Hierarchical spectro-temporal features for robust speech recognition.
Xavier DomontMartin HeckmannFrank JoublinChristian GoerickPublished in: ICASSP (2008)
Keyphrases
- speech recognition
- noisy environments
- language model
- hidden markov models
- pattern recognition
- speech understanding
- speech synthesis
- speech recognizer
- automatic speech recognition
- speech signal
- speech recognition technology
- speaker identification
- speech recognition systems
- speech processing
- handwriting recognition
- speech retrieval
- cepstral coefficients
- speech recognizers
- image processing
- speaker independent
- machine learning
- keyword spotting
- multi modal
- signal processing
- isolated word
- audio visual speech recognition