公开(公告)号：US08005666B2

公开(公告)日：2011-08-23

申请号：US11834778

申请日：2007-08-07

申请人： Masataka Goto ,  Hiromasa Fujihara ,  Hiroshi Okuno

发明人： Masataka Goto ,  Hiromasa Fujihara ,  Hiroshi Okuno

IPC分类号： G10L11/14 ,  G10L11/06 ,  G10L15/14 ,  G10H1/36

CPC分类号： G10L15/26 ,  G10L15/187

摘要： An automatic system for temporal alignment between a music audio signal and lyrics is provided. The automatic system can prevent accuracy for temporal alignment from being lowered due to the influence of non-vocal sections. Alignment means of the system is provided with a phone model for singing voice that estimates phonemes corresponding to temporal-alignment features or features available for temporal alignment. The alignment means receives temporal-alignment features outputted from temporal-alignment feature extraction means, information on the vocal and non-vocal sections outputted from vocal section estimation means, and a phoneme network, and performs an alignment operation on condition that no phoneme exists at least in non-vocal sections.

摘要翻译： 提供了一种用于音乐音频信号和歌词之间的时间对准的自动系统。 自动系统可以防止由于非声部的影响而使时间对准的精度降低。 系统的对准装置被提供有用于歌唱声音的电话模型，该模型估计对应于可用于时间对准的时间对准特征或特征的音素。 对准装置接收从时间对准特征提取装置输出的时间对准特征，从声部部分估计装置输出的声部和非声部的信息和音素网络，并且在没有音素存在的条件下执行对准操作 至少在非声部。

公开(公告)号：US20080097754A1

公开(公告)日：2008-04-24

申请号：US11834778

申请日：2007-08-07

申请人： Masataka Goto ,  Hiromasa Fujihara ,  Hiroshi Okuno

发明人： Masataka Goto ,  Hiromasa Fujihara ,  Hiroshi Okuno

IPC分类号： G10L15/04

CPC分类号： G10L15/26 ,  G10L15/187

摘要： An automatic system for temporal alignment between a music audio signal and lyrics is provided. The automatic system can prevent accuracy for temporal alignment from being lowered due to the influence of non-vocal sections. Alignment means of the system is provided with a phone model for singing voice that estimates phonemes corresponding to temporal-alignment features or features available for temporal alignment. The alignment means receives temporal-alignment features outputted from temporal-alignment feature extraction means, information on the vocal and non-vocal sections outputted from vocal section estimation means, and a phoneme network, and performs an alignment operation on condition that no phoneme exists at least in non-vocal sections.

摘要翻译： 提供了一种用于音乐音频信号和歌词之间的时间对准的自动系统。 自动系统可以防止由于非声部分的影响而使时间对准的精度降低。 系统的对准装置被提供有用于歌唱声音的电话模型，该模型估计对应于可用于时间对准的时间对准特征或特征的音素。 对准装置接收从时间对准特征提取装置输出的时间对准特征，从声部部分估计装置输出的声部和非声部的信息和音素网络，并且在没有音素存在的条件下执行对准操作 至少在非声部。

公开(公告)号：US20050283361A1

公开(公告)日：2005-12-22

申请号：US11020030

申请日：2004-12-21

申请人： Kazuyoshi Yoshii ,  Hiroshi Okuno ,  Masataka Goto

发明人： Kazuyoshi Yoshii ,  Hiroshi Okuno ,  Masataka Goto

IPC分类号： G10L19/04 ,  G10L21/02

CPC分类号： G10L21/0364 ,  G10L19/04 ,  G10L21/0232

摘要： An apparatus and method for extracting a predetermined non-harmonic structured spectral component contained in an audio signal. Then, the extracted predetermined spectral component is increased or decreased. In this process, the spectrum of the audio signal is calculated by frequency analysis, so that a spectrum component corresponding to the predetermined non-harmonic structured spectral component is extracted and then increased or decreased. The extraction of the predetermined non-harmonic structured spectral component is performed with reference to a spectral component of a template stored in advance. In this process, the spectral component of the template is adapted in such a manner that the difference between the extracted spectral component and the spectral component of the template goes below or at a predetermined value. This allows the audio-signal contained predetermined non-harmonic structured spectral component to be independently increased or decreased without an influence on other spectral components.

