公开(公告)号：US20150302845A1

公开(公告)日：2015-10-22

申请号：US14418680

申请日：2013-07-30

Applicant: National Institute of Advanced Industrial Science and Technology

Inventor： Tomoyasu Nakano ,  Masataka Goto

IPC: G10L13/02 ,  G10L25/90 ,  G10L25/78 ,  G10L25/15 ,  G10L25/18

CPC classification number: G10L13/02 ,  G10L19/022 ,  G10L21/013 ,  G10L25/15 ,  G10L25/18 ,  G10L25/45 ,  G10L25/78 ,  G10L25/90 ,  G10L2025/906

Abstract: For high-accuracy analysis and high-quality synthesis of voice sound (singing and speech), provided herein are a system and a method for estimating from an audio signal spectral envelopes and group delays for sound analysis and synthesis with high accuracy and high temporal resolution. An estimation system of spectral envelopes and group delays includes a fundamental frequency estimation section, an amplitude spectrum acquisition section, a group delay extraction section, a spectral envelope integration section, and a group delay integration section. The spectral envelope integration section sequentially obtains a spectral envelope for sound synthesis by averaging overlapped spectra. The group delay integration section selects from a plurality of group delays a group delay corresponding to the maximum envelope of each frequency component of the spectral envelope and integrates groups delays thus selected to sequentially obtain a group delay for sound synthesis.

Abstract translation: 对于高精度分析和语音（歌唱和语音）的高质量合成，本文提供了一种用于从音频信号估计频谱包络和组延迟的系统和方法，用于具有高精度和高时间分辨率的声音分析和合成 。 频谱包络和组延迟的估计系统包括基频估计部分，幅度频谱获取部分，组延迟提取部分，频谱包络积分部分和组延迟积分部分。 频谱包络积分部分通过平均重叠频谱顺序地获得声音合成的频谱包络。 组延迟积分部从多个组延迟中选择与频谱包络的​​每个频率分量的最大包络相对应的组延迟，并且对由此选择的组延迟进行积分，以顺序地获得用于声音合成的组延迟。

公开(公告)号：US09595256B2

公开(公告)日：2017-03-14

申请号：US14649630

申请日：2013-12-04

Applicant: National Institute of Advanced Industrial Science and Technology

Inventor： Tomoyasu Nakano ,  Masataka Goto

IPC: G10L13/08 ,  G10L11/04 ,  G10L13/04 ,  G10L13/02 ,  G10L13/033 ,  G10L13/10 ,  G10H1/00 ,  G10L25/90 ,  G10L15/02

CPC classification number: G10L13/033 ,  G10H1/0066 ,  G10H2220/106 ,  G10H2250/455 ,  G10L13/10 ,  G10L25/90 ,  G10L2015/025

Abstract: A singing synthesis section for generating singing by integrating into one singing a plurality of vocals sung by a singer a plurality of times or vocals of which parts that he/she does not like are sung again. A music audio signal playback section plays back the music audio signal from a signal portion or its immediately preceding signal corresponding to a character in the lyrics when the character displayed on the display screen is selected by a character selecting section. An estimation and analysis data storing section automatically aligns the lyrics with the vocal, decomposes the vocal into three elements, pitch, power, and timber, and stores them. A data selecting section allows the user to select each of the three elements for respective time periods of phonemes. The data editing section modifies the time periods of the three elements in alignment with the modified time periods of the phonemes.

Abstract translation: 歌唱综合部分通过多个唱歌组合唱歌，多个歌手唱歌，并重新唱歌，组成唱歌组合部分。 当通过字符选择部分选择显示在显示画面上的字符时，音乐音频信号播放部分从与信号部分或其紧邻的前一信号相对应的音乐音频信号中播放音乐音频信号。 估计和分析数据存储部分自动将歌词与声音对齐，将歌声分解为三个元素，音高，力量和木材，并存储它们。 数据选择部分允许用户在音素的各个时间段中选择三个元素中的每一个。 数据编辑部分修改与音素的修改时间段对齐的三个元素的时间段。

