公开(公告)号：US07848927B2

公开(公告)日：2010-12-07

申请号：US11791110

申请日：2005-11-01

申请人： Yoshio Ohno ,  Makoto Nishizaki ,  Shinichi Yoshizawa ,  Tetsu Suzuki

发明人： Yoshio Ohno ,  Makoto Nishizaki ,  Shinichi Yoshizawa ,  Tetsu Suzuki

IPC分类号： G10L15/14

CPC分类号： G10L15/30 ,  G10L15/18 ,  G10L2015/228

摘要： A speech recognition device is provided which includes: a language model storage unit which stores a language model indicating appearance probabilities of words or word sequences; an acoustic feature amount extracting unit and a checking unit which extract a feature amount of an inputted speech signal, and identifies the word or word sequence corresponding to the speech signal by checking the extracted feature amount with the language model stored in the language model storage unit; an obtained word signal receiving/analyzing unit which obtains and analyzes the word; and a language model adjusting unit which identifies the appearance probability of the word based on the time elapsed after obtaining the word by the obtained word signal receiving/analyzing unit and which adjusts the language model by reflecting the identified appearance probability on the language model stored in the language model storage unit.

摘要翻译： 提供语音识别装置，其包括：语言模型存储单元，其存储指示单词或单词序列的出现概率的语言模型; 声学特征量提取单元和检测单元，其提取输入的语音信号的特征量，并且通过使用存储在语言模型存储单元中的语言模型检查提取的特征量来识别与语音信号相对应的单词或单词序列 ; 获得并分析该单词的获取的单词信号接收/分析单元; 以及语言模型调整单元，其基于获得的单词信号接收/分析单元获得单词之后经过的时间来识别单词的出现概率，并且通过在所存储的语言模型中反映所识别的出现概率来调整语言模型 语言模型存储单元。

公开(公告)号：US20080046244A1

公开(公告)日：2008-02-21

申请号：US11791110

申请日：2005-11-01

申请人： Yoshio Ohno ,  Makoto Nishizaki ,  Shinichi Yoshizawa ,  Tetsu Suzuki

发明人： Yoshio Ohno ,  Makoto Nishizaki ,  Shinichi Yoshizawa ,  Tetsu Suzuki

IPC分类号： G10L15/14

CPC分类号： G10L15/30 ,  G10L15/18 ,  G10L2015/228

摘要： Provided is a speech recognition device which appropriately applies limitations on target words to be recognized which are obtained from outside of the speech recognition device, as well as to eliminate the uncomfortable feeling caused by the limitation processing. The speech recognition device includes: a language model storage unit (104) which stores a language model indicating appearance probabilities of words or word sequences; an acoustic feature amount extracting unit (101) and a checking unit (102) which extract a feature amount of an inputted speech signal, and identifies the word or word sequence corresponding to the speech signal by checking the extracted feature amount with the language model stored in the language model storage unit (104); an obtained word signal receiving/analyzing unit (105) which obtains and analyzes the word; and a language model adjusting unit (110) which identifies the appearance probability of the word based on the time elapsed after obtaining the word by the obtained word signal receiving/analyzing unit (105) and which adjusts the language model by reflecting the identified appearance probability on the language model stored in the language model storage unit (104).

摘要翻译： 提供一种语音识别装置，其适当地对从语音识别装置的外部获得的要识别的目标字进行限制，并且消除由限制处理引起的不适感。 语音识别装置包括：语言模型存储单元，其存储表示单词或单词序列的出现概率的语言模型; 提取输入的语音信号的特征量的声音特征量提取单元（101）和检查单元（102），并且通过利用存储的语言模型检查所提取的特征量来识别对应于语音信号的单词或单词序列 在所述语言模型存储单元（104）中; 获取并分析该单词的获取字信号接收/分析单元（105）; 以及语言模型调整单元，其基于获得的单词信号接收/分析单元（105）获得单词之后的经过时间来识别单词的出现概率，并且通过反映所识别的出现概率来调整语言模型 在存储在语言模型存储单元（104）中的语言模型上。

