Forward masking on a generalized logarithmic scale for robust speech recognition.
Yoshihiro ItoHiroshi MatsumotoKazumasa YamamotoPublished in: INTERSPEECH (2000)
Keyphrases
- speech recognition
- noisy environments
- language model
- pattern recognition
- speech processing
- automatic speech recognition
- hidden markov models
- speech signal
- speech recognition technology
- speech recognizer
- speech synthesis
- speaker independent
- speech recognition systems
- speech recognizers
- speech understanding
- image processing
- speaker identification
- neural network
- speech recognition errors
- keyword spotting
- cepstral coefficients
- handwriting recognition
- speaker recognition
- mixture model
- signal processing
- mobile devices
- machine learning
- data mining