Anuj Diwan

According to our database1, Anuj Diwan authored at least 11 papers between 2020 and 2024.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
Textless Speech-to-Speech Translation With Limited Parallel Data.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

2023
Unit-based Speech-to-Speech Translation Without Parallel Data.
CoRR, 2023

Continual Learning for On-Device Speech Recognition Using Disentangled Conformers.
Proceedings of the IEEE International Conference on Acoustics, 2023

When to Use Efficient Self Attention? Profiling Text, Speech and Image Transformer Variants.
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), 2023

2022
Zero-shot Video Moment Retrieval With Off-the-Shelf Models.
Proceedings of the Transfer Learning for Natural Language Processing Workshop, 2022

Why is Winoground Hard? Investigating Failures in Visuolinguistic Compositionality.
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022

2021
Multilingual and code-switching ASR challenges for low resource Indian languages.
CoRR, 2021

Low Resource ASR: The Surprising Effectiveness of High Resource Transliteration.
Proceedings of the 22nd Annual Conference of the International Speech Communication Association, Interspeech 2021, Brno, Czechia, August 30, 2021

MUCS 2021: Multilingual and Code-Switching ASR Challenges for Low Resource Indian Languages.
Proceedings of the 22nd Annual Conference of the International Speech Communication Association, Interspeech 2021, Brno, Czechia, August 30, 2021

Reduce and Reconstruct: ASR for Low-Resource Phonetic Languages.
Proceedings of the 22nd Annual Conference of the International Speech Communication Association, Interspeech 2021, Brno, Czechia, August 30, 2021

2020
Reduce and Reconstruct: Improving Low-resource End-to-end ASR Via Reconstruction Using Reduced Vocabularies.
CoRR, 2020


  Loading...