Pre-training apparatus and method for speech recognition
Number of patents in Portfolio can not be more than 2000
United States of America Patent
Stats
-
Jan 23, 2018
Issued Date -
N/A
app pub date -
Jul 12, 2016
filing date -
Mar 18, 2016
priority date (Note) -
In Force
status (Latency Note)
Importance
Abstract
A pre-training apparatus and method for recognition speech, which initialize, by layers, a deep neural network to correct a node connection weight. The pre-training apparatus for speech recognition includes an input unit configured to receive speech data, a model generation unit configured to initialize a connection weight of a deep neural network, based on the speech data, and an output unit configured to output information about the connection weight. In order for a state of a phoneme unit corresponding to the speech data to be output, the model generation unit trains the connection weight by piling a plurality of hidden layers according to a determined structure of the deep neural network, applies an output layer to a certain layer between the plurality of hidden layers to correct the trained connection weight in each of the plurality of hidden layers, thereby initializing the connection weight.
First Claim
Other Claims data not available
Family
International Classification(s)
- 2016 Application Filing Year
- G06N Class
- 4474 Applications Filed
- 2715 Patents Issued To-Date
- 60.69 % Issued To-Date
Cited Art Landscape
Patent Citation Ranking
- 2 Citation Count
- G06N Class
- 26.34 % this patent is cited more than
- 7 Age
Maintenance Fees
| Fee | Large entity fee | small entity fee | micro entity fee | due date |
|---|---|---|---|---|
| 7.5 Year Payment | $3600.00 | $1800.00 | $900.00 | Jul 23, 2025 |
| 11.5 Year Payment | $7400.00 | $3700.00 | $1850.00 | Jul 23, 2029 |
