Method of training speech recognition model, electronic device and storage medium
Number of patents in Portfolio can not be more than 2000
United States of America
Stats
-
Mar 25, 2025
Grant Date -
Nov 30, 2023
app pub date -
Dec 9, 2022
filing date -
Dec 9, 2022
priority date (Note) -
In Force
status (Latency Note)
Importance
Abstract
A method of training a speech recognition model is provided. The method includes that: speech data of each of a plurality of training samples is inputted into a teacher model and a to-be-trained speech recognition model separately. Additionally, an embedding outputted by the teacher model and encoded data outputted by the to-be-trained speech recognition model are obtained. Furthermore, quantized codebook data is obtained by performing a multi-codebook quantization on the embedding. A loss is calculated based on the encoded data, the quantized codebook data, and text data in the training sample. Moreover, a trained speech recognition model is obtained by stopping training the to-be-trained speech recognition model when the loss is less than or equal to a preset loss threshold and/or trained times is greater than preset trained times.
First Claim
Other Claims data not available
Family
International Classification(s)
- 2022 Application Filing Year
- G10L Class
- 3614 Applications Filed
- 1686 Patents Issued To-Date
- 46.66 % Issued To-Date
Cited Art Landscape
Patent Citation Ranking
- 0 Citation Count
- G10L Class
- 0 % this patent is cited more than
- < 1 Age
Maintenance Fees
| Fee | Large entity fee | small entity fee | micro entity fee | due date |
|---|---|---|---|---|
| 3.5 Year Payment | $1600.00 | $800.00 | $400.00 | Sep 25, 2028 |
| 7.5 Year Payment | $3600.00 | $1800.00 | $900.00 | Sep 25, 2032 |
| 11.5 Year Payment | $7400.00 | $3700.00 | $1850.00 | Sep 25, 2036 |