专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US6058365A Speech processing using an expanded left to right parser 失效
标题翻译：使用扩展的从左到右解析器的语音处理
公开(公告)号：US6058365A
公开(公告)日：2000-05-02
申请号：US86569
申请日：1993-07-06
申请人： Akito Nagai , Kenji Kita , Shigeki Sagayama
发明人： Akito Nagai , Kenji Kita , Shigeki Sagayama
IPC分类号： G10L15/14 , G10L15/18 , G10L5/06
CPC分类号： G10L15/187 , G10L15/142
摘要： Continuous speech is recognized by selecting among hypotheses, consisting of candidates of symbol strings obtained by connecting phonemes corresponding to a Hidden Markov Model (HMM) having the highest probability, by referring to a phoneme context dependent type HMM from input speech using a HMM phoneme verification portion. A phoneme context dependent type LR (Left-Right) parser portion predicts a subsequent phoneme by referring to an action specifying item stored in an LR (Left to Right) parsing table to predict a phoneme context around the predicted phoneme using an action specifying item of the LR table.
摘要翻译：通过选择由通过使用HMM音素验证参考来自输入语音的音素上下文相关类型HMM来连接具有最高概率的隐马尔可夫模型（HMM）的音素而获得的符号串的候选的假设来识别连续语音。一部分。音素上下文相关型LR（左右）解析器部分通过参考存储在LR（从左到右）解析表中的动作指定项来预测随后的音素，以使用动作指定项目来预测围绕预测音素的音素上下文 LR表。

2. 发明授权

US07929600B2 Multi-channel signal encoding method, decoding method, device thereof, program, and recording medium thereof 有权
标题翻译：多信道信号编码方法，解码方法，装置，程序及其记录介质
公开(公告)号：US07929600B2
公开(公告)日：2011-04-19
申请号：US11597905
申请日：2005-06-30
申请人： Takehiro Moriya , Yutaka Kamamoto , Shigeki Sagayama
发明人： Takehiro Moriya , Yutaka Kamamoto , Shigeki Sagayama
IPC分类号： H04B1/66
CPC分类号： G10L19/008
摘要： In difference coding, each of a first to M-th channel signals is divided into frames and independent energy of every channel signal and difference energy of difference signals between all channel signals are calculated for each frame. In ascending order of energy, if a signal corresponding to an energy value is independent signal, it is determined that independent coding should be used for the signal. If the signal is a difference signal and the type of coding for one of channel signals has been determined, it is determined that the other should be difference-coded using the former channel signal as a reference signal. If the type of coding for neither of the channel signals has been determined, it is determined that one of them should be independently coded and the other should be difference-coded using the former channel signal as a reference signal.
摘要翻译：在差分编码中，第一至第M信道信号中的每一个被分成帧和每个信道信号的独立能量，并且针对每个帧计算所有信道信号之间的差分信号的差分能量。按照能量的升序，如果对应于能量值的信号是独立的信号，则确定信号应该使用独立的编码。如果信号是差信号，并且已经确定了一个信道信号的编码类型，则确定另一个应当使用前一个信道信号作为参考信号进行差分编码。如果已经确定了对于两个信道信号的编码类型，则确定它们中的一个应该被独立地编码，而另一个应该使用前一个信道信号作为参考信号进行差分编码。

3. 发明申请

US20090190693A1 Multichannel signal encoding method, its decoding method, devices for these, program, and its recording medium 有权
标题翻译：多通道信号编码方法，其解码方法，这些设备，程序及其记录介质
公开(公告)号：US20090190693A1
公开(公告)日：2009-07-30
申请号：US11631019
申请日：2005-08-17
申请人： Takehiro Moriya , Noboru Harada , Yutaka Kamamoto , Takuya Nishimoto , Shigeki Sagayama
发明人： Takehiro Moriya , Noboru Harada , Yutaka Kamamoto , Takuya Nishimoto , Shigeki Sagayama
IPC分类号： H04L27/00
CPC分类号： G10L19/008
摘要： An object of the present invention is to efficiently perform weighted difference coding of two or more signals. Determination is made as to which of independent coding and weighted difference coding is to be used for each channel so that the total energy of the channel signals and weighted difference signals is minimized. A weighted difference signal is generated on the basis of the determination and a reference signal (parent) and a weight is generated as auxiliary codes, the difference signal is treated as an input channel signal, and the process of coding determination and difference signal and auxiliary code generation is repeated. The difference signal generated at the last iteration of the process and a signal to be coded by independent coding are compressive coded and the auxiliary codes generated at the iterations of the process are coded and outputted.
摘要翻译：本发明的目的是有效地执行两个或更多个信号的加权差分编码。确定哪个独立编码和加权差分编码将用于每个通道，使得信道信号和加权差分信号的总能量最小化。基于确定和参考信号（母）生成加权差分信号，生成权重作为辅助码，将差分信号作为输入信道信号，编码判定和差分信号和辅助处理重复代码生成。在过程的最后一次迭代中产生的差分信号和通过独立编码进行编码的信号被压缩编码，并且对该处理的迭代生成的辅助代码进行编码和输出。

