利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

8 条记录 (耗时 0.01 秒)

    VOICE SYNTHESIS
    1.
    发明授权
    VOICE SYNTHESIS 有权

    公开(公告)号：EP3065130B1

    公开(公告)日：2018-08-29

    申请号：EP16158430.5

    申请日：2016-03-03

    申请人： YAMAHA CORPORATION

    发明人： SAINO, Keijiro ,  BONADA, Jordi ,  BLAAUW, Merlijn

    IPC分类号： G10H1/00 ,  G10L13/033

    CPC分类号： G10L13/0335 ,  G10H1/0066 ,  G10H2210/066 ,  G10H2210/331 ,  G10H2250/455 ,  G10L13/047 ,  G10L13/06

    摘要： A voice synthesis method for generating a voice signal through connection of a phonetic piece extracted from a reference voice, includes selecting, by a piece selection unit, the phonetic piece sequentially; setting, by a pitch setting unit, a pitch transition in which a fluctuation of an observed pitch of the phonetic piece is reflected based on a degree corresponding to a difference value between a reference pitch being a reference of sound generation of the reference voice and the observed pitch of the phonetic piece selected by the piece selection unit; and generating, by a voice synthesis unit, the voice signal by adjusting a pitch of the phonetic piece selected by the piece selection unit based on the pitch transition generated by the pitch setting unit.

    PITCH CONVERTING APPARATUS
    2.
    发明授权
    PITCH CONVERTING APPARATUS 有权
    俯仰转换装置

    公开(公告)号：EP1806740B1

    公开(公告)日：2011-06-29

    申请号：EP05800146.2

    申请日：2005-10-27

    申请人： YAMAHA CORPORATION

    发明人： FUJISHIMA, Takuya, Yamaha Corporation ,  BONADA, Jordi

    IPC分类号： G10L21/04 ,  G10H1/00

    CPC分类号： G10H7/002 ,  G10H2210/331 ,  G10H2250/235 ,  G10H2250/621 ,  G10L21/003 ,  G10L21/013 ,  G10L21/04

    摘要： A pitch converting apparatus detects peak spectra (P1,P2) from the amplitude spectrum of an input sound. The pitch converting apparatus compresses or decompresses an amplitude spectrum distribution (AM1) of a first frequency range (A1) including a first frequency (f1) of the peak spectrum (P1) by use of a pitch conversion ratio, which is to maintain the shape of the amplitude spectrum distribution (AM1), to obtain an amplitude spectrum distribution (AM10) of a first frequency range (A10) as pitch converted. The pitch converting apparatus similarly compresses or decompresses an amplitude spectrum distribution (AM2) in the vicinity of the peakspectrum (P2) to obtain an amplitude spectrum distribution (AM20). The pitch converting apparatus compresses or decompresses an amplitude spectrum of an intermediate frequency range (A3) between the peak spectra (P1,P2) by use of a predetermined pitch conversion ratio in accordance with the frequencies of the amplitude spectra, thereby performing a pitch conversion.

    摘要翻译： 音调转换装置从输入声音的振幅谱中检测峰值频谱（P1，P2）。 音调转换装置通过使用音调转换比率来压缩或解压缩包括峰值频谱（P1）的第一频率（f1）的第一频率范围（A1）的振幅谱分布（AM1） （AM1），以获得作为音调转换的第一频率范围（A10）的振幅谱分布（AM10）。 类似地，音调转换设备压缩或解压缩在峰谱（P2）附近的幅度谱分布（AM2）以获得幅度谱分布（AM20）。 音调转换装置根据幅度谱的频率通过使用预定音调转换比来压缩或解压缩峰值频谱（P1，P2）之间的中频范围（A3）的幅度谱，由此执行音调转换 。

    PITCH CONVERTING APPARATUS
    3.
    发明公开
    PITCH CONVERTING APPARATUS 有权
    俯仰转换装置

