An investigation on the use of acoustic sub-word units for automatic speech recognition.
Jay G. WilponBiing-Hwang JuangLawrence R. RabinerPublished in: ICASSP (1987)
Keyphrases
- automatic speech recognition
- speech recognizers
- speech recognition
- speech sounds
- speech recognition systems
- acoustic features
- word error rate
- word recognition
- speech segments
- conversational speech
- speech signal
- broadcast news
- speech recognizer
- recognition errors
- hidden markov models
- compound words
- spontaneous speech
- acoustic models
- speech retrieval
- spoken words
- language model
- speaker independent
- handwriting recognition
- noisy environments
- natural language processing
- speech corpus
- speaker verification
- speaker identification
- vocal tract
- pattern recognition
- word level
- spoken document retrieval
- machine learning
- text corpus
- test collection
- image processing
- information retrieval