Multi-Corpus Acoustic-to-Articulatory Speech Inversion.
Nadee SeneviratneGanesh SivaramanCarol Y. Espy-WilsonPublished in: INTERSPEECH (2019)
Keyphrases
- acoustic features
- speech recognition
- vocal tract
- speech signal
- formant frequencies
- speech sounds
- speech recognition systems
- speech synthesis
- spontaneous speech
- prosodic features
- speaker independent
- speech recognizers
- automatic speech recognition
- multi stream
- speech recognizer
- acoustic models
- conversational speech
- visual features
- speaker verification
- noisy speech
- lexical features
- vowel phonemes
- speech processing
- speaker recognition
- mel frequency cepstral coefficients
- music information retrieval
- test set
- spoken language
- noisy environments
- image acquisition
- acoustic signal
- human computer interaction
- spanish language
- hidden markov models