Speaker Conditioned Acoustic-to-Articulatory Inversion Using x-Vectors.
Aravind IllaPrasanta Kumar GhoshPublished in: INTERSPEECH (2020)
Keyphrases
- acoustic features
- speech recognition
- speaker verification
- vocal tract
- speech sounds
- prosodic features
- speech synthesis
- automatic speech recognition
- speaker independent
- speech recognition systems
- speech signal
- acoustic models
- visual features
- music information retrieval
- mel frequency cepstral coefficients
- speaker recognition
- vowel phonemes
- vector space
- audio features
- speaker dependent
- noisy environments
- feature vectors
- speaker diarization
- audio visual
- laplace transform
- formant frequencies
- text to speech
- speaker identification
- image reconstruction
- probabilistic model
- low level
- audio stream
- pattern recognition