利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

140 条记录 (耗时 0.017 秒)

    SPEECH SYNTHESIS
    12.
    发明授权
    SPEECH SYNTHESIS 有权
    语音合成

    公开(公告)号：EP2062252B1

    公开(公告)日：2010-03-03

    申请号：EP08701665.5

    申请日：2008-01-25

    申请人： Nuance Communications, Inc.

    发明人： MÖHLER, Gregor ,  ZEHNPFENNING, Andreas

    IPC分类号： G10L13/06 ,  G10L13/08

    CPC分类号： G10L13/06 ,  G10L13/10

    摘要： Speech is synthesized for a given text by determining a sequence of phonetic components based on the text, determining a sequence of target phonetic elements associated phonetic components, determining a sequence of target event types associated with the phonetic components and determining a sequence of speech units from a plurality of stored speech unit candidates by use of a cost function. The cost function comprises a unit cost, a concatenation cost, and an event type cost for each speech unit in the sequence of speech units. The unit cost of a speech unit is determined with respect to the corresponding target phonetic element, while the concatenation cost of a speech unit is determined with respect to adjacent speech units and the event type cost of each speech unit is determined with respect to the corresponding target event type.

    SYSTEM AND METHOD FOR HYBRID SPEECH SYNTHESIS
    14.
    发明公开
    SYSTEM AND METHOD FOR HYBRID SPEECH SYNTHESIS 有权
    用于混合语音合成的系统和方法

    公开(公告)号：EP2140447A1

    公开(公告)日：2010-01-06

    申请号：EP08742827.2

    申请日：2008-04-14

    申请人： Novaspeech LLC

    发明人： HERTZ, Susan, R. ,  MILLS, Harold, G.

    IPC分类号： G10L13/02 ,  G10L13/06

    CPC分类号： G10L13/06 ,  G10L13/033 ,  G10L25/15

    摘要： A speech synthesis system receives symbolic input describing an utterance to be synthesized. In one embodiment, different portions of the utterance are constructed from different sources, one of which is a speech corpus recorded from a human speaker whose voice is to be modeled. The other sources may include other human speech corpora or speech produced using Rule-Based Speech Synthesis (RBSS). At least some portions of the utterance may be constructed by modifying prototype speech units to produce adapted speech units that are contextually appropriate for the utterance. The system concatenates the adapted speech units with the other speech units to produce a speech waveform. In another embodiment, a speech unit of a speech corpus recorded from a human speaker lacks transitions at one or both of its edges. A transition is synthesized using RBSS and concatenated with the speech unit in producing a speech waveform for the utterance.

    摘要翻译： 语音合成系统接收描述要合成的话语的符号输入。 在一个实施例中，话语的不同部分由不同的来源构成，其中之一是从要说明建模语音的人说话者记录的语音语料库。 其他来源可以包括使用基于规则的语音合成（RBSS）产生的其他人类语音语料库或语音。 可以通过修改原型语音单元以产生上下文适合于话语的适应的语音单元来构建话语的至少一些部分。 该系统将自适应语音单元与其他语音单元连接起来以产生语音波形。 在另一个实施例中，从人类说话者记录的语音语料库的语音单元在其一个或两个边缘处缺少转换。 使用RBSS合成转换并与语音单元连接产生话语的语音波形。

    Voice synthesizing apparatus
    17.
    发明公开
    Voice synthesizing apparatus 有权
    语音合成装置

    公开(公告)号：EP1688911A2

    公开(公告)日：2006-08-09

    申请号：EP06009153.5

    申请日：2002-03-07

    申请人： YAMAHA CORPORATION

    发明人： Hisaminato, Yuji ,  Bonada Sanjaume, Jordi

    IPC分类号： G10L13/06

    CPC分类号： G10L13/06 ,  G10L13/033

    摘要： A voice synthesizing apparatus comprises: means for storing phoneme pieces having a plurality of different pitches for each phoneme represented by a same phoneme symbol; means for reading a phoneme piece by using a pitch as an index; and a voice synthesizer that synthesizes a voice in accordance with the read phoneme piece.