摘要翻译： 一种用于提取包含在音频信号中的预定非谐波结构频谱分量的装置和方法。 然后，提取的预定光谱分量被增加或减小。 在该过程中，通过频率分析计算音频信号的频谱，从而提取与预定的非谐波结构频谱分量对应的频谱分量，然后增大或减小。 参考预先存储的模板的光谱分量来执行预定非谐波结构光谱分量的提取。 在该过程中，模板的频谱分量被调整成使得提取的频谱分量与模板的频谱分量之间的差异低于或处于预定值。 这允许包含预定非谐波结构频谱分量的音频信号独立地增加或减少，而不影响其他频谱分量。

公开(公告)号：US20110112994A1

公开(公告)日：2011-05-12

申请号：US12671255

申请日：2008-07-31

申请人： Masataka Goto ,  Kazuyoshi Yoshii ,  Hiroshi Okuno

发明人： Masataka Goto ,  Kazuyoshi Yoshii ,  Hiroshi Okuno

IPC分类号： G06F15/18

CPC分类号： G06F17/30766 ,  G06Q30/02 ,  G10H1/0008 ,  G10H2210/031 ,  G10H2240/081 ,  G10H2240/105 ,  G10H2240/131

摘要： A musical piece recommendation system is provided that allows instantaneous registration of a new user and a new musical piece without retraining in a basic training section. A first incremental training section 21 monitors a rating history storage section 3, and each time a change is made to a rating history or a new user is added, performs updating of or addition of the topic selection probability for the user for which the change is made to the rating history or for the new user such that the likelihood determined by a basic training section 17 is kept maximized. A second incremental training section 21 monitors an acoustic feature storage section 5, and each time a new musical piece is added to perform addition to acoustic features, adds the musical piece selection probability related to the added musical piece such that the likelihood determined by the basic training section 17 is kept maximized.

摘要翻译： 提供了一种音乐作品推荐系统，其允许新用户和新音乐作品的瞬时登记，而无需在基本训练部分中重新训练。 第一增量训练部分21监视评级历史存储部分3，并且每当对评级历史进行改变或添加新用户时，执行更改为该用户的主题选择概率的更新或添加 对于评级历史或新用户，使得由基本训练部分17确定的可能性被保持最大化。 第二增量训练部分21监测声学特征存储部分5，并且每次添加新的音乐作品以对声学特征进行加法时，将与所添加的乐曲相关的乐曲选择概率相加，使得由基本 训练部分17被保持最大化。

公开(公告)号：US08239052B2

公开(公告)日：2012-08-07

申请号：US12595542

申请日：2008-04-14

申请人： Katsutoshi Itoyama ,  Hiroshi Okuno ,  Masataka Goto

发明人： Katsutoshi Itoyama ,  Hiroshi Okuno ,  Masataka Goto

IPC分类号： G06F17/00

CPC分类号： G10H3/125 ,  G10H1/0008 ,  G10H2210/056 ,  G10H2210/066 ,  G10H2210/086 ,  G10H2210/301 ,  G10H2240/056 ,  G10H2250/031

摘要： An audio signal produced by playing a plurality of musical instruments is separated into sound sources according to respective instrument sounds. Each time a separation process is performed, the updated model parameter estimation/storage section 114 estimates parameters respectively contained in updated model parameters such that updated power spectrograms gradually change from a state close to initial power spectrograms to a state close to a plurality of power spectrograms most recently stored in a power spectrogram separation/storage section. Respective sections including the power spectrogram separation/storage section 112 and an updated distribution function computation/storage section 118 repeatedly perform process operations until the updated power spectrograms change from the state close to the initial power spectrograms to the state close to the plurality of power spectrograms most recently stored in the power spectrogram separation/storage section 112. The final updated power spectrograms are close to the power spectrograms of single tones of one musical instrument contained in the input audio signal formed to contain harmonic and inharmonic models.

摘要翻译： 通过播放多个乐器产生的音频信号根据相应的乐器声音被分离成声源。 每当执行分离处理时，更新的模型参数估计/存储部114估计更新的模型参数中包含的参数，使得更新的功率谱图从接近初始功率谱图的状态逐渐变化到接近多个功率谱图的状态 最近存储在功率谱图分离/存储部分中。 包括功率谱图分离/存储部分112和更新的分布函数计算/存储部分118的各个部分重复执行处理操作，直到更新的功率谱图从接近初始功率谱图的状态改变到接近多个功率谱图的状态 最近存储在功率谱图分离/存储部分112中。最终更新的功率谱图接近包含在形成为包含谐波和非谐波模型的输入音频信号中的一个乐器的单个音调的功率谱图。

