公开(公告)号：US5347612A

公开(公告)日：1994-09-13

申请号：US552842

申请日：1990-07-16

申请人： Junichiroh Fujimoto ,  Seigo Yasuda ,  Tomofumi Nakatani

发明人： Junichiroh Fujimoto ,  Seigo Yasuda ,  Tomofumi Nakatani

IPC分类号： G10L15/00 ,  G10L7/08

CPC分类号： G10L15/00

摘要： After sampling a voice signal by a microphone (31), a voice interval is detected by a voice interval detector (32). Then, the voice signal is processed by a frequency analyzer (33) having a predetermined number of channels at a predetermined time interval, whereby a corresponding portion of the voice signal is quantized at each channel. Then, quantized data obtained from these channels are binary converted (34) to thereby form a frame comprised of a series of binary data. Each data of this frame corresponds to one of the channels, and preferably it is set to be an integral multiple of a computer calculation unit (e.g., 4 bits, 8 bits, etc.). When forming a combination frame by superimposing two or more of such frames, the combination frame is divided into layers, whereby it is so structured that each bit is represented by a binary number in each layer. On the other hand, it may also be so structured that one frame is divided in a plurality of sub-frames and a preliminary comparison process is carried out using each sub-frame.

摘要翻译： 在通过麦克风（31）采样语音信号之后，语音间隔检测器（32）检测语音间隔。 然后，语音信号由具有预定数量的信道的频率分析器（33）以预定的时间间隔进行处理，由此在每个信道上对语音信号的相应部分进行量化。 然后，从这些通道获得的量化数据被二进制转换（34），从而形成由一系列二进制数据组成的帧。 该帧的每个数据对应于一个信道，优选地被设置为计算机计算单元的整数倍（例如，4位，8位等）。 当通过叠加两个或更多个这样的帧来形成组合帧时，组合帧被分成多个层，由此它被构造成使得每个比特由每层中的二进制数表示。 另一方面，也可以如此构造使得一帧被分割成多个子帧，并且使用每个子帧执行初步比较处理。

公开(公告)号：US5150413A

公开(公告)日：1992-09-22

申请号：US415481

申请日：1989-10-02

申请人： Tomofumi Nakatani ,  Shogo Nakamura

发明人： Tomofumi Nakatani ,  Shogo Nakamura

IPC分类号： G10L15/00 ,  H03H17/06

CPC分类号： H03H17/06 ,  G10L15/00

摘要： When subjected to frequency analysis and plotted in a frequency spectral distribution, a voice signal typically includes a monotonously and relatively slowly changing component and a relatively rapidly changing component. For the recognition of voice sound, the relatively rapidly changing component contains phonemic information and thus is more important. In order to extract such a relatively rapidly changing component containing phonemic information from a voice signal, the voice signal is first subjected to frequency analysis to obtain a frequency spectral distribution, which is then sampled from one end to the other and then in the reversed order in timed sequence repetitively to produce a periodic waveform. Then, the thus obtained periodic waveform is filtered to remove the relatively slowly changing component thereby extracting the relatively rapidly changing component.

摘要翻译： 当进行频率分析并绘制在频谱分布中时，语音信号通常包括单调且相对缓慢变化的分量和相对快速变化的分量。 为了识别声音，相对快速变化的部件包含音素信息，因此更重要。 为了从语音信号中提取含有音素信息的相对快速变化的组件，首先对语音信号进行频率分析以获得频谱分布，然后从一端到另一端然后以相反的顺序进行采样 以定时序列重复地产生周期波形。 然后，将如此获得的周期波形滤波以除去相对缓慢变化的分量，从而提取相对快速变化的分量。

