Fine-Tuned Self-supervised Speech Representations for Language Diarization in Multilingual Code-Switched Speech.
Geoffrey T. FrostEmily MorrisJoshua Jansen van VürenThomas NieslerPublished in: SACAIR (2022)
Keyphrases
- speech recognition
- text to speech
- language acquisition
- spoken language
- fine tuned
- text to speech synthesis
- speech signal
- multi lingual
- audio visual
- english text
- speaker identification
- speech synthesis
- broadcast news
- human communication
- fine tuning
- information retrieval
- emotion recognition
- noisy environments
- source code
- natural language
- language resources
- human language
- recognition engine
- spoken dialog systems
- dialogue system
- domain specific
- comparable corpora
- pattern recognition