公开(公告)号：US20080001780A1

公开(公告)日：2008-01-03

申请号：US11632716

申请日：2005-06-13

申请人： Yoshio Ohno ,  Shinichi Yoshizawa ,  Tetsu Suzuki

发明人： Yoshio Ohno ,  Shinichi Yoshizawa ,  Tetsu Suzuki

IPC分类号： G08G1/00

CPC分类号： H04R3/00 ,  G08G1/0962 ,  G08G1/0965 ,  G10L17/26 ,  H04R5/033 ,  H04R25/00 ,  H04R2225/41 ,  H04R2499/13

摘要： An audio identifying device which can transmit with certainty audio information which is important for a user, according to an importance level of input audio information which varies depending on the action of the user includes: a checking unit 104 which judges a type of inputted audio; a user action obtainment unit 108 which detects an action of the user; an output mode determination unit 106 which determines an output mode of an audio identification result regarding the input audio by checking, with output mode definition information stored in the output mode definition information storage unit 107, the result judged by the checking unit 104 and the result detected by the user action obtainment unit 108; and the audio identification result output processing unit 110 which outputs the audio identification result on which processing according to the output mode determined by the audio identification result has been performed by checking the judgment result determined by the output mode determination unit 106 with the output processing method definition information stored in an output processing method definition information storage unit 111.

摘要翻译： 根据用户的动作而变化的输入音频信息的重要性水平，可以确定地发送对用户重要的音频信息的音频识别装置包括：判断输入音频的类型的检查单元104; 用户动作获取单元108，其检测用户的动作; 输出模式确定单元106，通过检查输出模式定义信息存储单元107中存储的输出模式定义信息，通过检查单元104判断的结果和结果来确定关于输入音频的音频识别结果的输出模式 由用户动作获取单元108检测; 并且音频识别结果输出处理单元110输出根据由音频识别结果确定的输出模式的哪个处理的音频识别结果已经通过用输出处理方法检查由输出模式确定单元106确定的判断结果来执行 存储在输出处理方法定义信息存储单元111中的定义信息。

公开(公告)号：US07616128B2

公开(公告)日：2009-11-10

申请号：US11632716

申请日：2005-06-13

申请人： Yoshio Ohno ,  Shinichi Yoshizawa ,  Tetsu Suzuki

发明人： Yoshio Ohno ,  Shinichi Yoshizawa ,  Tetsu Suzuki

IPC分类号： G08G1/00

CPC分类号： H04R3/00 ,  G08G1/0962 ,  G08G1/0965 ,  G10L17/26 ,  H04R5/033 ,  H04R25/00 ,  H04R2225/41 ,  H04R2499/13

摘要： An audio identifying device which can transmit with certainty audio information which is important for a user, according to an importance level of input audio information which varies depending on the action of the user includes: a checking unit 104 which judges a type of inputted audio; a user action obtainment unit 108 which detects an action of the user; an output mode determination unit 106 which determines an output mode of an audio identification result regarding the input audio by checking, with output mode definition information stored in the output mode definition information storage unit 107, the result judged by the checking unit 104 and the result detected by the user action obtainment unit 108; and the audio identification result output processing unit 110 which outputs the audio identification result on which processing according to the output mode determined by the audio identification result has been performed by checking the judgment result determined by the output mode determination unit 106 with the output processing method definition information stored in an output processing method definition information storage unit 111.

摘要翻译： 根据用户的动作而变化的输入音频信息的重要性水平，可以确定地发送对用户重要的音频信息的音频识别装置包括：判断输入音频的类型的检查单元104; 用户动作获取单元108，其检测用户的动作; 输出模式确定单元106，通过检查输出模式定义信息存储单元107中存储的输出模式定义信息，通过检查单元104判断的结果和结果来确定关于输入音频的音频识别结果的输出模式 由用户动作获取单元108检测; 并且音频识别结果输出处理单元110输出根据由音频识别结果确定的输出模式的哪个处理的音频识别结果已经通过用输出处理方法检查由输出模式确定单元106确定的判断结果来执行 存储在输出处理方法定义信息存储单元111中的定义信息。

