When the words are not everything: the use of laughter, fillers, back-channel, silence and overlapping speech in phone calls.
Alessandro VinciarelliParaskevi ChatziioannouAnna EspositoPublished in: Frontiers ICT (2015)
Keyphrases
- audio visual
- speech signal
- broadcast news
- speech corpus
- text recognition
- speech recognition
- prosodic features
- spoken term detection
- spoken words
- n gram
- continuous speech recognition
- grapheme to phoneme conversion
- automatic speech recognition
- speech recognition systems
- spoken document retrieval
- spontaneous speech
- recognition errors
- acoustic models
- spectral features
- multi modal
- lexical features
- speech recognition errors
- speaker diarization
- speech synthesis
- multi channel
- multi party
- conversational speech
- speaker identification
- mobile phone
- text to speech
- automatic transcription
- word sense disambiguation
- noisy environments
- spoken language
- communication channels
- speech sounds
- keywords
- word recognition
- out of vocabulary
- genre classification
- vocal tract
- text documents
- wordnet
- bayesian information criterion
- emotion recognition