From cslt Wiki
Revision as of 03:12, 11 October 2013 by Zhaomy
ASR Kernel development
- CD lab files done. Refining the script.
- Training toolkit is cleaned up. Now no alignment is required. Parallel training is done.
- Tried syllable based system instead of phones.
- Collected an online-novel reading.
- Refine the script
- Clean up the online reading.
- Conducting the initial experiment:
- Using 9k dim TF/IDF, compose feature vectors for each query, each answer. Mach the TF/IDF of query+answer to match the TF/IDF of new queries.
- Keep two top-level categories, try to reduce top-level errors:
Add the scores of the Cosine score of the match with queries and answers directly: top-level errors: 2/60 , all errors: 13/60 Use scores of the Cosine score of the match with queries only: top-level errors: 0/60 , all errors: 7/60 speed: 2 query/second
- Reverse index-based fast match (only match with queries)
- code done in python
- CER 7/60, speed 1 query/second
- Use the new data set to verify the program.