CENSREC-1-AV: an audio-visual corpus for noisy bimodal speech recognition.
Satoshi TamuraChiyomi MiyajimaNorihide KitaokaTakeshi YamadaSatoru TsugeTetsuya TakiguchiKazumasa YamamotoTakanobu NishiuraMasato NakayamaYuki DendaMasakiyo FujimotoShigeki MatsudaTetsuji OgawaShingo KuroiwaKazuya TakedaSatoshi NakamuraPublished in: AVSP (2010)
Keyphrases
- audio visual
- speech recognition
- noisy environments
- audio visual speech recognition
- multi modal
- multi stream
- visual information
- hidden markov models
- visual data
- language model
- multimedia
- speech signal
- digit recognition
- pattern recognition
- emotion recognition
- automatic speech recognition
- speaker verification
- speech recognition systems
- search engine
- image features
- speaker identification
- visual features
- text data
- audio features
- high level