Fusion of standard and alternative acoustic sensors for robust automatic speech recognition.
Panikos HeracleousJani EvenCarlos Toshinori IshiTakahiro MiyashitaNorihiro HagitaPublished in: ICASSP (2012)
Keyphrases
- automatic speech recognition
- acoustic features
- speech recognition
- noisy environments
- speech sounds
- data fusion
- speech recognizers
- multi sensor
- speech signal
- word error rate
- hidden markov models
- speech segments
- sensor fusion
- acoustic models
- speech retrieval
- word recognition
- conversational speech
- spoken words
- spontaneous speech
- speech recognition systems
- formant frequencies
- speech corpus
- multi modal
- wavelet transform
- image processing