END-TO-END TEXT-TO-SPEECH CONVERSION

Title:

END-TO-END TEXT-TO-SPEECH CONVERSION

Document Type and Number:

WIPO Patent Application WO/2018/183650

Kind Code:

A3

Abstract:

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating speech from text. One of the systems includes one or more computers and one or more storage devices storing instructions that when executed by one or more computers cause the one or more computers to implement: a sequence-to-sequence recurrent neural network configured to: receive a sequence of characters in a particular natural language, and process the sequence of characters to generate a spectrogram of a verbal utterance of the sequence of characters in the particular natural language; and a subsystem configured to: receive the sequence of characters in the particular natural language, and provide the sequence of characters as input to the sequence-to-sequence recurrent neural network to obtain as output the spectrogram of the verbal utterance of the sequence of characters in the particular natural language.

More Like This:

JP2022539912	Electronic device backplane appearance defect inspection method and apparatus
WO/2023/283914	Y-NET-BASED DIGITAL WATERMARKING METHOD, APPARATUS, AND SYSTEM
JP7055211	Data processing system and data processing method

Inventors:

BENGIO SAMUEL (US)
WANG YUXUAN (US)
YANG ZONGHENG (US)
CHEN ZHIFENG (US)
WU YONGHUI (US)
AGIOMYRGIANNAKIS IOANNIS (GB)
WEISS RON J (US)
JAITLY NAVDEEP (US)
RIFKIN RYAN M (US)
CLARK ROBERT ANDREW JAMES (GB)
LE QUOC V (US)
RYAN RUSSELL J (US)
XIAO YING (US)

Application Number:

PCT/US2018/025101

Publication Date:

November 08, 2018

Filing Date:

March 29, 2018

Export Citation:

Click for automatic bibliography generation Help

Assignee:

GOOGLE LLC (US)

International Classes:

G06N3/08; G10L13/04; G10L15/16

Foreign References:

EP2953065A2

2015-12-09

Other References:

JOSE SOTELO ET AL: "Workshop track -ICLR 2017 CHAR2WAV: END-TO-END SPEECH SYNTHESIS", 10 March 2017 (2017-03-10), XP055481275, Retrieved from the Internet [retrieved on 20180605]
AARON VAN DEN OORD ET AL: "WaveNet: A Generative Model for Raw Audio", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 12 September 2016 (2016-09-12), XP080725972

Attorney, Agent or Firm:

PORTNOV, Michael (US)

Download PDF:

View/Download PDF PDF Help

Previous Patent: PROCESS FOR THE PREPARATION OF 6-(CYCLOPROPANEAMIDO)-4-((2-METHOXY-3-(1-METHYL-1H-1,2,4-TRIAZOL-3-YL...

Next Patent: ABSORBENT ARTICLE WITH AN EXUDATE MANAGEMENT LAYER