USING NON-PARALLEL VOICE CONVERSION FOR SPEECH CONVERSION MODELS
Number of patents in Portfolio can not be more than 2000
United States of America
Stats
-
N/A
Issued Date -
Mar 20, 2025
app pub date -
Nov 27, 2024
filing date -
Nov 27, 2024
priority date (Note) -
Published
status (Latency Note)
Importance
|
US Family Size
|
Non-US Coverage
|
Abstract
A method includes receiving a set of training utterances each including a non-synthetic speech representation of a corresponding utterance, and for each training utterance, generating a corresponding synthetic speech representation by using a voice conversion model. The non-synthetic speech representation and the synthetic speech representation form a corresponding training utterance pair. At each of a plurality of output steps for each training utterance pair, the method also includes generating, for output by a speech recognition model, a first probability distribution over possible non-synthetic speech recognition hypotheses for the non-synthetic speech representation and a second probability distribution over possible synthetic speech recognition hypotheses for the synthetic speech representation. The method also includes determining a consistent loss term for the corresponding training utterance pair based on the first and second probability distributions and updating parameters of the speech recognition model based on the consistent loss term.
First Claim
Other Claims data not available
Family
| Country | kind | publication No. | Filing Date |
|---|---|---|---|
| WO | A1 | WO2023183010 | Apr 25, 2022 |
| CN | A | CN119054013 | Apr 25, 2022 |
| JP | A | JP2025510710 | Apr 25, 2022 |
| EP | A1 | EP4476718 | Apr 25, 2022 |
| US | B2 | US12190862 | Apr 25, 2022 |
International Classification(s)
- 2024 Application Filing Year
- G10L Class
- 1934 Applications Filed
- 150 Patents Issued To-Date
- 7.76 % Issued To-Date
Cited Art Landscape
Patent Citation Ranking
- 0 Citation Count
- G10L Class
- 0 % this patent is cited more than
- < 1 Age