Recognition of speech from live sports coverage using acoustic and language model adaptation.
Yasuo ArikiJun OgataMasakiyo FujimotoKiyoshi TsukadaPublished in: Systems and Computers in Japan (2005)
Keyphrases
- speech sounds
- speech recognition systems
- recognition engine
- speech recognition
- speaker independent
- spoken language
- vowel phonemes
- text to speech
- language acquisition
- recognition rate
- vocal tract
- speech signal
- feature extraction
- text to speech synthesis
- programming language
- english text
- automatic speech recognition systems
- acoustic features
- object recognition
- language learning
- emotional speech
- speech corpus
- environmental sounds
- natural language
- hidden markov models
- digit recognition
- language processing
- acoustic signal
- speech recognizer
- noisy speech
- human activities
- visual speech
- automatic speech recognition
- recognition accuracy
- continuous speech recognition
- character recognition
- text recognition
- human communication
- face recognition
- acoustic models
- prosodic features
- speaker verification
- speaker identification
- noisy environments
- video analysis
- pattern recognition
- activity recognition