公开(公告)号：US08370277B2

公开(公告)日：2013-02-05

申请号：US12671255

申请日：2008-07-31

申请人： Masataka Goto ,  Kazuyoshi Yoshii ,  Hiroshi Okuno

发明人： Masataka Goto ,  Kazuyoshi Yoshii ,  Hiroshi Okuno

IPC分类号： G06F15/18

CPC分类号： G06F17/30766 ,  G06Q30/02 ,  G10H1/0008 ,  G10H2210/031 ,  G10H2240/081 ,  G10H2240/105 ,  G10H2240/131

摘要： A musical piece recommendation system that allows instantaneous registration of a new user and a new musical piece without retraining in a basic training section. A first incremental training section monitors a rating history storage section, and each time a change is made to a rating history or a new user is added, performs updating of or addition of the topic selection probability for the user for which the change is made to the rating history or for the new user such that the likelihood determined by a basic training section is kept maximized. A second incremental training section monitors an acoustic feature storage section, and each time a new musical piece is added to perform addition to acoustic features, adds the musical piece selection probability related to the added musical piece such that the likelihood determined by the basic training section is kept maximized.

摘要翻译： 一种音乐作品推荐系统，允许新用户和新音乐作品的瞬时注册，而不需要在基本训练部分重新训练。 第一增量训练部分监视评级历史存储部分，并且每当对评级历史进行改变或添加新用户时，对进行了改变的用户进行主题选择概率的更新或添加 评级历史或新用户使得由基本训练部确定的可能性被保持最大化。 第二增量训练部分监视声学特征存储部分，并且每当添加新的音乐作品以对声学特征进行加法时，增加与所添加的乐曲相关的乐曲选择概率，使得由基本训练部分确定的可能性 被保持最大化。

公开(公告)号：US20100131086A1

公开(公告)日：2010-05-27

申请号：US12595542

申请日：2008-04-14

申请人： Katsutoshi Itoyama ,  Hiroshi Okuno ,  Masataka Goto

发明人： Katsutoshi Itoyama ,  Hiroshi Okuno ,  Masataka Goto

IPC分类号： G06F17/10 ,  G09B15/02 ,  G06F17/00 ,  G06G7/62

CPC分类号： G10H3/125 ,  G10H1/0008 ,  G10H2210/056 ,  G10H2210/066 ,  G10H2210/086 ,  G10H2210/301 ,  G10H2240/056 ,  G10H2250/031

摘要： An audio signal produced by playing a plurality of musical instruments is separated into sound sources according to respective instrument sounds. Each time a separation process is performed, the updated model parameter estimation/storage section 114 estimates parameters respectively contained in updated model parameters such that updated power spectrograms gradually change from a state close to initial power spectrograms to a state close to a plurality of power spectrograms most recently stored in a power spectrogram separation/storage section. Respective sections including the power spectrogram separation/storage section 112 and an updated distribution function computation/storage section 118 repeatedly perform process operations until the updated power spectrograms change from the state close to the initial power spectrograms to the state close to the plurality of power spectrograms most recently stored in the power spectrogram separation/storage section 112. The final updated power spectrograms are close to the power spectrograms of single tones of one musical instrument contained in the input audio signal formed to contain harmonic and inharmonic models.

摘要翻译： 通过播放多个乐器产生的音频信号根据相应的乐器声音被分离成声源。 每当执行分离处理时，更新的模型参数估计/存储部114估计更新的模型参数中包含的参数，使得更新的功率谱图从接近初始功率谱图的状态逐渐变化到接近多个功率谱图的状态 最近存储在功率谱图分离/存储部分中。 包括功率谱图分离/存储部分112和更新的分布函数计算/存储部分118的各个部分重复执行处理操作，直到更新的功率谱图从接近初始功率谱图的状态改变到接近多个功率谱图的状态 最近存储在功率谱图分离/存储部分112中。最终更新的功率谱图接近包含在形成为包含谐波和非谐波模型的输入音频信号中的一个乐器的单个音调的功率谱图。

公开(公告)号：US08244522B2

公开(公告)日：2012-08-14

申请号：US12123757

申请日：2008-05-20

申请人： Mikio Nakano ,  Hiroshi Okuno ,  Kazunori Komatani ,  Yuichiro Fukubayashi ,  Kotaro Funakoshi

发明人： Mikio Nakano ,  Hiroshi Okuno ,  Kazunori Komatani ,  Yuichiro Fukubayashi ,  Kotaro Funakoshi

IPC分类号： G06F17/27 ,  G06F17/20 ,  G10L15/00

CPC分类号： G06F17/2775 ,  G10L15/1815

摘要： A language understanding device includes: a language understanding model storing unit configured to store word transition data including pre-transition states, input words, predefined outputs corresponding to the input words, word weight information, and post-transition states, and concept weighting data including concepts obtained from language understanding results for at least one word, and concept weight information corresponding to the concepts; a finite state transducer processing unit configured to output understanding result candidates including the predefined outputs, to accumulate word weights so as to obtain a cumulative word weight, and to sequentially perform state transition operations; a concept weighting processing unit configured to accumulate concept weights so as to obtain a cumulative concept weight; and an understanding result determination unit configured to determine an understanding result from the understanding result candidates by referring to the cumulative word weight and the cumulative concept weight.

