Enhancing distributed speech recognition with back- end speech reconstruction.
Tenkasi RamabadranJeff MeunierMark A. JasiukBill KushnerPublished in: INTERSPEECH (2001)
Keyphrases
- speech recognition
- back end
- speech synthesis
- speech signal
- automatic speech recognition
- speech processing
- language model
- user friendly
- hidden markov models
- speech recognizer
- speech recognition technology
- building blocks
- data management
- noisy environments
- speaker independent
- pattern recognition
- speaker identification
- data types
- cepstral coefficients
- recognition engine
- speech recognition systems
- speaker dependent
- noisy speech
- speech recognizers
- isolated word
- image processing
- spoken language
- vocal tract
- word error rate
- acoustic models