4. 发明授权

US07970605B2 Method, apparatus, program and recording medium for long-term prediction coding and long-term prediction decoding 有权
标题翻译：用于长期预测编码和长期预测解码的方法，装置，程序和记录介质
公开(公告)号：US07970605B2
公开(公告)日：2011-06-28
申请号：US11793821
申请日：2006-01-11
申请人： Takehiro Moriya , Noboru Harada , Yutaka Kamamoto , Takuya Nishimoto , Shigeki Sagayama
发明人： Takehiro Moriya , Noboru Harada , Yutaka Kamamoto , Takuya Nishimoto , Shigeki Sagayama
IPC分类号： G10L19/12
CPC分类号： G10L19/0017 , G10L19/08 , G10L19/09
摘要： A method and apparatus multiplies a past sample a time lag τ older than a current sample by a quantized multiplier ρ′ on a frame by frame basis, subtracts the multiplication result from the current sample, codes the subtraction result, and codes the time lag using a fixed-length coder if the multiplier ρ′ is smaller than 0.2 or if information about the previous frame is unavailable, or codes the time lag using a variable-length coder if ρ′ is not smaller than 0.2. A multiplier ρ is coded by a multiplier coder and the multiplier ρ′ obtained by decoding the multiplier ρ is outputted. The process is performed for each frame.
摘要翻译：一种方法和装置将一个比当前样本更早的时间滞后τ乘以一个逐帧的量化乘法器，从当前样本中减去相乘结果，对相减结果进行编码，并对时间延迟进行编码如果乘数＆rgr''小于0.2，或者如果关于前一帧的信息不可用，则使用固定长度编码器，如果＆rgr;'不小于0.2，则使用可变长度编码器对时间延迟进行编码。乘法器由乘法器编码器和乘法器＆rgr;'通过对乘法器＆rgr进行解码获得; 被输出。对每个帧执行该过程。

5. 发明申请

US20110058685A1 METHOD OF SEPARATING SOUND SIGNAL 审中-公开
标题翻译：分离声信号的方法
公开(公告)号：US20110058685A1
公开(公告)日：2011-03-10
申请号：US12920299
申请日：2008-08-27
申请人： Shigeki Sagayama , Nobutaka Ono , Hirokazu Kameoka , Kenichi Miyamoto , Jonathan Le Roux
发明人： Shigeki Sagayama , Nobutaka Ono , Hirokazu Kameoka , Kenichi Miyamoto , Jonathan Le Roux
IPC分类号： H03G5/00
CPC分类号： G10L21/0272
摘要： The present invention obtains a separated signal from an audio signal based on the anisotropy of smoothness of spectral elements in the time-frequency domain. A spectrogram of the audio signal is assumed to be a sum of a plurality of sub-spectrograms, and smoothness of spectral elements of each sub-spectrogram in the time-frequency domain has directionality on the time-frequency plane. The method comprises obtaining a distribution coefficient for distributing spectral elements of said audio signal in the time-frequency domain to at least one sub-spectrogram based on the directionality of the smoothness of each sub-spectrogram on the time-frequency plane, and separating at least one sub-spectrogram from said spectral elements of said audio signal using said distribution coefficient.
摘要翻译：本发明基于时频域中的频谱元素的平滑度的各向异性从音频信号中获得分离的信号。假设音频信号的频谱是多个子频谱图的和，并且时频域中的每个子频谱图的频谱元素的平滑度在时间 - 频率平面上具有方向性。该方法包括：基于时频平面上的每个子频谱图的平滑度的方向性，获得用于将时频域中的所述音频信号的频谱元素分配到至少一个子频谱图的分布系数，并且在使用所述分布系数，从所述音频信号的所述频谱元素的至少一个子频谱图。

