Speech recognition using sub-word units dependent on phonetic contexts of both training and recognition vocabularies.
Hiroaki HattoriEiko YamadaPublished in: ICSLP (1996)
Keyphrases
- speech recognition
- speech recognition systems
- speech sounds
- speaker independent
- speech recognizer
- acoustic models
- spoken document retrieval
- spoken term detection
- word recognition
- recognition engine
- automatic speech recognition
- speech signal
- keyword spotting
- speech corpus
- broadcast news
- hidden markov models
- automatic transcription
- speaker dependent
- spoken language
- vocal tract
- recognition rate
- word level
- hearing impaired
- spoken words
- pattern recognition
- numeral strings
- word error rate
- spoken documents
- spontaneous speech
- language model
- digit recognition
- prosodic features
- handwriting recognition
- noisy environments
- lexical features
- handwritten words
- speech synthesis
- discriminative training
- english text
- object recognition
- speaker identification
- automatic speech recognition systems
- n gram
- feature extraction
- cursive handwriting
- speaker adaptation
- text input
- probabilistic model
- word spotting
- text to speech
- cross language
- recognition algorithm