Automatic speech recognition using acoustic sub-words and no time alignment.
V. Ralph AlgaziKathy L. BrownPublished in: ICASSP (1988)
Keyphrases
- speech recognition systems
- speech recognition
- speech sounds
- text recognition
- fully automatic
- spoken words
- semi automatic
- speech segments
- speech recognition errors
- automatic speech recognition
- speech recognizer
- spoken document retrieval
- speech synthesis
- word level
- word segmentation
- spontaneous speech
- continuous speech recognition
- grapheme to phoneme conversion
- acoustic features
- n gram
- word alignment
- lexical features
- text to speech
- prosodic features
- word recognition
- acoustic signal
- dynamic time warping
- audio stream
- word sense disambiguation
- speech recognizers
- language model
- hidden markov models