公开(公告)号：US20060193671A1

公开(公告)日：2006-08-31

申请号：US11401263

申请日：2006-04-11

申请人： Shinichi Yoshizawa ,  Tetsu Suzuki ,  Yoshihisa Nakatoh

发明人： Shinichi Yoshizawa ,  Tetsu Suzuki ,  Yoshihisa Nakatoh

IPC分类号： B41J35/28

CPC分类号： G10L19/005 ,  G10L21/0208

摘要： An audio restoration apparatus which restores an audio to be restored having a missing audio part and being included in a mixed audio. The audio restoration apparatus includes: a mixed audio separation unit which extracts the audio to be restored included in the mixed audio; an audio structure analysis unit which generates at least one of a phoneme sequence, a character sequence and a musical note sequence of the missing audio part in the extracted audio to be restored, based on an audio structure knowledge database in which semantics of audio are registered; an unchanged audio characteristic domain analysis unit which segments the extracted audio to be restored into time domains in each of which an audio characteristic remains unchanged; an audio characteristic extraction unit which identifies a time domain where the missing audio part is located, from among the segmented time domains, and extract audio characteristics of the identified time domain in the audio to be restored; and an audio restoration unit which restores the missing audio part in the audio to be restored, using the extracted audio characteristics and the generated one or more of phoneme sequence, character sequence and musical note sequence.

摘要翻译： 一种音频恢复装置，其恢复具有丢失的音频部分并被包括在混合音频中的要恢复的音频。 音频恢复装置包括：混合音频分离单元，其提取包含在混合音频中的要恢复的音频; 音频结构分析单元，其基于音频结构知识数据库中生成音频结构知识数据库中的音素序列，字符序列和所提取的要恢复的音频中的音符序列中的至少一个。 ; 一个不变的音频特征域分析单元，其将提取的音频分段成恢复到每个音频特性保持不变的时域; 音频特征提取单元，从分段时域中识别缺失音频部分所在的时域，并且提取要恢复的音频中所识别的时域的音频特征; 以及音频恢复单元，其使用所提取的音频特性和所生成的一个或多个音素序列，字符序列和音符序列来恢复要恢复的音频中的丢失音频部分。

公开(公告)号：US20090067647A1

公开(公告)日：2009-03-12

申请号：US11665265

申请日：2006-04-11

申请人： Shinichi Yoshizawa ,  Tetsu Suzuki ,  Yoshihisa Nakatoh

发明人： Shinichi Yoshizawa ,  Tetsu Suzuki ,  Yoshihisa Nakatoh

IPC分类号： H04B1/00 ,  G10L19/00

CPC分类号： G10L21/0272 ,  G10L19/0204

摘要： A mixed audio separation system (100) which separates a specific audio from among a mixed audio (S100) includes a local frequency information generation unit (105) which obtains pieces of local frequency information (S103) corresponding to local reference waveforms (S102), based on the local reference waveforms (S102) and an analysis waveform which is the waveform of the mixed audio (S100). Each of the local reference waveforms (S102) (i) constitutes a part of a reference waveform for analyzing a predetermined frequency, (ii) has a predetermined temporal/spatial resolution and (iii) includes at least one of an amplification spectrum and a phase spectrum in the predetermined frequency. The system includes: a specific audio's frequency feature value extraction unit (106) which performs pattern matching between a first set which is the pieces of local frequency information and a second set of pieces of frequency information (S103) of a predetermined specific audio, and extracts the first set of the pieces of local frequency information (S103), based on a result of the pattern matching; and an audio signal generation unit which generates a signal of the specific audio, based on the first set of the pieces of local frequency information (S103) extracted by the specific audio's frequency feature value extraction unit.

摘要翻译： 从混合音频（S100）中分离特定音频的混合音频分离系统（100）包括本地频率信息生成单元（105），其获取与局部参考波形相对应的本地频率信息（S103）（S102）， 基于本地参考波形（S102）和作为混合音频的波形的分析波形（S100）。 每个局部参考波形（S102）（i）构成用于分析预定频率的参考波形的一部分，（ii）具有预定的时间/空间分辨率，以及（iii）包括放大光谱和相位 频谱在预定频率。 该系统包括：特定音频频率特征值提取单元（106），其执行作为本地频率信息的第一组与预定特定音频的第二组频率信息（S103）之间的模式匹配，以及 基于模式匹配的结果提取第一组本地频率信息（S103）; 以及音频信号生成单元，其基于由特定音频的频率特征值提取单元提取的第一组本地频率信息（S103），生成特定音频的信号。