6. 发明授权

US5732392A Method for speech detection in a high-noise environment 失效
标题翻译：在高噪声环境中进行语音检测的方法
公开(公告)号：US5732392A
公开(公告)日：1998-03-24
申请号：US719015
申请日：1996-09-24
申请人： Osamu Mizuno , Satoshi Takahashi , Shigeki Sagayama
发明人： Osamu Mizuno , Satoshi Takahashi , Shigeki Sagayama
IPC分类号： G10L11/02 , G10L15/04 , G01L3/00
CPC分类号： G10L25/78 , G10L25/06 , G10L25/18 , G10L25/24
摘要： In method for detecting a speech period in a high-noise environment, the variation in the spectrum of an input signal per unit time is calculated over an analysis frame period, and when the frequency of spectrum variation falls in a predetermined range, the input signal of that frame is decided to be a speech signal.
摘要翻译：在高噪声环境下用于检测语音周期的方法中，在分析帧周期内计算每单位时间的输入信号的频谱变化，并且当频谱变化的频率落在预定范围内时，输入信号该帧被决定为语音信号。

7. 发明授权

US5307442A Method and apparatus for speaker individuality conversion 失效
标题翻译：扬声器个性转换的方法和装置
公开(公告)号：US5307442A
公开(公告)日：1994-04-26
申请号：US761155
申请日：1991-09-17
申请人： Masanobu Abe , Shigeki Sagayama
发明人： Masanobu Abe , Shigeki Sagayama
IPC分类号： G10L13/00 , G10L13/02 , G10L21/00 , G10L9/06
CPC分类号： G10L13/033 , G10L2021/0135
摘要： Input speech of a reference speaker, who wants to convert his/her voice quality, and speech of a target speaker are converted into a digital signal by an analog to digital (A/D) converter. The digital signal is then subjected to speech analysis by a linear predictive coding (LPC) analyzer. Speech data of the reference speaker is processed into speech segments by a speech segmentation unit. A speech segment correspondence unit makes a dynamic programming (DP) based correspondence between the obtained speech segments and training speech data of the target speaker, thereby making a speech segment correspondence table. A speaker individuality conversion is made on the basis of the speech segment correspondence table by a speech individuality conversion and synthesis unit.
摘要翻译：通过模拟（A / D）转换器将参考扬声器的输入语音转换成数字信号，该语音人员希望将他/她的语音质量和目标扬声器的语音转换成数字信号。然后通过线性预测编码（LPC）分析仪对数字信号进行语音分析。通过语音分割单元将参考说话者的语音数据处理成语音段。语音片段对应单元在获得的语音片段与目标说话者的训练语音数据之间进行基于动态规划（DP）的对应，从而形成语音段对应表。通过语音个性转换和合成单元，基于语音段对应表进行扬声器个性转换。

8. 发明申请

US20110166854A1 METHOD, APPARATUS, PROGRAM AND RECORDING MEDIUM FOR LONG-TERM PREDICTION CODING AND LONG-TERM PREDICTION DECODING 有权
标题翻译：用于长期预测编码和长期预测解码的方法，装置，程序和记录介质
公开(公告)号：US20110166854A1
公开(公告)日：2011-07-07
申请号：US13049442
申请日：2011-03-16
申请人： Takehiro Moriya , Noboru Harada , Yutaka Kamamoto , Takuya Nishimoto , Shigeki Sagayama
发明人： Takehiro Moriya , Noboru Harada , Yutaka Kamamoto , Takuya Nishimoto , Shigeki Sagayama
IPC分类号： G10L19/04
CPC分类号： G10L19/0017 , G10L19/08 , G10L19/09
摘要： A method and apparatus multiplies a past sample a time lag τ older than a current sample by a quantized multiplier ρ′ on a frame by frame basis, subtracts the multiplication result from the current sample, codes the subtraction result, and codes the time lag using a fixed-length coder if the multiplier ρ′ is smaller than 0.2 or if information about the previous frame is unavailable, or codes the time lag using a variable-length coder if ρ′ is not smaller than 0.2. A multiplier ρ is coded by a multiplier coder and the multiplier ρ′ obtained by decoding the multiplier ρ is outputted. The process is performed for each frame.
摘要翻译：一种方法和装置将一个比当前样本更早的时间滞后τ乘以一个逐帧的量化乘法器，从当前样本中减去相乘结果，对相减结果进行编码，并对其进行编码如果乘数＆rgr''小于0.2，或者如果关于前一帧的信息不可用，则使用固定长度编码器，如果＆rgr;'不小于0.2，则使用可变长度编码器对时间延迟进行编码。乘法器由乘法器编码器和乘法器＆rgr;'通过对乘法器＆rgr进行解码获得; 被输出。对每个帧执行该过程。

