu ,  Miyuki Tanaka ,  Xavier Menendez-Pidal

发明人： Duanpei Wu ,  Miyuki Tanaka ,  Xavier Menendez-Pidal

IPC分类号： G10L2102

CPC分类号： G10L21/0208 ,  G10L21/0232 ,  G10L25/18 ,  G10L25/78

摘要： A method for implementing a noise suppressor in a speech recognition system comprises a filter bank for separating source speech data into discrete frequency sub-bands to generate filtered channel energy, and a noise suppressor for weighting the frequency sub-bands to improve the signal-to-noise ratio of the resultant noise-suppressed channel energy. The noise suppressor preferably includes a noise calculator for calculating background noise values, a speech energy calculator for calculating speech energy values for each channel of the filter bank, and a weighting module for applying calculated weighting values to the projected channel energy to generate the noise-suppressed channel energy.

摘要翻译： 一种用于在语音识别系统中实现噪声抑制器的方法包括：滤波器组，用于将源语音数据分离成离散频率子带以产生经滤波的信道能量;以及噪声抑制器，用于对频率子带进行加权以改善信号到 噪声抑制通道能量的噪声比。 噪声抑制器优选地包括用于计算背景噪声值的噪声计算器，用于计算滤波器组的每个通道的语音能量值的语音能量计算器，以及用于将计算的加权值应用于投影的通道能量以产生噪声抑制器的加权模块， 抑制通道能量。

公开(公告)号：USRE38269E1

公开(公告)日：2003-10-07

申请号：US09422820

申请日：1999-10-21

申请人： Yu-Jih Liu

发明人： Yu-Jih Liu

IPC分类号： G10L2102

CPC分类号： G10L19/04 ,  G10L21/0264 ,  G10L25/09 ,  G10L25/93

摘要： A speech coding system employs measurements of robust features of speech frames whose distribution are not strongly affected by noise/levels to make voicing decisions for input speech occurring in a noisy environment. Linear programing analysis of the robust features and respective weights are used to determine an optimum linear combination of these features. The input speech vectors are matched to a vocabulary of codewords in order to select the corresponding, optimally matching codeword. Adaptive vector quantization is used in which a vocabulary of words obtained in a quiet environment is updated based upon a noise estimate of a noisy environment in which the input speech occurs, and the “noisy” vocabulary is then searched for the best match with an input speech vector. The corresponding clean codeword index is then selected for transmission and for synthesis at the receiver end. The results are better spectral reproduction and significant intelligibility enhancement over prior coding approaches. Robust features found to allow robust voicing decisions include: low-band energy; zero-crossing counts adapted for noise level; AMDF ratio (speech periodicity) measure; low-pass filtered backward correlation; low-pass filtered forward correlation; inverse-filtered backward correlation; and inverse-filtered pitch prediction gain measure.

公开(公告)号：US06606595B1

公开(公告)日：2003-08-12

申请号：US09652398

申请日：2000-08-31

申请人： Rathinavelu Chengalvarayan ,  Richard Harry Ketchum ,  Anand Rangaswamy Setlur ,  David Lynn Thomson

发明人： Rathinavelu Chengalvarayan ,  Richard Harry Ketchum ,  Anand Rangaswamy Setlur ,  David Lynn Thomson

IPC分类号： G10L2102

CPC分类号： G10L15/20 ,  G10L15/142 ,  G10L2021/02082

摘要： An automatic speech recognition system for the condition that an incoming caller's speech is quiet and a resulting echo (of a loud playing prompt) can cause the residual (the portion of the echo remaining after even echo cancellation) to be of the magnitude of the incoming speech input. Such loud echoes can falsely trigger the speech recognition system and interfere with the recognition of valid input speech. An echo model has been proven to alleviate this fairly common problem and to be effective in eliminating such false triggering. Further, this automatic speech recognition system enhanced the recognition of valid speech was provided within an existing hidden Markov modeling framework.

摘要翻译： 一种自动语音识别系统，用于条件是来话呼叫者的语音安静，并且由此产生的响应（响亮的播放提示）可能导致剩余（甚至回波消除之后留下的回波的部分）为输入的大小 语音输入 这种大声回波可能会错误地触发语音识别系统并干扰有效输入语音的识别。 已经证明回波模型可以缓解这个相当普遍的问题，并有效消除这种错误的触发。 此外，这种自动语音识别系统增强了在现有的隐马尔可夫建模框架内提供有效语音的识别。