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. 发明申请

US20190108830A1 SYSTEMS AND METHODS FOR MULTI-STYLE SPEECH SYNTHESIS 审中-公开
公开(公告)号：US20190108830A1
公开(公告)日：2019-04-11
申请号：US15997602
申请日：2018-06-04
申请人： Nuance Communications, Inc.
发明人： Vincent Pollet
IPC分类号： G10L13/027 , G10L13/08 , G10L13/047 , G10L13/07
摘要： Techniques for performing multi-style speech synthesis. The techniques include using at least one computer hardware processor to perform: obtaining input comprising text and an identification of a desired speaking style to use in rendering the text as speech; identifying a plurality of speech segments for use in rendering the text as speech, the identifying comprising identifying a first speech segment recorded and/or synthesized in a first speaking style that is different from the desired speaking style based at least in part on a measure of similarity between the desired speaking style and the first speaking style; synthesizing speech from the text in the desired speaking style at least in part by using the first speech segment; and outputting the synthesized speech.

2. 发明申请

US20160093289A1 SYSTEMS AND METHODS FOR MULTI-STYLE SPEECH SYNTHESIS 有权
标题翻译：多种语音合成的系统和方法
公开(公告)号：US20160093289A1
公开(公告)日：2016-03-31
申请号：US14499444
申请日：2014-09-29
申请人： Nuance Communications, Inc.
发明人： Vincent Pollet
IPC分类号： G10L13/08 , G10L13/047 , G10L13/027
CPC分类号： G10L13/027 , G10L13/047 , G10L13/07 , G10L13/08
摘要： Techniques for performing multi-style speech synthesis. The techniques include using at least one computer hardware processor to perform: obtaining input comprising text and an identification of a first speaking style to use in rendering the text as speech; identifying a plurality of speech segments for use in rendering the text as speech, the identified plurality of speech segments comprising a first speech segment having the first speaking style and a second speech segment having a second speaking style different from the first speaking style; and rendering the text as speech having the first speaking style, at least in part, by using the identified plurality of speech segments.
摘要翻译：执行多风格语音合成的技术。这些技术包括使用至少一个计算机硬件处理器来执行：获得包括文本的输入和用于将文本呈现为语音的第一说话风格的标识; 识别用于将文本呈现为语音的多个语音片段，所识别的多个语音片段包括具有第一说话风格的第一语音片段和具有不同于第一说话风格的第二说话风格的第二语音片段; 以及至少部分地通过使用所识别的多个语音片段将文本呈现为具有第一说话风格的语音。

3. 发明申请

US20200211529A1 SYSTEMS AND METHODS FOR MULTI-STYLE SPEECH SYNTHESIS 审中-公开
公开(公告)号：US20200211529A1
公开(公告)日：2020-07-02
申请号：US16787916
申请日：2020-02-11
申请人： Nuance Communications, Inc.
发明人： Vincent Pollet
IPC分类号： G10L13/027 , G10L13/047 , G10L13/07 , G10L13/08
摘要： Techniques for performing multi-style speech synthesis. The techniques include using at least one computer hardware processor to perform: obtaining input comprising text and an identification of a desired speaking style to use in rendering the text as speech; identifying a plurality of speech segments for use in rendering the text as speech, the identifying comprising identifying a first speech segment recorded and/or synthesized in a first speaking style that is different from the desired speaking style based at least in part on a measure of similarity between the desired speaking style and the first speaking style; synthesizing speech from the text in the desired speaking style at least in part by using the first speech segment; and outputting the synthesized speech.