    公开(公告)号：EP1806740A1

    公开(公告)日：2007-07-11

    申请号：EP05800146.2

    申请日：2005-10-27

    申请人： YAMAHA CORPORATION

    发明人： FUJISHIMA, Takuya, Yamaha Corporation ,  BONADA, Jordi

    IPC分类号： G10L21/04 ,  G10H1/00

    CPC分类号： G10H7/002 ,  G10H2210/331 ,  G10H2250/235 ,  G10H2250/621 ,  G10L21/003 ,  G10L21/013 ,  G10L21/04

    摘要： A pitch shifting apparatus detects peak spectra P1 and P2 from amplitude spectra of inputs sound. The pitch shifting apparatus compresses or expands an amplitude spectrum distribution AM1 in a first frequency region A1 including a first frequency f1 of the peak spectrum P1 using a pitch shift ratio which keeps its shape to obtain an amplitude spectrum distribution AM10 for a pitch-shifted first frequency region A10. The pitch shifting apparatus similarly compresses or expands an amplitude spectrum distribution AM2 adjacent to the peak spectrum P2 to obtain an amplitude spectrum distribution AM20. The pitch shifting apparatus performs pitch shifting by compressing or expanding amplitude spectra in an intermediate frequency region A3 between the peak spectra P1 and P2 at a given pitch shift ratio in response to the each amplitude spectrum.

    摘要翻译： 音调移动设备从输入声音的振幅谱中检测峰值谱P1和P2。 音调移位装置使用保持其形状的音调偏移比率来压缩或扩展包括峰值频谱P1的第一频率f1的第一频率区域A1中的振幅频谱分布AM1，以获得用于音调偏移的第一频率的振幅频谱分布AM10 频率区域A10。 类似地，音调移位装置压缩或扩展与峰值频谱P2相邻的振幅频谱分布AM2，以获得振幅频谱分布AM20。 该音调移位装置响应于每个振幅谱，通过在给定音调移位比率的峰值频谱P1和P2之间的中频区域A3中压缩或扩展振幅频谱来执行音调移位。

    INFORMATION PROCESSING METHOD AND INFORMATION PROCESSING SYSTEM
    4.
    发明公开
    INFORMATION PROCESSING METHOD AND INFORMATION PROCESSING SYSTEM 审中-公开

    公开(公告)号：EP3879524A1

    公开(公告)日：2021-09-15

    申请号：EP19882179.5

    申请日：2019-11-06

    申请人： YAMAHA CORPORATION

    发明人： DAIDO, Ryunosuke ,  BLAAUW, Merlijn ,  BONADA, Jordi

    IPC分类号： G10L13/00 ,  G10L13/033 ,  G10L13/047

    摘要： An information processing system includes a synthesis processor configured to input a piece of sound source data representative of a sound source, style data representative of a performance style, and a piece of synthesis data representative of sounding conditions into a synthesis model generated by machine learning, and generate, using the synthesis model, feature data representative of acoustic features of a target sound of the sound source to be generated in the performance style and according to the sounding conditions.

    VOICE SYNTHESIS
    5.
    发明公开
    VOICE SYNTHESIS 有权
    SPRACHSYNTHESE

    公开(公告)号：EP3065130A1

    公开(公告)日：2016-09-07

    申请号：EP16158430.5

    申请日：2016-03-03

    申请人： YAMAHA CORPORATION

    发明人： SAINO, Keijiro ,  BONADA, Jordi ,  BLAAUW, Merlijn

    IPC分类号： G10L13/033

    CPC分类号： G10L13/0335 ,  G10H1/0066 ,  G10H2210/066 ,  G10H2210/331 ,  G10H2250/455 ,  G10L13/047 ,  G10L13/06

    摘要： A voice synthesis method for generating a voice signal through connection of a phonetic piece extracted from a reference voice, includes selecting, by a piece selection unit, the phonetic piece sequentially; setting, by a pitch setting unit, a pitch transition in which a fluctuation of an observed pitch of the phonetic piece is reflected based on a degree corresponding to a difference value between a reference pitch being a reference of sound generation of the reference voice and the observed pitch of the phonetic piece selected by the piece selection unit; and generating, by a voice synthesis unit, the voice signal by adjusting a pitch of the phonetic piece selected by the piece selection unit based on the pitch transition generated by the pitch setting unit.

    摘要翻译： 一种语音合成方法，用于通过连接从参考语音提取的语音片段来生成语音信号，包括由片选择单元依次选择语音片段; 通过音高设定单元，基于对应于作为参考语音的声音产生的参考音调的参考音调之间的差值的程度来反映音标的观察音高的波动的音调转变， 由片选择单元选择的语音片的观察间距; 以及由语音合成单元通过基于音调设置单元产生的音调转换来调整由片选择单元选择的语音片段的节距来产生语音信号。