Lost speech reconstruction method using speech recognition based on missing feature theory and HMM-based speech synthesis.
Shingo KuroiwaSatoru TsugeFuji RenPublished in: INTERSPEECH (2006)
Keyphrases
- speech synthesis
- speech recognition
- reconstruction method
- hidden markov models
- image reconstruction
- speech signal
- vocal tract
- language model
- text to speech
- speech processing
- automatic speech recognition
- speech recognizer
- speech recognition technology
- speech recognition systems
- cepstral coefficients
- keyword spotting
- pattern recognition
- handwriting recognition
- surface reconstruction
- noisy environments
- word error rate
- speaker independent
- speaker dependent
- neural network
- speech recognizers
- speaker identification
- non stationary
- image data