SAMU-XLSR: Semantically-Aligned Multimodal Utterance-Level Cross-Lingual Speech Representation.
Sameer KhuranaAntoine LaurentJames R. GlassPublished in: IEEE J. Sel. Top. Signal Process. (2022)
Keyphrases
- cross lingual
- speech recognition
- multi lingual
- machine translation
- language modeling
- spoken language
- cross lingual information retrieval
- event extraction
- language independent
- language model
- image representation
- cross language
- parallel corpus
- natural language
- query translation
- text classification
- speech signal
- parallel corpora
- bayesian networks