An investigation of subspace modeling for phonetic and speaker variability in automatic speech recognition.
Richard C. RoseShou-Chun YinYun TangPublished in: ICASSP (2011)
Keyphrases
- automatic speech recognition
- speech recognition
- speech sounds
- speech signal
- hidden markov models
- broadcast news
- word error rate
- acoustic models
- conversational speech
- speaker adaptation
- spoken words
- discriminative training
- speech synthesis
- speech segments
- speech recognizer
- word recognition
- noisy environments
- language model
- pattern recognition
- speaker identification
- speech corpus
- speech retrieval
- acoustic features
- speech recognition systems
- recognition errors
- handwriting recognition
- spoken term detection
- vocal tract
- spontaneous speech
- information retrieval systems