摘要翻译： 语言理解装置包括：语言理解模型存储单元，被配置为存储包括转换前状态，输入字，对应于输入字的预定义输出，字重量信息和转换后状态的字跃迁数据，以及概念加权数据，包括 从至少一个单词的语言理解中获得的概念，以及对应于概念的概念权重信息; 有限状态传感器处理单元，被配置为输出包括预定义输出的理解结果候选，以累积字权重，以获得累积字权重，并且顺序执行状态转换操作; 概念加权处理单元，被配置为累积概念权重以获得累积概念权重; 以及理解结果确定单元，被配置为通过参考累积单词权重和累积概念权重来确定理解结果候选的理解结果。

公开(公告)号：US20090018828A1

公开(公告)日：2009-01-15

申请号：US10579235

申请日：2004-11-12

申请人： Kazuhiro Nakadai ,  Hiroshi Tsujino ,  Hiroshi Okuno

发明人： Kazuhiro Nakadai ,  Hiroshi Tsujino ,  Hiroshi Okuno

IPC分类号： G10L19/14

CPC分类号： G10L15/20 ,  G10L21/028 ,  G10L2021/02166

摘要： An automatic speech recognition system includes: a sound source localization module for localizing a sound direction of a speaker based on the acoustic signals detected by the plurality of microphones; a sound source separation module for separating a speech signal of the speaker from the acoustic signals according to the sound direction; an acoustic model memory which stores direction-dependent acoustic models that are adjusted to a plurality of directions at intervals; an acoustic model composition module which composes an acoustic model adjusted to the sound direction, which is localized by the sound source localization module, based on the direction-dependent acoustic models, the acoustic model composition module storing the acoustic model in the acoustic model memory; and a speech recognition module which recognizes the features extracted by a feature extractor as character information using the acoustic model composed by the acoustic model composition module.

摘要翻译： 一种自动语音识别系统，包括：声源定位模块，用于基于由所述多个麦克风检测到的声信号来定位扬声器的声音方向; 声源分离模块，用于根据声音方向将扬声器的语音信号与声学信号分离; 声学模型存储器，其存储以间隔被调整到多个方向的方向相关的声学模型; 声学模型合成模块，其基于所述方向相关的声学模型，将声学模型组合模块存储在所述声学模型存储器中;声学模型组合模块，其将声学模型组合模块存储在所述声学模型存储器中; 以及语音识别模块，其使用由声学模型组合模块组成的声学模型识别由特征提取器提取的特征作为字符信息。

公开(公告)号：US20080294437A1

公开(公告)日：2008-11-27

申请号：US12123757

申请日：2008-05-20

申请人： Mikio Nakano ,  Hiroshi Okuno ,  Kazunori Komatani ,  Yuichiro Fukubayashi ,  Kotaro Funakoshi

发明人： Mikio Nakano ,  Hiroshi Okuno ,  Kazunori Komatani ,  Yuichiro Fukubayashi ,  Kotaro Funakoshi

IPC分类号： G10L15/00

CPC分类号： G06F17/2775 ,  G10L15/1815

摘要： A language understanding device includes: a language understanding model storing unit configured to store word transition data including pre-transition states, input words, predefined outputs corresponding to the input words, word weight information, and post-transition states, and concept weighting data including concepts obtained from language understanding results for at least one word, and concept weight information corresponding to the concepts; a finite state transducer processing unit configured to output understanding result candidates including the predefined outputs, to accumulate word weights so as to obtain a cumulative word weight, and to sequentially perform state transition operations; a concept weighting processing unit configured to accumulate concept weights so as to obtain a cumulative concept weight; and an understanding result determination unit configured to determine an understanding result from the understanding result candidates by referring to the cumulative word weight and the cumulative concept weight.

摘要翻译： 语言理解装置包括：语言理解模型存储单元，被配置为存储包括转换前状态，输入字，对应于输入字的预定义输出，字重量信息和转换后状态的字跃迁数据，以及概念加权数据，包括 从至少一个单词的语言理解中获得的概念，以及对应于概念的概念权重信息; 有限状态传感器处理单元，被配置为输出包括预定义输出的理解结果候选，以累积字权重，以获得累积字权重，并且顺序执行状态转换操作; 概念加权处理单元，被配置为累积概念权重以获得累积概念权重; 以及理解结果确定单元，被配置为通过参考累积单词权重和累积概念权重来确定理解结果候选的理解结果。