    摘要翻译： 一种语音合成装置包括：用于存储对于由相同音素符号表示的每个音素具有多个不同音高的音素片的装置; 用于通过使用音高作为索引来读取音素片的装置; 以及根据所读取的音素片合成语音的语音合成器。

    Voice synthesis apparatus and method
    18.
    发明公开
    Voice synthesis apparatus and method 审中-公开
    语音合成设备和方法

    公开(公告)号：EP1617408A2

    公开(公告)日：2006-01-18

    申请号：EP05106399.8

    申请日：2005-07-13

    申请人： YAMAHA CORPORATION

    发明人： Kemmochi, Hideki

    IPC分类号： G10L13/06 ,  G10L13/02

    CPC分类号： G10L13/06 ,  G10L13/033 ,  G10L13/04

    摘要： A plurality of voice segments, each including one or more phonemes are acquired in a time-serial manner, in correspondence with desired singing or speaking words. As necessary, a boundary is designated between start and end points of a vowel phoneme included in any one of the acquired voice segments. Voice is synthesized for a region of the vowel phoneme that precedes the designated boundary vowel phoneme, or a region of the vowel phoneme that succeeds the designated boundary in the vowel phoneme. By synthesizing a voice for the region preceding the designated boundary, it is possible to synthesize a voice imitative of a vowel sound that is uttered by a person and then stopped to sound with his or her mouth kept opened. Further, by synthesizing a voice for the region succeeding the designated boundary, it is possible to synthesize a voice imitative of a vowel sound that is started to sound with the mouth opened.

    摘要翻译： 对应于期望的歌唱或说话单词，以时间序列方式获取每个包括一个或多个音素的多个语音片段。 必要时，在所获取的语音片段中的任何一个中包括的元音音素的开始点和结束点之间指定边界。 对于在指定的边界元音音素之前的元音音素的区域或在元音音素中成功指定的边界的元音音素的区域，合成语音。 通过为指定边界之前的区域合成语音，可以合成人类发出的元音声音的模拟声音，然后停止发声，使他的或她的嘴保持打开状态。 此外，通过合成对于指定边界之后的区域的语音，可以合成开口的声音的语音模仿。

    Speech synthesis
    19.
    发明公开
    Speech synthesis 有权
    语音合成

    公开(公告)号：EP1369846A3

    公开(公告)日：2005-04-06

    申请号：EP03253523.9

    申请日：2003-06-04

    申请人： CANON KABUSHIKI KAISHA

    发明人： Yamada, Masayuki, c/o Canon Kabushiki Kaisha ,  Komori, Yasuhiro, c/o Canon Kabushiki Kaisha ,  Fukada, Toshiaki, c/o Canon Kabushiki Kaisha

    IPC分类号： G10L13/06

    CPC分类号： G10L13/06 ,  G10L13/04

    摘要： In a speech synthesis process, micro-segments are cut from acquired waveform data and a window function. The obtained micro-segments are re-arranged to implement a desired prosody, and superposed data is generated by superposing the re-arranged micro-segments, so as to obtain synthetic speech waveform data. A spectrum correction filter is formed based on the acquired waveform data. At least one of the waveform data, micro-segments, and superposed data is corrected using the spectrum correction filter. In this way, "blur" of a speech spectrum due to the window function applied to obtain micro-segments is reduced, and speech synthesis with high sound quality is realized.

    Automatic segmentation in speech synthesis
    20.
    发明公开
    Automatic segmentation in speech synthesis 有权
    语音合成中的自动分割

    公开(公告)号：EP1394769A3

    公开(公告)日：2004-06-09

    申请号：EP03100795.8

    申请日：2003-03-27

    申请人： AT&T Corp.

    发明人： CONKIE, Alistair, D. ,  KIM, Yeon-Jun

    IPC分类号： G10L13/06

    CPC分类号： G10L13/06

    摘要： Systems and methods for automatically segmenting speech inventories. A set of Hidden Markov Models (HMMs) are initialized using bootstrap data. The HMMs are next re-estimated and aligned to produce phone labels. The phone boundaries of the phone labels are then corrected using spectral boundary correction. Optionally, this process of using the spectral-boundary-corrected phone labels as input instead of the bootstrap data is performed iteratively in order to further reduce mismatches between manual labels and phone labels assigned by the HMM approach.

    摘要翻译： 用于自动分割语音库存的系统和方法。 一组隐马尔可夫模型（HMM）使用引导数据进行初始化。 接下来重新估计HMM并调整以产生电话标签。 然后使用频谱边界校正来校正电话标签的电话边界。 可选地，这种使用频谱边界校正的电话标签作为输入而不是自举数据的过程是迭代执行的，以进一步减少由HMM方法分配的手动标签和电话标签之间的不匹配。