公开(公告)号：US06937977B2

公开(公告)日：2005-08-30

申请号：US09412202

申请日：1999-10-05

申请人： Ira A. Gerson

发明人： Ira A. Gerson

IPC分类号： G10L15/00 ,  G10L11/02 ,  G10L15/28 ,  H04B7/26 ,  H04M1/00 ,  H04M3/00 ,  H04M3/42 ,  H04M3/493 ,  H04M3/50 ,  H04M3/527 ,  G10L19/00

CPC分类号： G10L25/78 ,  H04M3/002 ,  H04M3/493 ,  H04M2201/40 ,  H04M2201/60 ,  H04M2207/18

摘要： A start of an input speech signal is detected during presentation of an output audio signal and an input start time, relative to the output audio signal, is determined. The input start time is then provided for use in responding to the input speech signal. In another embodiment, the output audio signal has a corresponding identification. When the input speech signal is detected during presentation of the output audio signal, the identification of the output audio signal is provided for use in responding to the input speech signal. Information signals comprising data and/or control signals are provided in response to at least the contextual information provided, i.e., the input start time and/or the identification of the output audio signal. In this manner, the present invention accurately establishes a context of an input speech signal relative to an output audio signal regardless of the delay characteristics of the underlying communication system.

摘要翻译： 在输出音频信号的呈现期间检测输入语音信号的开始，并且确定相对于输出音频信号的输入开始时间。 然后提供输入开始时间以用于响应于输入语音信号。 在另一实施例中，输出音频信号具有相应的标识。 当在输出音频信号的呈现期间检测到输入语音信号时，提供输出音频信号的识别以用于响应输入的语音信号。 响应于至少提供的上下文信息，即输入开始时间和/或输出音频信号的识别，提供包括数据和/或控制信号的信息信号。 以这种方式，无论底层通信系统的延迟特性如何，本发明都可以准确地建立输出语音信号相对于输出音频信号的上下文。

公开(公告)号：US06868385B1

公开(公告)日：2005-03-15

申请号：US09412119

申请日：1999-10-05

申请人： Ira A. Gerson

发明人： Ira A. Gerson

IPC分类号： G10L15/00 ,  G10L15/28 ,  H04M1/00 ,  H04M3/42 ,  H04M3/493 ,  H04M3/527 ,  G10L21/00

CPC分类号： G10L15/30 ,  H04M3/4936 ,  H04M2201/40 ,  H04M2207/18

摘要： A wireless system comprises at least one subscriber unit in wireless communication with an infrastructure. Each subscriber unit implements a speech recognition client, and the infrastructure comprises a speech recognition server. A given subscriber unit takes as input an unencoded speech signal that is subsequently parameterized by the speech recognition client. The parameterized speech is then provided to the speech recognition server that, in turn, performs speech recognition analysis on the parameterized speech. Information signals, based in part upon any recognized utterances identified by the speech recognition analysis, are subsequently provided to the subscriber unit. The information signals may be used to control the subscriber unit itself; to control one or more devices coupled to the subscriber unit, or may be operated upon by the subscriber unit or devices coupled thereto.

摘要翻译： 无线系统包括与基础设施进行无线通信的至少一个用户单元。 每个用户单元实现语音识别客户端，并且基础设施包括语音识别服务器。 给定的用户单元将随后由语音识别客户端参数化的未编码的语音信号作为输入。 然后将参数化语音提供给语音识别服务器，语音识别服务器又对参数化语音进行语音识别分析。 部分地基于通过语音识别分析识别的任何认可话语的信息信号随后被提供给用户单元。 信息信号可以用于控制用户单元本身; 以控制耦合到用户单元的一个或多个设备，或者可以由与其耦合的用户单元或设备进行操作。

公开(公告)号：US5434947A

公开(公告)日：1995-07-18

申请号：US21364

申请日：1993-02-23

申请人： Ira A. Gerson ,  Mark A. Jasiuk ,  Matthew A. Hartman

发明人： Ira A. Gerson ,  Mark A. Jasiuk ,  Matthew A. Hartman

IPC分类号： G10L19/12 ,  H03H17/00 ,  H03H17/02 ,  H03M7/30 ,  H03M7/38 ,  H04B14/04 ,  G10L9/14

CPC分类号： G10L19/12

摘要： An Rth-order filter models the frequency response of multiple filters, to provide a filter which offers the control of multiple filters without the complexity of multiple filters. The Rth-order filter can be used as a spectral noise weighting filter or a combination of a short-term predictor filter and a spectral noise weighting filter, referred to as the spectrally noise weighted synthesis filter, depending on which embodiment is employed. In general, the method models the frequency response of L Pth-order filters by a single Rth-order filter, where the order R