公开(公告)号：US4833717A

公开(公告)日：1989-05-23

申请号：US932602

申请日：1986-11-20

申请人： Shogo Nakamura ,  Tomofumi Nakatani

发明人： Shogo Nakamura ,  Tomofumi Nakatani

IPC分类号： G10L11/00 ,  G10L15/02

CPC分类号： G10L15/02

摘要： A voice spectrum analyzing method and system subjects a voice signal to frequency analysis by passing the voice signal through a filter bank containing a plurality of band pass filters each having a different band pass filter range to produce a voice spectral pattern over a predetermined frequency range. The voice spectral pattern is sampled at a predetermined sampling time interval successively, and each of the sampled voice spectral patterns is stored for a predetermined time period. While the voice spectral pattern is retained, it is scanned once in a predetermined time sequence, thereby forming an approximate periodic signal from a series of the scanned voice spectral voice patterns. And the periodic signal thus formed is then digitized and filtered through a digital high pass filter, thereby obtaining a high frequency component from the periodic signal which indicates a feature parameter of the voice signal.

摘要翻译： 语音频谱分析方法和系统通过使语音信号通过包含多个带通滤波器范围的多个带通滤波器的滤波器组来对语音信号进行频率分析，以在预定频率范围内产生语音频谱图案。 语音频谱模式以预定的采样时间间隔连续采样，并且每个采样的声频谱图案被存储预定的时间段。 当声音谱图被保留时，以预定的时间顺序扫描一次，从而形成来自一系列扫描的声音频谱语音模式的近似周期信号。 然后由此形成的周期信号通过数字高通滤波器进行数字化和滤波，从而从表示语音信号的特征参数的周期信号中获得高频分量。

公开(公告)号：US4634966A

公开(公告)日：1987-01-06

申请号：US713431

申请日：1985-03-19

申请人： Tomofumi Nakatani ,  Shogo Nakamura

发明人： Tomofumi Nakatani ,  Shogo Nakamura

IPC分类号： G10L15/02 ,  G01H3/08 ,  G01R23/16 ,  G10L11/00

CPC分类号： G01R23/16 ,  G01H3/08

摘要： A frequency spectral distribution of sound signal has a plurality of discrete data at respective channels where sampling takes place. Such a spectral distribution, defining a parallel signal, is converted into a time series signal which is used to produce a peak-detected signal and a zero-cross signal. Then, based on the timing of the zero-cross signal, the peak-detected signal is compared with the original parallel signal to process the original parallel signal to be binary-valued. The present invention provides a simple hardware structure having the above-described function.

摘要翻译： 声音信号的频谱分布在进行采样的各个信道上具有多个离散数据。 定义并行信号的这种频谱分布被转换为用于产生峰值检测信号和零交叉信号的时间序列信号。 然后，基于零交叉信号的定时，将峰值检测信号与原始并行信号进行比较，以处理原始并行信号为二值。 本发明提供具有上述功能的简单的硬件结构。

公开(公告)号：US4928302A

公开(公告)日：1990-05-22

申请号：US265766

申请日：1988-11-01

申请人： Kunihiro Kaneuchi ,  Seigou Yasuda ,  Takashi Ariyoshi ,  Tomofumi Nakatani ,  Hiroshi Aizawa

发明人： Kunihiro Kaneuchi ,  Seigou Yasuda ,  Takashi Ariyoshi ,  Tomofumi Nakatani ,  Hiroshi Aizawa

IPC分类号： G10L15/22 ,  H04M1/27

CPC分类号： H04M1/27 ,  G10L15/22 ,  H04M1/271

摘要： A voice actuated dialing apparatus has a feature extraction part for extracting a feature of an input data, a storage for storing registered standard patterns and corresponding telephone numbers of destination subscribers, a pattern matching part for comparing a standard pattern of the feature extracted by the feature extracting part with the registered standard patterns so as to recognize a predetermined one of the registered standard patterns which matches the standard pattern of the extracted feature, a speech synthesis part for outputting a speech corresponding to the predetermined standard pattern read out from the storage for confirmation of a result of the recognition, and a dialing circuit for dialing to a predetermined one of the registered telephone numbers corresponding to the predetermined standard pattern in a voice-dialing mode.

