SSR7000: A Synchronized Corpus of Ultrasound Tongue Imaging for End-to-End Silent Speech Recognition.
Naoki KimuraZixiong SuTakaaki SaekiJun RekimotoPublished in: LREC (2022)
Keyphrases
- end to end
- speech recognition
- ultrasound images
- speech synthesis
- vocal tract
- speech signal
- hidden markov models
- automatic speech recognition
- language model
- high resolution
- speech processing
- pattern recognition
- image processing
- speech recognizer
- speaker identification
- congestion control
- speech recognition systems
- computer vision
- speech recognition technology
- speaker independent
- conversational speech
- neural network
- image compression
- noisy environments
- image coding
- bayesian networks
- information retrieval