Phonetic subspace adaptation for automatic speech recognition.
Sina Hamidi GhalehjeghRichard C. RosePublished in: ICASSP (2013)
Keyphrases
- automatic speech recognition
- speech recognition
- speaker adaptation
- speech signal
- speech sounds
- hidden markov models
- word error rate
- broadcast news
- language model
- spoken words
- speech recognizer
- spoken term detection
- noisy environments
- conversational speech
- pattern recognition
- word recognition
- speaker independent
- acoustic models
- speech synthesis
- recognition errors
- spontaneous speech
- speech retrieval
- speech segments
- maximum likelihood
- feature extraction
- speaker identification
- computer vision
- vocal tract