公开(公告)号：US20150310850A1

公开(公告)日：2015-10-29

申请号：US14649630

申请日：2013-12-04

Applicant: NATIONAL INSTITUTE OF ADVANCED INDUSTRIAL SCIENCE AND TECHNOLOGY

Inventor： Tomoyasu Nakano ,  Masataka Goto

IPC: G10L13/033 ,  G10L25/90

CPC classification number: G10L13/033 ,  G10H1/0066 ,  G10H2220/106 ,  G10H2250/455 ,  G10L13/10 ,  G10L25/90 ,  G10L2015/025

Abstract: A singing synthesis section for generating singing by integrating into one singing a plurality of vocals sung by a singer a plurality of times or vocals of which parts that he/she does not like are sung again. A music audio signal playback section plays back the music audio signal from a signal portion or its immediately preceding signal corresponding to a character in the lyrics when the character displayed on the display screen is selected by a character selecting section. An estimation and analysis data storing section automatically aligns the lyrics with the vocal, decomposes the vocal into three elements, pitch, power, and timber, and stores them. A data selecting section allows the user to select each of the three elements for respective time periods of phonemes. The data editing section modifies the time periods of the three elements in alignment with the modified time periods of the phonemes.

Abstract translation: 歌唱综合部分通过多个唱歌组合唱歌，多个歌手唱歌，并重新唱歌，组成唱歌组合部分。 当通过字符选择部分选择显示在显示画面上的字符时，音乐音频信号播放部分从与信号部分或其紧邻的前一信号相对应的音乐音频信号中播放音乐音频信号。 估计和分析数据存储部分自动将歌词与声音对齐，将歌声分解为三个元素，音高，力量和木材，并存储它们。 数据选择部分允许用户在音素的各个时间段中选择三个元素中的每一个。 数据编辑部分修改与音素的修改时间段对齐的三个元素的时间段。

公开(公告)号：US20170061988A1

公开(公告)日：2017-03-02

申请号：US15119747

申请日：2014-08-15

Applicant: National Institute of Advanced Industrial Science and Technology

Inventor： Tomoyasu Nakano ,  Kazuyoshi Yoshii ,  Masataka Goto

IPC: G10L25/54 ,  G06F17/30 ,  G10L21/14 ,  G10L21/01 ,  G10L19/022 ,  G10L25/12

CPC classification number: G10L25/54 ,  G06F17/30758 ,  G10H1/00 ,  G10H2210/056 ,  G10L13/02 ,  G10L19/022 ,  G10L21/003 ,  G10L21/01 ,  G10L21/10 ,  G10L21/14 ,  G10L25/12 ,  G10L25/24 ,  G10L25/90

Abstract: A system for multifaceted singing analysis for retrieval of songs or music including singing voices having some relationship in latent semantics with a singing voice included in one particular song or music. A topic analyzing processor uses a topic model to analyze a plurality of vocal symbolic time series obtained for a plurality of musical audio signals. The topic analyzing processor generates a vocal topic distribution for each of the musical audio signals whereby the vocal topic distribution is composed of a plurality of vocal topics each indicating a relationship of one of the musical audio signals with the other musical audio signals. The topic analyzing processor generates a vocal symbol distribution for each of the vocal topics whereby the vocal symbol distribution indicates occurrence probabilities for the vocal symbols. A multifaceted singing analyzing processor performs analysis of singing voices included in musical audio signals, in the multifaceted viewpoint.