摘要翻译： 语音激活拨号装置具有用于提取输入数据的特征的特征提取部分，用于存储登记的标准模式的存储和目的地用户的相应电话号码;模式匹配部分，用于比较由特征提取的特征的标准模式 提取具有登记的标准图案的部分，以便识别与所提取的特征的标准图案相匹配的登记的标准图案中的预定的一个;语音合成部分，用于输出与从存储器中读出的预定标准模式相对应的语音，用于确认 以及用于在语音拨号模式中拨打对应于预定标准模式的预定的一个登记电话号码的拨号电路。

公开(公告)号：US5091947A

公开(公告)日：1992-02-25

申请号：US566884

申请日：1990-08-13

申请人： Takashi Ariyoshi ,  Toshiki Kawamoto ,  Seigou Yasuda ,  Syoji Kuriki ,  Tomofumi Nakatani

发明人： Takashi Ariyoshi ,  Toshiki Kawamoto ,  Seigou Yasuda ,  Syoji Kuriki ,  Tomofumi Nakatani

IPC分类号： G10L15/10 ,  G10L15/32

CPC分类号： G10L15/32

摘要： A voice recognition apparatus includes a coefficient memory for storing at least one coefficient for correcting a degree of similarity which is obtained by either one of the speaker-independent recognition and the speaker-dependent recognition. The apparatus also includes a voice identification circuit for comparing the degrees of similarity of the candidates obtained by either one of the speaker-independent recognition and the speaker-dependent recognition with corrected degrees of similarity of the candidates related to the other recognition type which are obtained by performing a predetermined operation to the degree of similarity of each candidate which is supplied from the other recognition type. Then the voice identification decides one candidate having the highest degree of similarity to be an identification result.

摘要翻译： 语音识别装置包括：系数存储器，用于存储用于校正通过与说话者无关的识别和说话者相关的识别中的任一个获得的相似程度的至少一个系数。 该装置还包括语音识别电路，用于将通过与说话者无关的识别和说话者相关的识别中的任一个获得的候选的相似度与用于获得的与其他识别类型相关的候选的相似度相比较 通过对从其他识别类型提供的每个候选者的相似度进行预定的操作。 然后，语音识别将具有最高相似度的一个候选确定为识别结果。

公开(公告)号：US4945557A

公开(公告)日：1990-07-31

申请号：US333698

申请日：1989-04-05

申请人： Kunihiro Kaneuchi ,  Toshiki Kawamoto ,  Tomofumi Nakatani

发明人： Kunihiro Kaneuchi ,  Toshiki Kawamoto ,  Tomofumi Nakatani

IPC分类号： H04M1/27 ,  H04M1/2745

CPC分类号： H04M1/271 ,  H04M1/274566

摘要： An automatic dialing apparatus for use in a telepone or facsimile machine sends out a dial signal to an external network automatically. A detachable telephone number memory, which stores a telephone number together with an area code, is detachably mounted on a telephone unit which includes a memory storing an area code of the district in which the telephone unit is located. The area code of the telepone number data supplied from the telephone number memory is deleted if that area code agrees with the area code stored in the memory of the telephone unit. An automatic dialing apparatus is preferably constructed to carry out dialing automatically responsive to a voice. In the preferred embodiment of such a voice activated dialing apparatus, a telephone number is input through a keyboard and a corresponding identifier, typically the name of a subscriber, is voiced and its voice signal is stored in association with the telephone number.

摘要翻译： 用于电话或传真机的自动拨号装置自动发送拨号信号到外部网络。 将电话号码与区号一起存储的可拆卸电话号码存储器可拆卸地安装在电话单元上，该电话单元包括存储电话单元所在区域的区号的存储器。 如果该区域代码与存储在电话单元的存储器中的区域代码一致，则从电话号码存储器提供的电话号码数据的区号被删除。 优选地，自动拨号装置被构造为自动响应于语音进行拨号。 在这样的语音激活拨号装置的优选实施例中，通过键盘输入电话号码，并且通常将用户名称的相应标识符发声，并且其语音信号与电话号码相关联地存储。