SAMU-XLSR: Semantically-Aligned Multimodal Utterance-level Cross-Lingual Speech Representation.
Sameer KhuranaAntoine LaurentJames R. GlassPublished in: CoRR (2022)
Keyphrases
- cross lingual
- multi lingual
- speech recognition
- machine translation
- spoken language
- language independent
- cross language
- language modeling
- cross lingual information retrieval
- event extraction
- text classification
- parallel corpus
- image representation
- natural language
- training data
- broadcast news
- parallel corpora
- multimedia
- out of vocabulary
- information retrieval