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

US11289066B2 Voice synthesis apparatus and voice synthesis method utilizing diphones or triphones and machine learning 有权
公开(公告)号：US11289066B2
公开(公告)日：2022-03-29
申请号：US16233421
申请日：2018-12-27
申请人： YAMAHA CORPORATION
发明人： Yuji Hisaminato , Ryunosuke Daido , Keijiro Saino , Jordi Bonada , Merlijn Blaauw
IPC分类号： G10L13/06 , G10L13/07 , G10L13/00 , G10L13/033 , G10L13/10 , G10L13/08 , G10L25/18
摘要： A voice synthesis method includes: sequentially acquiring voice units comprising at least one of diphone or a triphone in accordance with synthesis information for synthesizing voices; generating statistical spectral envelopes using a statistical model built by machine learning in accordance with the synthesis information for synthesizing the voices; and concatenating the sequentially acquired voice units and modifying a frequency spectral envelope of each voice unit in accordance with the generated statistical spectral envelope, thereby synthesizing a voice signal based on the concatenated voice units having the modified frequency spectra.

2. 发明授权

US10490181B2 Technology for responding to remarks using speech synthesis 有权
公开(公告)号：US10490181B2
公开(公告)日：2019-11-26
申请号：US15375984
申请日：2016-12-12
申请人： YAMAHA CORPORATION
发明人： Hiroaki Matsubara , Junya Ura , Takehiko Kawahara , Yuji Hisaminato , Katsuji Yoshimura
IPC分类号： G10L13/033 , G10L13/027 , G10L15/18 , G10L25/90 , G10L13/06 , G10L13/10
CPC分类号： G10L13/0335 , G10L13/027 , G10L15/18 , G10L25/90 , G10L13/033 , G10L13/06 , G10L13/10 , H04M2201/39
摘要： The present invention is provided with: a voice input section that receives a remark (a question) via a voice signal; a reply creation section that creates a voice sequence of a reply (response) to the remark; a pitch analysis section that analyzes the pitch of a first segment (e.g., word ending) of the remark; and a voice generation section (a voice synthesis section, etc.) that generates a reply, in the form of voice, represented by the voice sequence. The voice generation section controls the pitch of the entire reply in such a manner that the pitch of a second segment (e.g., word ending) of the reply assumes a predetermined pitch (e.g., five degrees down) with respect to the pitch of the first segment of the remark. Such arrangements can realize synthesis of replying voice capable of giving a natural feel to the user.

3. 发明授权

US09685152B2 Technology for responding to remarks using speech synthesis 有权
公开(公告)号：US09685152B2
公开(公告)日：2017-06-20
申请号：US14892624
申请日：2014-06-02
申请人： YAMAHA CORPORATION
发明人： Hiroaki Matsubara , Junya Ura , Takehiko Kawahara , Yuji Hisaminato , Katsuji Yoshimura
IPC分类号： G10L13/033 , G10L13/027 , G10L13/10 , G10L15/18 , G10L13/06 , G10L25/90
CPC分类号： G10L13/0335 , G10L13/027 , G10L13/033 , G10L13/06 , G10L13/10 , G10L15/18 , G10L25/90 , H04M2201/39
摘要： The present invention is provided with: a voice input section that receives a remark (a question) via a voice signal; a reply creation section that creates a voice sequence of a reply (response) to the remark; a pitch analysis section that analyzes the pitch of a first segment (e.g., word ending) of the remark; and a voice generation section (a voice synthesis section, etc.) that generates a reply, in the form of voice, represented by the voice sequence. The voice generation section controls the pitch of the entire reply in such a manner that the pitch of a second segment (e.g., word ending) of the reply assumes a predetermined pitch (e.g., five degrees down) with respect to the pitch of the first segment of the remark. Such arrangements can realize synthesis of replying voice capable of giving a natural feel to the user.

4. 发明授权

US11410637B2 Voice synthesis method, voice synthesis device, and storage medium 有权
公开(公告)号：US11410637B2
公开(公告)日：2022-08-09
申请号：US16395737
申请日：2019-04-26
申请人： YAMAHA CORPORATION
发明人： Jordi Bonada , Merlijn Blaauw , Keijiro Saino , Ryunosuke Daido , Michael Wilson , Yuji Hisaminato
IPC分类号： G10L13/033 , G10L13/00
摘要： A voice synthesis method according to an embodiment includes altering a series of synthesis spectra in a partial period of a synthesis voice based on a series of amplitude spectrum envelope contours of a voice expression to obtain a series of altered spectra to which the voice expression has been imparted, and synthesizing a series of voice samples to which the voice expression has been imparted, based on the series of altered spectra.

