Short- and long-term dynamic features for robust speech recognition.
Takashi FukudaOsamu IchikawaMasafumi NishimuraPublished in: INTERSPEECH (2008)
Keyphrases
- speech recognition
- short and long term
- noisy environments
- hidden markov models
- language model
- speech signal
- speech recognizer
- speech synthesis
- automatic speech recognition
- short term
- speech processing
- long term
- pattern recognition
- speech recognition technology
- speech recognition systems
- isolated word
- speaker independent
- speaker identification
- non stationary
- acoustic models
- speech retrieval
- image processing
- computer vision