4. 发明授权

US09570065B2 Systems and methods for multi-style speech synthesis 有权
标题翻译：多风格语音合成的系统和方法
公开(公告)号：US09570065B2
公开(公告)日：2017-02-14
申请号：US14499444
申请日：2014-09-29
申请人： Nuance Communications, Inc.
发明人： Vincent Pollet
IPC分类号： G10L13/027
CPC分类号： G10L13/027 , G10L13/047 , G10L13/07 , G10L13/08
摘要： Techniques for performing multi-style speech synthesis. The techniques include using at least one computer hardware processor to perform: obtaining input comprising text and an identification of a first speaking style to use in rendering the text as speech; identifying a plurality of speech segments for use in rendering the text as speech, the identified plurality of speech segments comprising a first speech segment having the first speaking style and a second speech segment having a second speaking style different from the first speaking style; and rendering the text as speech having the first speaking style, at least in part, by using the identified plurality of speech segments.
摘要翻译：执行多风格语音合成的技术。这些技术包括使用至少一个计算机硬件处理器来执行：获得包括文本的输入和用于将文本呈现为语音的第一说话风格的标识; 识别用于将文本呈现为语音的多个语音片段，所识别的多个语音片段包括具有第一说话风格的第一语音片段和具有不同于第一说话风格的第二说话风格的第二语音片段; 以及至少部分地通过使用所识别的多个语音片段将文本呈现为具有第一说话风格的语音。

5. 发明授权

US09990915B2 Systems and methods for multi-style speech synthesis 有权
公开(公告)号：US09990915B2
公开(公告)日：2018-06-05
申请号：US15392923
申请日：2016-12-28
申请人： Nuance Communications, Inc.
发明人： Vincent Pollet
IPC分类号： G10L13/027 , G10L13/08 , G10L13/07 , G10L13/047
CPC分类号： G10L13/027 , G10L13/047 , G10L13/07 , G10L13/08
摘要： Techniques for performing multi-style speech synthesis. The techniques include using at least one computer hardware processor to perform: obtaining input comprising text and an identification of a desired speaking style to use in rendering the text as speech; identifying a plurality of speech segments for use in synthesizing the text as speech, the identifying comprising identifying a first speech segment recorded and/or synthesized in a first speaking style that is different from the desired speaking style based at least in part on a measure of similarity between the desired speaking style and the first speaking style; synthesizing speech from the text in the desired speaking style at least in part by using the first speech segment; and outputting the synthesized speech.

6. 发明申请

US20180096677A1 Speech Synthesis 审中-公开
公开(公告)号：US20180096677A1
公开(公告)日：2018-04-05
申请号：US15648022
申请日：2017-07-12
申请人： Nuance Communications, Inc.
发明人： Vincent Pollet , Enrico Zovato
IPC分类号： G10L13/08 , G10L13/02 , G06N3/02 , G06N3/08 , G06F17/30
CPC分类号： G10L13/08 , G06F16/24 , G06N3/02 , G06N3/0445 , G06N3/0454 , G06N3/08 , G10L13/02 , G10L13/04 , G10L13/10
摘要： Aspects of the disclosure are related to synthesizing speech or other audio based on input data. Additionally, aspects of the disclosure are related to using one or more recurrent neural networks. For example, a computing device may receive text input; may determine features based on the text input; may provide the features as input to an recurrent neural network; may determine embedded data from one or more activations of a hidden layer of the recurrent neural network; may determine speech data based on a speech unit search that attempts to select, from a database, speech units based on the embedded data; and may generate speech output based on the speech data.

7. 发明申请

US20170110110A1 SYSTEMS AND METHODS FOR MULTI-STYLE SPEECH SYNTHESIS 有权
公开(公告)号：US20170110110A1
公开(公告)日：2017-04-20
申请号：US15392923
申请日：2016-12-28
申请人： Nuance Communications, Inc.
发明人： Vincent Pollet
IPC分类号： G10L13/027 , G10L13/07 , G10L13/047 , G10L13/08
CPC分类号： G10L13/027 , G10L13/047 , G10L13/07 , G10L13/08
摘要： Techniques for performing multi-style speech synthesis. The techniques include using at least one computer hardware processor to perform: obtaining input comprising text and an identification of a first speaking style to use in rendering the text as speech; identifying a plurality of speech segments for use in rendering the text as speech, the identified plurality of speech segments comprising a first speech segment having the first speaking style and a second speech segment having a second speaking style different from the first speaking style; and rendering the text as speech having the first speaking style, at least in part, by using the identified plurality of speech segments.

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