Language Discrimination Improves Linguistic Learning in Multilingual Speech Models
Imported from official source
Multilingual self-supervised speech models can benefit from sharing information across languages, but under a matched total pretraining data budget they still fall short of monolingual models. …
This version
- Version
- 1 of 1
- Recorded
- October 02, 2026 15:00
- Change
- Initial
- Content hash
de811f9f337fb9b8c00f1fc1872d0b12- All versions
- Revision history