Speaker- and Text-Independent Estimation of Articulatory Movements and Phoneme Alignments from Speech.
Tobias WeisePhilipp KlumppKubilay Can DemirPaula Andrea Pérez-ToroMaria SchusterElmar NöthBjörn HeismannAndreas K. MaierSeung Hee YangPublished in: CoRR (2024)
Keyphrases
- speech recognition
- speech synthesis
- vocal tract
- text to speech
- automatic speech recognition
- speech signal
- speaker dependent
- prosodic features
- speaker identification
- automatic speech recognition systems
- hidden markov models
- speech sounds
- language model
- speech recognizer
- speaker independent
- phoneme recognition
- speech recognition systems
- information retrieval
- text to speech synthesis
- noisy environments
- acoustic features
- pattern recognition
- speaker adaptation
- speaker diarization
- synthesized speech
- text data
- pairwise
- keywords
- spontaneous speech
- acoustic models
- english text
- text recognition
- speaker recognition
- speaker verification
- language identification
- text mining
- speech enhancement
- broadcast news
- news video
- natural language
- vowel phonemes