Speech synthesis using one or more recurrent neural networks
V Pollet, E Zovato - US Patent 11,069,335, 2021 - Google Patents
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 …
data. Additionally, aspects of the disclosure are related to using one or more recurrent …
Methods and systems for intent detection and slot filling in spoken dialogue systems
P Angkititrakul, R Schumann - US Patent 10,431,207, 2019 - Google Patents
A method for spoken language understanding (SLU) includes generating a first encoded
representation of words from a user based on an output of a recurrent neural network (RNN) …
representation of words from a user based on an output of a recurrent neural network (RNN) …
Text-to-speech processing using input voice characteristic data
RB Chicote, V Aggarwal, AP Breen… - US Patent …, 2022 - Google Patents
During text-to-speech processing, a speech model creates synthesized speech that
corresponds to input data. The speech model may include an encoder for encoding the input …
corresponds to input data. The speech model may include an encoder for encoding the input …
Text-to-speech (TTS) processing with transfer of vocal characteristics
V Klimkov, TR Drugman, A Galkin… - US Patent 11,410,684, 2022 - Google Patents
Audio data from a first, source speaker is received and processed to determine linguistic
units and vocal characteristics corresponding to those linguistic units. The linguistic units …
units and vocal characteristics corresponding to those linguistic units. The linguistic units …
Voice synthesis method, model training method, device and computer device
This application relates to a speech synthesis method and apparatus, a model training
method and apparatus, and a computer device. The method includes: obtaining to-be …
method and apparatus, and a computer device. The method includes: obtaining to-be …
Multilingual speech synthesis and cross-language voice cloning
2020-04-29 Assigned to GOOGLE LLC reassignment GOOGLE LLC ASSIGNMENT OF
ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: CHEN, ZHIFENG …
ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: CHEN, ZHIFENG …
Generating expressive speech audio from text data
(57) ABSTRACT A system for use in video game development to generate expressive
speech audio comprises a user interface config ured to receive user-input text data and a …
speech audio comprises a user interface config ured to receive user-input text data and a …
Matching mouth shape and movement in digital video to alternative audio
TD Stratton, S Lile - US Patent 11,436,780, 2022 - Google Patents
A method for matching mouth shape and movement in digital video to alternative audio
includes deriving a sequence of facial poses including mouth shapes for an actor from a …
includes deriving a sequence of facial poses including mouth shapes for an actor from a …
Systems and methods for neural voice cloning with a few samples
Voice cloning is a highly desired capability for personalized speech interfaces. Neural
network-based speech synthesis has been shown to generate high quality speech for a …
network-based speech synthesis has been shown to generate high quality speech for a …
Method and apparatus with text-to-speech conversion
H Lee - US Patent 11,138,963, 2021 - Google Patents
A processor-implemented text-to-speech method includes determining, using a sub-
encoder, a first feature vector indicating an utterance characteristic of a speaker from feature …
encoder, a first feature vector indicating an utterance characteristic of a speaker from feature …