Robustness to speaker position in distant-talking automatic speech recognition.
Randy GomezKeisuke NakamuraKazuhiro NakadaiPublished in: ICASSP (2013)
Keyphrases
- automatic speech recognition
- speech recognition
- speech signal
- hidden markov models
- word error rate
- broadcast news
- conversational speech
- noisy environments
- spoken words
- acoustic features
- word recognition
- spontaneous speech
- recognition errors
- speech retrieval
- speech recognizer
- information retrieval
- speech segments
- multi modal
- machine learning
- speech sounds
- neural network