2 papers
cs.LG2023
Improving Spoken Language Identification with Map-Mix
Shangeth Rajaa, Kriti Anandan, Swaraj Dalmia +2
The pre-trained multi-lingual XLSR model generalizes well for language identification after fine-tuning on unseen languages. However, the performance significantly degrades when th…
cs.CL2022
Skit-S2I: An Indian Accented Speech to Intent dataset
Shangeth Rajaa, Swaraj Dalmia, Kumarmanas Nethil
Conventional conversation assistants extract text transcripts from the speech signal using automatic speech recognition (ASR) and then predict intent from the transcriptions. Using…