9. 发明授权

US5677988A Method of generating a subword model for speech recognition 失效
标题翻译：生成用于语音识别的子词模型的方法
公开(公告)号：US5677988A
公开(公告)日：1997-10-14
申请号：US532318
申请日：1995-09-21
申请人： Jun-ichi Takami , Shigeki Sagayama
发明人： Jun-ichi Takami , Shigeki Sagayama
IPC分类号： G10L15/06 , G10L15/02 , G10L15/14 , G10L5/06
CPC分类号： G10L15/142 , G10L15/146
摘要： An automated method of generating a subword model for speech recognition dependent on phoneme context for processing speech information using a Hidden Markov Model in which static features of speech and dynamic features of speech are modeled as a chain of a plurality of output probability density distributions. The method comprising determining a phoneme context class which is a model unit allocated to each model, the number of states used for representing each model, relationship of sharing of states among a plurality of models, and output probability density distribution of each model, by repeating splitting of a small number of states, provided in an initial Hidden Markov Model, based on a prescribed criterion on a probabilistic model.
摘要翻译：一种用于根据音素上下文生成语音识别的子词模型的自动化方法，用于使用隐性马尔可夫模型处理语音信息，其中语音的静态特征和语音的动态特征被建模为多个输出概率密度分布的链。该方法包括：确定作为分配给每个模型的模型单元的音素上下文类，用于表示每个模型的状态数，多个模型之间的状态共享关系，以及每个模型的输出概率密度分布基于概率模型的规定标准，在初始隐马尔可夫模型中提供少量状态的分割。

10. 发明授权

US5555345A Learning method of neural network 失效
标题翻译：神经网络的学习方法
公开(公告)号：US5555345A
公开(公告)日：1996-09-10
申请号：US845096
申请日：1992-03-03
申请人： Yasuhiro Komori , Shigeki Sagayama
发明人： Yasuhiro Komori , Shigeki Sagayama
IPC分类号： G06F15/18 , G06G7/60 , G06N3/08 , G06N99/00 , G06E1/00 , G06F3/00 , G06G7/00
CPC分类号： G06K9/6276 , G06N3/08
摘要： The present invention is a learning method of a neural network for identifying N category using a data set consisted of N categories, in which one learning sample is extracted from a learning sample set in step SP1, and the distances between the sample and all the learning samples are obtained in step SP2. The closest n samples are obtained for each category in step SP3, and similarity for each category is obtained using the distances from the samples and a similarity conversion function f(d)=exp (-.alpha..multidot.d.sup.2). In step SP4, the similarity for each category is used as a target signal for the extracted learning sample, and it returns to an initial state until target signals for all the learning samples are determined. When target signals are determined for all the learning samples, in step SP5, the neural network is subjected to learning by the back-propagation using the learning samples and the obtained target signals.
摘要翻译：本发明是使用由N个类别组成的数据集来识别N类别的神经网络的学习方法，其中从在步骤SP1中设置的学习样本中提取一个学习样本以及样本与所有学习之间的距离在步骤SP2中获得样品。在步骤SP3中为每个类别获得最接近的n个样本，并且使用距离样本和相似度转换函数f（d）= exp（-a xd2）获得每个类别的相似度。在步骤SP4中，将各类别的相似度用作所提取的学习样本的目标信号，并返回到初始状态，直到确定了所有学习样本的目标信号为止。当针对所有学习样本确定目标信号时，在步骤SP5中，通过使用学习样本和获得的目标信号的反向传播对神经网络进行学习。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式