Neural Speaker Embeddings for Ultrasound-Based Silent Speech Interfaces.
Amin Honarmandi ShandizLászló TóthGábor GosztolyaAlexandra MarkóTamás Gábor CsapóPublished in: Interspeech (2021)
Keyphrases
- speech recognition
- speaker recognition
- audio visual
- automatic speech recognition
- speaker identification
- speaker verification
- speaker dependent
- prosodic features
- speaker diarization
- speech signal
- ultrasound images
- vocal tract
- spoken dialogue systems
- network architecture
- automatic speech recognition systems
- multimodal interfaces
- synthesized speech
- speech synthesis
- speaker independent
- speech sounds
- acoustic features
- text to speech
- multi modal
- automatic transcription
- neural network
- hidden markov models
- speech recognizer
- dimensionality reduction
- language model
- speech recognition systems
- vector space
- dialogue system
- user interface
- hands free
- acoustic models
- gaussian mixture model
- visual information
- emotion recognition
- euclidean space
- broadcast news
- phoneme recognition
- recognition engine
- spoken language
- speaker adaptation
- audio stream
- visual data
- speech segments
- pattern recognition
- artificial neural networks
- visual speech
- noisy environments
- interface design
- multimodal interaction
- low dimensional