Joint estimation of confidence and error causes in speech recognition.
Atsunori OgawaAtsushi NakamuraPublished in: Speech Commun. (2012)
Keyphrases
- speech recognition
- joint estimation
- hidden markov models
- automatic speech recognition
- speech synthesis
- language model
- speech signal
- error rate
- speech understanding
- speaker identification
- speech processing
- speech recognition technology
- pattern recognition
- speech recognizers
- speech recognizer
- speaker independent
- noisy environments
- isolated word
- speech recognition systems
- handwriting recognition
- neural network
- speech recognition errors
- non stationary
- speech retrieval
- probabilistic model
- face recognition
- computer vision