Deep autoencoders augmented with phone-class feature for reverberant speech recognition.
Masato MimuraShinsuke SakaiTatsuya KawaharaPublished in: ICASSP (2015)
Keyphrases
- speech recognition
- speech signal
- hidden markov models
- language model
- automatic speech recognition
- cepstral coefficients
- pattern recognition
- acoustic models
- speech recognizer
- speech processing
- feature vectors
- speech synthesis
- denoising
- speech recognition systems
- speaker identification
- handwriting recognition
- speech understanding
- linear prediction
- noisy environments
- speech recognition technology
- audio visual speech recognition
- speaker recognition
- keyword spotting
- natural language processing
- speech recognizers
- speaker independent
- speech recognition errors
- isolated word