5. 发明授权

US09286906B2 Voice processing apparatus 有权
标题翻译：语音处理装置
公开(公告)号：US09286906B2
公开(公告)日：2016-03-15
申请号：US13923203
申请日：2013-06-20
申请人： Yamaha Corporation
发明人： Jordi Bonada , Merlijn Blaauw , Yuji Hisaminato
IPC分类号： G10L21/013 , G10L19/26
CPC分类号： G10L19/265 , G10L21/013
摘要： In a voice processing apparatus, a processor is configured to adjust, a fundamental frequency of a first voice signal corresponding to a voice having target voice characteristics to a fundamental frequency of a second voice signal corresponding to a voice having initial voice characteristics different from the target voice characteristics. The processor is further configured to sequentially generate a processed spectrum based on a spectrum of the first voice signal and a spectrum of the second voice signal by: dividing the spectrum of the first voice signal into a plurality of harmonic band components after the fundamental frequency of the first voice signal has been adjusted; allocating each harmonic band component of the first voice signal to each harmonic frequency associated with the fundamental frequency of the second voice signal; and adjusting an envelope and phase of each harmonic band component according to the spectrum of the second voice signal.
摘要翻译：在语音处理装置中，处理器被配置为将与具有目标语音特性的语音相对应的第一语音信号的基频调整为对应于具有与目标不同的初始语音特征的语音的第二语音信号的基频声音特征。处理器还被配置为通过以下方式顺序地生成基于第一语音信号的频谱和第二语音信号的频谱的处理频谱：将基本频率的第一语音信号的频谱划分为多个谐波频带分量第一个语音信号已被调整; 将第一语音信号的每个谐波频带分量分配给与第二语音信号的基频相关联的每个谐波频率; 以及根据第二语音信号的频谱调整每个谐波频带分量的包络和相位。

6. 发明授权

US11842719B2 Sound processing method, sound processing apparatus, and recording medium 有权
公开(公告)号：US11842719B2
公开(公告)日：2023-12-12
申请号：US17027058
申请日：2020-09-21
申请人： YAMAHA CORPORATION
发明人： Merlijn Blaauw , Jordi Bonada , Ryunosuke Daido , Yuji Hisaminato
IPC分类号： G10L13/033 , G10L21/013
CPC分类号： G10L13/0335 , G10L21/013
摘要： A sound processing method obtains note data representative of a note; obtains an audio signal to be processed; specifies, in accordance with the note, an expression sample representative of a sound expression to be imparted to the note and an expression period, of the audio signal, to which the sound expression is to be imparted to the note; and specifies, in accordance with the expression sample and the expression period, a processing parameter relating to an expression imparting processing for imparting the sound expression to a portion corresponding to the expression period in the audio signal. The method then generates a processed audio signal by performing the expression imparting processing in accordance with the expression sample, the expression period, and the processing parameter to the audio signal.

7. 发明授权

US09424831B2 Voice synthesizing having vocalization according to user manipulation 有权
标题翻译：具有根据用户操纵的声音合成
公开(公告)号：US09424831B2
公开(公告)日：2016-08-23
申请号：US14185448
申请日：2014-02-20
申请人： Yamaha Corporation
发明人： Yuji Hisaminato
IPC分类号： G10L13/00 , G10L13/06 , G10L13/08 , G10L13/02 , G10H1/14 , G10H7/00 , G10L13/07 , G10H1/00
CPC分类号： G10L13/02 , G10H1/0091 , G10H1/14 , G10H7/008 , G10H2220/096 , G10H2250/455 , G10L13/07
摘要： A voice synthesizing apparatus includes a manipulation determiner configured to determine a manipulation position which is moved according to a manipulation of a user, and a voice synthesizer configured to generate, in response to an instruction to generate a voice in which a second phoneme follows a first phoneme, a voice signal so that vocalization of the first phoneme starts before the manipulation position reaches a reference position and that vocalization from the first phoneme to the second phoneme is made when the manipulation position reaches the reference position.
摘要翻译：语音合成装置包括：操作确定器，被配置为根据用户的操纵来确定移动的操作位置;以及语音合成器，被配置为响应于生成第二音素跟随第一音素的语音的指令，音素，声音信号，使得第一音素的声音在操作位置到达参考位置之前开始，并且当操作位置到达参考位置时，从第一音素到第二音素的声音被发出。

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