UltraFit: A Speaker-friendly Headset for Ultrasound Recordings in Speech Science.
Lorenzo SpreaficoMichael PucherAnna MatosovaPublished in: INTERSPEECH (2018)
Keyphrases
- audio visual
- acoustic features
- speech recognition
- spontaneous speech
- automatic speech recognition
- speaker recognition
- speaker verification
- multi modal
- prosodic features
- speech signal
- speaker identification
- automatic transcription
- ultrasound images
- speaker dependent
- human machine interaction
- vocal tract
- audio stream
- speech synthesis
- emotion recognition
- visual information
- visual data
- multimedia
- computer science
- visual features
- automatic speech recognition systems
- audio features
- artificial intelligence
- data mining
- speaker diarization
- friendly interface
- science learning
- hidden markov models
- probabilistic neural network
- sound source
- visual speech
- mel frequency cepstral coefficients
- speech recognition systems
- science education
- language model
- phoneme recognition
- information retrieval