Binaural Cues for Fragment-Based Speech Recognition in Reverberant Multisource Environments.
Ning MaJon BarkerHeidi ChristensenPhil D. GreenPublished in: INTERSPEECH (2011)
Keyphrases
- speech recognition
- multi source
- speech signal
- sound source
- automatic speech recognition
- information fusion
- data fusion
- speech processing
- language model
- hidden markov models
- speech synthesis
- multiple sources
- pattern recognition
- noisy environments
- speech recognition technology
- speaker identification
- speech recognizer
- speech recognition systems
- data integration
- speaker independent
- information retrieval
- data sources
- data sets
- isolated word
- speech retrieval
- community detection
- data mining