Abstract translation: 一种用于检索歌曲或音乐的多方面歌唱分析系统，包括在一种特定歌曲或音乐中包括具有歌声的潜在语义中具有一些关系的歌唱声音。 主题分析处理器使用主题模型来分析为多个音乐音频信号获得的多个声乐符号时间序列。 主题分析处理器为每个音乐音频信号生成声乐主题分布，由此声乐主题分布由多个声乐主题组成，每个声乐主题各自表示音乐音频信号之一与其他音乐音频信号的关系。 主题分析处理器为每个声乐主题生成声乐符号分布，由此声乐符号分布指示声乐符号的出现概率。 多方面的歌唱分析处理器在多方面的观点中对包括在音乐音频信号中的歌声进行分析。

公开(公告)号：US09747927B2

公开(公告)日：2017-08-29

申请号：US15119747

申请日：2014-08-15

Applicant: National Institute of Advanced Industrial Science and Technology

Inventor： Tomoyasu Nakano ,  Kazuyoshi Yoshii ,  Masataka Goto

IPC: G10L21/00 ,  G10L25/54 ,  G10L13/02 ,  G06F17/30 ,  G10H1/00 ,  G10L19/022 ,  G10L21/01 ,  G10L21/14 ,  G10L25/12 ,  G10L25/00

CPC classification number: G10L25/54 ,  G06F17/30758 ,  G10H1/00 ,  G10H2210/056 ,  G10L13/02 ,  G10L19/022 ,  G10L21/003 ,  G10L21/01 ,  G10L21/10 ,  G10L21/14 ,  G10L25/12 ,  G10L25/24 ,  G10L25/90

Abstract: A system for multifaceted singing analysis for retrieval of songs or music including singing voices having some relationship in latent semantics with a singing voice included in one particular song or music. A topic analyzing processor uses a topic model to analyze a plurality of vocal symbolic time series obtained for a plurality of musical audio signals. The topic analyzing processor generates a vocal topic distribution for each of the musical audio signals whereby the vocal topic distribution is composed of a plurality of vocal topics each indicating a relationship of one of the musical audio signals with the other musical audio signals. The topic analyzing processor generates a vocal symbol distribution for each of the vocal topics whereby the vocal symbol distribution indicates occurrence probabilities for the vocal symbols. A multifaceted singing analyzing processor performs analysis of singing voices included in musical audio signals, in the multifaceted viewpoint.

公开(公告)号：US09368103B2

公开(公告)日：2016-06-14

申请号：US14418680

申请日：2013-07-30

Applicant: National Institute of Advanced Industrial Science and Technology

Inventor： Tomoyasu Nakano ,  Masataka Goto

IPC: G10L25/90 ,  G10L13/02 ,  G10L25/18 ,  G10L25/45 ,  G10L25/15 ,  G10L25/78 ,  G10L21/013 ,  G10L19/022

CPC classification number: G10L13/02 ,  G10L19/022 ,  G10L21/013 ,  G10L25/15 ,  G10L25/18 ,  G10L25/45 ,  G10L25/78 ,  G10L25/90 ,  G10L2025/906

Abstract: For high-accuracy analysis and high-quality synthesis of voice sound (singing and speech), provided herein are a system and a method for estimating from an audio signal spectral envelopes and group delays for sound analysis and synthesis with high accuracy and high temporal resolution. An estimation system of spectral envelopes and group delays includes a fundamental frequency estimation section, an amplitude spectrum acquisition section, a group delay extraction section, a spectral envelope integration section, and a group delay integration section. The spectral envelope integration section sequentially obtains a spectral envelope for sound synthesis by averaging overlapped spectra. The group delay integration section selects from a plurality of group delays a group delay corresponding to the maximum envelope of each frequency component of the spectral envelope and integrates groups delays thus selected to sequentially obtain a group delay for sound synthesis.

Abstract translation: 对于高精度分析和语音（歌唱和语音）的高质量合成，本文提供了一种用于从音频信号估计频谱包络和组延迟的系统和方法，用于具有高精度和高时间分辨率的声音分析和合成 。 频谱包络和组延迟的估计系统包括基频估计部分，幅度频谱获取部分，组延迟提取部分，频谱包络积分部分和组延迟积分部分。 频谱包络积分部分通过平均重叠频谱顺序地获得声音合成的频谱包络。 组延迟积分部从多个组延迟中选择与频谱包络的​​每个频率分量的最大包络相对应的组延迟，并且对由此选择的组延迟进行积分，以顺序地获得用于声音合成的组延迟。