Asynchronous, online, GMM-free training of a context dependent acoustic model for speech recognition.
Michiel BacchianiAndrew W. SeniorGeorg HeigoldPublished in: INTERSPEECH (2014)
Keyphrases
- speech recognition
- context dependent
- speaker identification
- wall street journal corpus
- online learning
- isolated word
- speaker recognition
- speech processing
- hidden markov models
- acoustic models
- speech signal
- language model
- gaussian mixture model
- voice activity detection
- low level
- speech synthesis
- speech recognizer
- pattern recognition
- high level
- speech recognizers
- automatic speech recognition
- speech recognition systems
- speaker independent
- speech recognition technology
- speaker dependent
- natural language
- noisy environments
- expectation maximization
- neural network
- speech retrieval
- information retrieval
- mel frequency cepstral coefficients
- probabilistic neural network
- em algorithm