Exploiting ASR in CASA : ICSI talk, 1997may21
These are the slides I used in a talk I gave at ICSI on 1997may21.
The talk described my
WASPAA'97 paper, Computational Auditory
Scene Analysis using speech recognizer knowledge.
- Exploiting Automatic Speech Recognition (ASR) knowledge in Computational Auditory Scene Analysis (CASA)
- Analyzing sound mixtures
- Integrating ASR into CASA
- Inverting speech representation
- Inverting labels to features
- Inverting RASTA (features->spectra)
- Preliminary results
- Preliminary results 2
- Conclusions
DAn Ellis <dpwe@icsi.berkeley.edu>
International Computer Science Institute, Berkeley CA