摘要翻译： R阶滤波器对多个滤波器的频率响应进行建模，以提供一个滤波器，可提供多个滤波器的控制，而不需要多个滤波器的复杂性。 根据使用哪个实施例，R阶滤波器可以用作频谱噪声加权滤波器或短期预测器滤波器和被称为频谱噪声加权合成滤波器的频谱噪声加权滤波器的组合。 通常，该方法通过单个R阶滤波器对L P阶滤波器的频率响应建模，其中阶数R

公开(公告)号：US5241650A

公开(公告)日：1993-08-31

申请号：US870199

申请日：1992-04-13

申请人： Ira A. Gerson ,  Mark A. Jasiuk

发明人： Ira A. Gerson ,  Mark A. Jasiuk

IPC分类号： G10L19/14

CPC分类号： G10L19/26

摘要： An adaptive spectral postfilter in a synthesized speech platform has a denominator characteristic that corresponds to a preceding LPC filter stage, and a numerator characteristic that is developed as a function of the denominator characteristic through application of spectral smoothing techniques. This allows the numerator to track the denominator without the introduction of spectral distortion that would otherwise affect the processing in an adverse way.

摘要翻译： 合成语音平台中的自适应频谱后置滤波器具有对应于前面的LPC滤波器级的分母特征，以及通过应用频谱平滑技术作为分母特性的函数而发展的分子特征。 这允许分子跟踪分母而不引入光谱失真，否则会以不利的方式影响处理。

公开(公告)号：US4817157A

公开(公告)日：1989-03-28

申请号：US141446

申请日：1988-01-07

申请人： Ira A. Gerson

发明人： Ira A. Gerson

IPC分类号： G10L11/00 ,  G10L15/02 ,  G10L19/00 ,  G10L19/04 ,  G10L19/08 ,  G10L19/12 ,  G10L5/00

CPC分类号： G10L19/135 ,  G10L25/06

摘要： An improved excitation vector generation and search technique (FIG. 1) is described for a code-excited linear prediction (CELP) speech coder (100) using a codebook of excitation code vectors. A set of M basis vectors V.sub.m (n) are used along with the excitation signal codewords (i) to generate the codebook of excitation vectors u.sub.i (n) according to a "vector sum" technique (120) of converting the selector codewords into a plurality of interim data signals, multiplying the set of M basis vectors by the interim data signals, and summing the resultant vectors to produce the set of 2.sup.M codebook vectors. The entire codebook of 2.sup.M possible excitation vectors is efficiently searched by using the vector sum generation technique with the M basis vectors--without ever having to generate and evaluate each of the 2.sup.M code vectors themselves. Furthermore, only M basis vectors need to be stored in memory (114), as opposed to all 2.sup.M code vectors.

摘要翻译： 针对使用激励码矢量码本的代码激励线性预测（CELP）语音编码器（100）描述了改进的激励矢量生成和搜索技术（图1）。 使用一组M个基矢量V m（n）与激励信号码字（i）一起根据“矢量和”技术（120）生成激励矢量ui（n）的码本，以将选择器码字转换成 多个中间数据信号，将M个基矢量的集合乘以中间数据信号，并将所得到的矢量相加以产生一组2M码本矢量。 通过使用具有M个基本向量的矢量和生成技术来有效地搜索2M个可能的激励矢量的整个码本，而无需生成和评估每个2M码矢量本身。 此外，与所有2M代码矢量相反，只有M个基矢量需要存储在存储器（114）中。

公开(公告)号：US4797929A

公开(公告)日：1989-01-10

申请号：US816161

申请日：1986-01-03

申请人： Ira A. Gerson ,  Brett L. Lindsley ,  Philip J. Smanski

发明人： Ira A. Gerson ,  Brett L. Lindsley ,  Philip J. Smanski

IPC分类号： G10L11/00 ,  A61K35/14 ,  A61K38/00 ,  A61P31/12 ,  A61P35/00 ,  C07K1/20 ,  C07K14/395 ,  C07K14/52 ,  C07K14/54 ,  C12N15/09 ,  C12P21/02 ,  C12R1/865 ,  G10L15/06 ,  G10L15/10 ,  G10L15/18 ,  G10L5/00

