Autoencoder-Based Articulatory-to-Acoustic Mapping for Ultrasound Silent Speech Interfaces.
Gábor GosztolyaÁdám PintérLászló TóthTamás GrószAlexandra MarkóTamás Gábor CsapóPublished in: CoRR (2019)
Keyphrases
- acoustic features
- speech recognition
- speech signal
- formant frequencies
- vocal tract
- speech recognition systems
- speech sounds
- speech synthesis
- automatic speech recognition
- speaker independent
- speaker verification
- prosodic features
- speech recognizers
- multi stream
- acoustic models
- noisy environments
- ultrasound images
- noisy speech
- emotional speech
- vowel phonemes
- music information retrieval
- visual features
- speech recognizer
- multimodal interfaces
- text to speech
- hands free
- spoken dialogue systems
- sound source
- language model
- acoustic signal
- audio stream
- underwater acoustic
- speaker identification
- speech segments
- audio visual