公开(公告)号：US07974420B2

公开(公告)日：2011-07-05

申请号：US11665265

申请日：2006-04-11

申请人： Shinichi Yoshizawa ,  Tetsu Suzuki ,  Yoshihisa Nakatoh

发明人： Shinichi Yoshizawa ,  Tetsu Suzuki ,  Yoshihisa Nakatoh

IPC分类号： H03G5/00 ,  H04B15/00

CPC分类号： G10L21/0272 ,  G10L19/0204

摘要： A mixed audio separation system (100) which separates a specific audio from among a mixed audio (S100) includes a local frequency information generation unit (105) which obtains pieces of local frequency information (S103) corresponding to local reference waveforms (S102), based on the local reference waveforms (S102) and an analysis waveform which is the waveform of the mixed audio (S100). Each of the local reference waveforms (S102) (i) constitutes a part of a reference waveform for analyzing a predetermined frequency, (ii) has a predetermined temporal/spatial resolution and (iii) includes at least one of an amplification spectrum and a phase spectrum in the predetermined frequency. The system includes: a specific audio's frequency feature value extraction unit (106) which performs pattern matching between a first set which is the pieces of local frequency information and a second set of pieces of frequency information (S103) of a predetermined specific audio, and extracts the first set of the pieces of local frequency information (S103), based on a result of the pattern matching; and an audio signal generation unit which generates a signal of the specific audio, based on the first set of the pieces of local frequency information (S103) extracted by the specific audio's frequency feature value extraction unit.

摘要翻译： 从混合音频（S100）中分离特定音频的混合音频分离系统（100）包括本地频率信息生成单元（105），其获取与局部参考波形相对应的本地频率信息（S103）（S102）， 基于本地参考波形（S102）和作为混合音频的波形的分析波形（S100）。 每个局部参考波形（S102）（i）构成用于分析预定频率的参考波形的一部分，（ii）具有预定的时间/空间分辨率，以及（iii）包括放大光谱和相位 频谱在预定频率。 该系统包括：特定音频频率特征值提取单元（106），其执行作为本地频率信息的第一组与预定特定音频的第二组频率信息（S103）之间的模式匹配，以及 基于模式匹配的结果提取第一组本地频率信息（S103）; 以及音频信号生成单元，其基于由特定音频的频率特征值提取单元提取的第一组本地频率信息（S103），生成特定音频的信号。

公开(公告)号：US07473838B2

公开(公告)日：2009-01-06

申请号：US11783376

申请日：2007-04-09

申请人： Tetsu Suzuki ,  Yoshihisa Nakatoh ,  Shinichi Yoshizawa

发明人： Tetsu Suzuki ,  Yoshihisa Nakatoh ,  Shinichi Yoshizawa

IPC分类号： G10H1/00 ,  G06F17/00

CPC分类号： G10L25/48

摘要： A sound identification apparatus which reduces the chance of a drop in the identification rate, including: a frame sound feature extraction unit which extracts a sound feature per frame of an inputted audio signal; a frame likelihood calculation unit which calculates a frame likelihood of the sound feature in each frame, for each of a plurality of sound models; a confidence measure judgment unit which judges a confidence measure based on the frame likelihood; a cumulative likelihood output unit time determination unit which determines a cumulative likelihood output unit time based on the confidence measure; a cumulative likelihood calculation unit which calculates a cumulative likelihood in which the frame likelihoods of the frames included in the cumulative likelihood output unit time are cumulated, for each sound model; a sound type candidate judgment unit which determines, for each cumulative likelihood output unit time, a sound type corresponding to the sound model that has a maximum cumulative likelihood; a sound type frequency calculation unit which calculates the frequency of the sound type candidate; and a sound type interval determination unit which determines the sound type of the inputted audio signal and the interval of the sound type, based on the frequency of the sound type.

摘要翻译： 一种声音识别装置，其减少识别率下降的可能性，包括：帧声音特征提取单元，其提取每帧输入的音频信号的声音特征; 帧似然计算单元，对于多个声音模型中的每一个，计算每个帧中的声音特征的帧似然度; 置信度判断单元，其基于所述帧可能性判断置信度量; 累积似然度输出单元时间确定单元，其基于所述置信度测量来确定累积似然度输出单位时间; 对于每个声音模型，计算累积似然输出单元时间中包括的帧的帧似然性的累积似然度的累积似然度计算单元; 声音候选判定单元，对于每个累积似然度输出单位时间，确定与具有最大累积似然性的声音模型对应的声音类型; 声音型频率计算单元，其计算声音类型候选的频率; 以及声音类型间隔确定单元，其基于声音类型的频率来确定输入的音频信号的声音类型和声音类型的间隔。