CPC分类号： G10L15/063 ,  C07K2319/02

摘要： Described herein, is an arrangement and method for processing speech information in a speech recognition system (300). In such a system where the speech information is depicted as words, each word representing a sequence of frames (510) and where the recognition system has means (120) for comparing present input speech to a word template, the word template stored in template memory and derived from one or more previous input word, the present invention is best employed. The invention describes combining contiguous acoustically similar frames (512) derived from the previous input word or words into representative frames to form a corresponding reduced word template, storing the reduced word template in template memory in an efficient manner, and comparing frames of the present input speech to the representative frames of the reduced word template according to the number of frames combined in the representative frames of the reduced word template. In doing so, a measure of similarity between the present input speech and the word template is generated.

摘要翻译： 这里描述了一种在语音识别系统（300）中处理语音信息的装置和方法。 在这样的系统中，语音信息被描绘为单词，每个单词表示帧序列（510），并且其中识别系统具有用于将当前输入语音与单词模板进行比较的装置（120），存储在模板存储器中的单词模板 并且从一个或多个先前的输入字导出，本发明是最佳的。 本发明描述将从先前输入的单词或多个单词导出的连续的声学上相似的帧（512）组合成代表性的帧，以形成相应的缩减词模板，以有效的方式将缩减的单词模板存储在模板存储器中，并且比较当前输入 根据在缩小词模板的代表帧中组合的帧的数量，将缩减词模板的代表帧进行语音。 在这样做时，产生了当前输入语音和单词模板之间的相似性度量。

公开(公告)号：US4751737A

公开(公告)日：1988-06-14

申请号：US795562

申请日：1985-11-06

申请人： Ira A. Gerson ,  Brett L. Lindsley

发明人： Ira A. Gerson ,  Brett L. Lindsley

IPC分类号： G10L15/06 ,  G10L1/00

CPC分类号： G10L15/063

摘要： Disclosed is a method for generating word templates for a speech recognition system. It is used where speech is represented by data in frames of equal time intervals. The method includes generating an interim template, generating a time alignment path between the interim template and a token, mapping frames from the interim template and the token along the time alignment path onto an averaged time axis, and combining data associated with the mapped frames to produce composite frames representative of the final word template. The method realizes advantages of reduced memory usage and a realistic data average from each contributing averaged word.

摘要翻译： 公开了一种用于生成用于语音识别系统的单词模板的方法。 用于以等时间间隔的帧表示数据的语音。 该方法包括生成临时模板，在临时模板和令牌之间生成时间对准路径，将来自临时模板的帧和沿着时间对准路径的令牌映射到平均时间轴上，以及将与映射的帧相关联的数据组合到 产生代表最终单词模板的复合框架。 该方法实现了减少存储器使用的优点和来自每个贡献平均字的实际数据平均。

公开(公告)号：US4630305A

公开(公告)日：1986-12-16

申请号：US750941

申请日：1985-07-01

申请人： David E. Borth ,  Ira A. Gerson ,  Philip J. Smanski ,  Richard J. Vilmur

发明人： David E. Borth ,  Ira A. Gerson ,  Philip J. Smanski ,  Richard J. Vilmur

IPC分类号： G10L21/02 ,  H04R25/00 ,  H04R27/00 ,  H04B15/00

CPC分类号： G10L21/0208 ,  G10L2021/02168 ,  G10L25/27 ,  H04R2225/43 ,  H04R25/505

摘要： An automatic gain selector is disclosed for use with a noise suppression system which performs speech quality enhancement upon a noisy speech signal available at the input to generate a noise-suppressed speech signal at the output by spectral gain modification. The channel gain controller (240) of the present invention produces a modification signal (245), comprised of individual channel gain values, for application to a channel gain modifier (250). A particular gain table set is automatically selected from one of a plurality of gain tables (450) by a selector switch (470) and a noise level quantizer (440) in response to a multi-channel noise parameter, such as the overall average background noise level of the input signal. Then the individual channel gain values (455) are obtained from the particular gain table set in response to the individual channel signal-to-noise ratio estimate (235). Hence, each individual channel gain value is selected as a function of (a) the channel number, (b) the current channel SNR estimate, and (c) the overall average background noise level. The automatic gain selector further includes a gain smoothing filter (460) for smoothing these noise suppression gain factors on a per-sample basis thereby improving noise flutter performance caused by step discontinuities in frame-to-frame gain changes.

