公开(公告)号：US20180268806A1

公开(公告)日：2018-09-20

申请号：US15649311

申请日：2017-07-13

Applicant: Google Inc.

Inventor： Byung Ha Chun ,  Javier Gonzalvo ,  Chun-an Chan ,  Ioannis Agiomyrgiannakis ,  Vincent Ping Leung Wan ,  Robert Andrew James Clark ,  Jakub Vit

IPC: G10L13/047 ,  G10L13/06 ,  G10L19/00 ,  G10L25/30 ,  G10L13/027

CPC classification number: G10L13/047 ,  G10L13/027 ,  G10L13/06 ,  G10L13/08 ,  G10L19/0019 ,  G10L25/30

Abstract: Methods, systems, and computer-readable media for text-to-speech synthesis using an autoencoder. In some implementations, data indicating a text for text-to-speech synthesis is obtained. Data indicating a linguistic unit of the text is provided as input to an encoder. The encoder is configured to output speech unit representations indicative of acoustic characteristics based on linguistic information. A speech unit representation that the encoder outputs is received. A speech unit is selected to represent the linguistic unit, the speech unit being selected from among a collection of speech units based on the speech unit representation output by the encoder. Audio data for a synthesized utterance of the text that includes the selected speech unit is provided.

公开(公告)号：US09922641B1

公开(公告)日：2018-03-20

申请号：US13665390

申请日：2012-10-31

Applicant: Google Inc.

Inventor： Byung Ha Chun

IPC: G10L13/00 ,  G10L13/06 ,  G10L15/06 ,  G10L15/07 ,  G10L15/02 ,  G10L21/013

CPC classification number: G10L15/063 ,  G10L15/02 ,  G10L15/07 ,  G10L2015/025 ,  G10L2021/0135

Abstract: The subject matter of the disclosure is embodied in a method that includes receiving input speech data from a speaker in a first language, and estimating, based on a universal speech model, a speaker transform representing speaker characteristics associated with the input speech data. The method also includes accessing a speaker-independent speech model for generating speech data in a second language that is different from the first language. The method further includes modifying the speaker-independent speech model using the speaker transform to obtain a speaker-specific speech model, and generating speech data in the second language using the speaker-specific speech model.