The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Mar. 07, 2023

Filed:

May. 27, 2022
Applicant:

Microsoft Technology Licensing, Llc, Redmond, WA (US);

Inventors:

Shifeng Pan, Beijing, CN;

Lei He, Beijing, CN;

Yulin Li, Beijing, CN;

Sheng Zhao, Beijing, CN;

Chunling Ma, Beijing, CN;

Assignee:
Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G10L 13/10 (2013.01); G10L 15/06 (2013.01); G10L 21/013 (2013.01); G10L 15/18 (2013.01); G10L 15/187 (2013.01); G10L 25/18 (2013.01); G10L 25/30 (2013.01); G10L 25/63 (2013.01);
U.S. Cl.
CPC ...
G10L 15/063 (2013.01); G10L 13/10 (2013.01); G10L 15/1807 (2013.01); G10L 15/187 (2013.01); G10L 25/18 (2013.01); G10L 25/30 (2013.01); G10L 25/63 (2013.01); G10L 2021/0135 (2013.01);
Abstract

Systems are configured for generating spectrogram data characterized by a voice timbre of a target speaker and a prosody style of source speaker by converting a waveform of source speaker data to phonetic posterior gram (PPG) data, extracting additional prosody features from the source speaker data, and generating a spectrogram based on the PPG data and the extracted prosody features. The systems are configured to utilize/train a machine learning model for generating spectrogram data and for training a neural text-to-speech model with the generated spectrogram data.


Find Patent Forward Citations

Loading…