摘要翻译： 公开了一种与噪声抑制系统一起使用的自动增益选择器，该噪声抑制系统在输入端可用的噪声语音信号上执行语音质量增强，以通过频谱增益修改在输出端产生噪声抑制语音信号。 本发明的信道增益控制器（240）产生一个包括各个信道增益值的修改信号（245），用于应用于信道增益修改器（250）。 响应于诸如总体平均背景的多通道噪声参数，选择器开关（470）和噪声电平量化器（440）从多个增益表（450）中的一个自动选择特定增益表集合 输入信号的噪声电平。 然后，从响应于各个信道信噪比估计（235）设置的特定增益表获得各个信道增益值（455）。 因此，根据（a）信道号，（b）当前信道SNR估计和（c）整体平均背景噪声电平来选择每个单独信道增益值。 自动增益选择器还包括增益平滑滤波器（460），用于在每采样的基础上平滑这些噪声抑制增益因子，从而改善由帧间增益变化中的步长不连续性引起的噪声颤动性能。

公开(公告)号：US4544919A

公开(公告)日：1985-10-01

申请号：US687486

申请日：1984-12-28

申请人： Ira A. Gerson

发明人： Ira A. Gerson

IPC分类号： G10L19/06

CPC分类号： G10L19/06

摘要： An improved method and means of determining reflection coefficients that characterize an electrical signal that obtains characteristics of an all-zero inverse lattice filter. The reflection coefficients are obtained by filtering the signal, sample the filtered signal, obtaining the elements of a correlation array from the samples, initializing values of arrays forward residuals, backward residuals, and cross correlation of residuals, combining array elements to obtain a first reflection coefficient, removing from the forward, backward and cross-correlation arrays the effect of the first reflection coefficient, calculating from the revised arrays a second coefficient, and repeating the calculations to the desired order. In a second embodiment of the present invention, samples are selected from the digitized signal and multiplied by a windowing function. The windowed samples are used to derive values of an autocorrelation array which eliminates the need for both forward and backward arrays as in the first embodiment of the invention.

摘要翻译： 一种确定表征获得全零逆格值滤波器的特性的电信号的反射系数的改进方法和装置。 通过对信号进行滤波，对滤波后的信号进行采样，从采样获得相关阵列的元素，初始化数组前向残差值，后向残差和残差互相关，获得反射系数，组合数组元素以获得第一反射 系数，从前向，后向和互相关阵列中去除第一反射系数的影响，从经修改的阵列计算第二系数，并将计算重复到所需顺序。 在本发明的第二实施例中，从数字化信号中选择样本并乘以加窗函数。 窗口样本用于导出自相关阵列的值，其消除了如在本发明的第一实施例中对前向和后向阵列的需要。

公开(公告)号：US5528723A

公开(公告)日：1996-06-18

申请号：US303271

申请日：1994-09-07

申请人： Ira A. Gerson ,  Mark A. Jasiuk

发明人： Ira A. Gerson ,  Mark A. Jasiuk

IPC分类号： G10L19/00 ,  G10L19/14 ,  G10L3/02

CPC分类号： G10L19/12 ,  G10L25/90

摘要： A digital speech coder utilizes harmonic noise weighting to overcome some limitations of low-rate CELP-type speech coders in reproducing voiced speech. In addition to a short term correction factor, which constitutes spectral noise weighting as known in the art, a long term pitch correction factor is utilized to provide harmonic noise weighting. The inclusion of harmonic noise weighting in a speech coder more efficiently utilizes noise-masking properties of a speech signal, allowing synthesis of a higher quality speech at a given bit rate.

摘要翻译： 数字语音编码器利用谐波噪声加权来克服在再现有声语音时低速率CELP型语音编码器的一些限制。 除了构成本领域已知的频谱噪声加权的短期校正因子之外，还使用长期的音调校正因子来提供谐波噪声加权。 在语音编码器中更高效地包含谐波噪声加权，利用语音信号的噪声掩蔽特性，允许以给定比特率合成较高质量的语音。