公开(公告)号：US20080304672A1

公开(公告)日：2008-12-11

申请号：US11902731

申请日：2007-09-25

申请人： Shinichi Yoshizawa ,  Yoshihisa Nakatoh ,  Tetsu Suzuki

发明人： Shinichi Yoshizawa ,  Yoshihisa Nakatoh ,  Tetsu Suzuki

IPC分类号： H04R29/00

CPC分类号： G10L25/48 ,  G08G1/017 ,  G10L21/028 ,  G10L25/90

摘要： A target sound analysis apparatus capable of distinguishing between a sound having the same fundamental period as a target sound but which differs therefrom and the target sound and analyzing whether or not the target sound is contained in an evaluation sound is an target sound analysis apparatus that analyzes whether or not a target sound is included in an evaluation sound, and includes: a target sound preparation unit that prepares a target sound that is an analysis waveform to be used for analyzing a fundamental period; an evaluation sound preparation unit that prepares an evaluation sound that is an analyzed waveform in which its fundamental period will be analyzed; and an analysis unit that temporally shifts the target sound with respect to the evaluation sound to sequentially calculate differential values of the evaluation sound and the target sound at corresponding points in time, calculate an iterative interval between the points in time where the differential value is equal to or lower than a predetermined threshold value, and judge whether or not the target sound exists in the evaluation sound based on a period of the iterative interval and the fundamental period of the target sound.

摘要翻译： 能够区别具有与目标声音相同但与之不同的基准周期的声音与目标声音并且分析目标声音是否包含在评价声音中的目标声音分析装置是分析 无论目标声音是否被包括在评价声音中，并且包括：目标声音准备单元，其准备作为用于分析基本周期的分析波形的目标声音; 评估声音准备单元，其准备作为其分析基本周期的分析波形的评价声音; 以及分析单元，其相对于所述评价声音暂时移动所述目标声音，以在相应的时间点顺序地计算所述评价声音和所述目标声音的差分值，计算所述差分值相等的时间点之间的迭代间隔 达到或低于预定阈值，并且基于迭代间隔的周期和目标声音的基本周期来判断评估声中是否存在目标声音。

公开(公告)号：US08223978B2

公开(公告)日：2012-07-17

申请号：US11902731

申请日：2007-09-25

申请人： Shinichi Yoshizawa ,  Yoshihisa Nakatoh ,  Tetsu Suzuki

发明人： Shinichi Yoshizawa ,  Yoshihisa Nakatoh ,  Tetsu Suzuki

IPC分类号： H04R29/00

CPC分类号： G10L25/48 ,  G08G1/017 ,  G10L21/028 ,  G10L25/90

摘要： A target sound analysis apparatus capable of distinguishing between a sound having the same fundamental period as a target sound but which differs therefrom and the target sound and analyzing whether or not the target sound is contained in an evaluation sound is an target sound analysis apparatus that analyzes whether or not a target sound is included in an evaluation sound, and includes: a target sound preparation unit that prepares a target sound that is an analysis waveform to be used for analyzing a fundamental period; an evaluation sound preparation unit that prepares an evaluation sound that is an analyzed waveform in which its fundamental period will be analyzed; and an analysis unit that temporally shifts the target sound with respect to the evaluation sound to sequentially calculate differential values of the evaluation sound and the target sound at corresponding points in time, calculate an iterative interval between the points in time where the differential value is equal to or lower than a predetermined threshold value, and judge whether or not the target sound exists in the evaluation sound based on a period of the iterative interval and the fundamental period of the target sound.

摘要翻译： 能够区别具有与目标声音相同但与之不同的基准周期的声音与目标声音并且分析目标声音是否包含在评价声音中的目标声音分析装置是分析 无论目标声音是否被包括在评价声音中，并且包括：目标声音准备单元，其准备作为用于分析基本周期的分析波形的目标声音; 评估声音准备单元，其准备作为其分析基本周期的分析波形的评价声音; 以及分析单元，其相对于所述评价声音暂时移动所述目标声音，以在相应的时间点顺序地计算所述评价声音和所述目标声音的差分值，计算所述差分值相等的时间点之间的迭代间隔 达到或低于预定阈值，并且基于迭代间隔的周期和目标声音的基本周期来判断评估声中是否存在目标声音。