Medium-duration modulation cepstral feature for robust speech recognition.
Vikramjit MitraHoracio FrancoMartin GraciarenaDimitra VergyriPublished in: ICASSP (2014)
Keyphrases
- speech recognition
- noisy environments
- hidden markov models
- language model
- speech synthesis
- speech signal
- pattern recognition
- speech processing
- cepstral coefficients
- speech recognizer
- automatic speech recognition
- speech recognition technology
- speech understanding
- keyword spotting
- speech recognition systems
- speaker independent
- speaker identification
- isolated word
- digit recognition
- speech recognition errors
- feature vectors
- neural network
- speech retrieval
- word recognition
- probabilistic model