Acoustic-to-articulatory Inversion based on Speech Decomposition and Auxiliary Feature.
Jianrong WangJinyu LiuLongxuan ZhaoShanyu WangRuiguo YuLi LiuPublished in: CoRR (2022)
Keyphrases
- acoustic features
- speech recognition
- vocal tract
- speech signal
- speech recognition systems
- formant frequencies
- speech sounds
- speech synthesis
- automatic speech recognition
- vowel phonemes
- prosodic features
- speaker identification
- speaker verification
- visual features
- feature vectors
- mel frequency cepstral coefficients
- source localization
- speaker independent
- acoustic models
- speech recognizers
- multi stream
- speech recognizer
- image reconstruction
- underwater vehicles
- decomposition algorithm
- linear prediction
- decomposition method
- audio visual
- language model
- image features