[go: up one dir, main page]

Follow
Kushal Lakhotia
Title
Cited by
Cited by
Year
The llama 3 herd of models
A Dubey, A Jauhri, A Pandey, A Kadian, A Al-Dahle, A Letman, A Mathur, ...
arXiv e-prints, arXiv: 2407.21783, 2024
12323*2024
Hubert: Self-supervised speech representation learning by masked prediction of hidden units
WN Hsu, B Bolte, YHH Tsai, K Lakhotia, R Salakhutdinov, A Mohamed
IEEE/ACM transactions on audio, speech, and language processing 29, 3451-3460, 2021
46942021
Superb: Speech processing universal performance benchmark
S Yang, PH Chi, YS Chuang, CIJ Lai, K Lakhotia, YY Lin, AT Liu, J Shi, ...
arXiv preprint arXiv:2105.01051, 2021
12032021
XLS-R: Self-supervised cross-lingual speech representation learning at scale
A Babu, C Wang, A Tjandra, K Lakhotia, Q Xu, N Goyal, K Singh, ...
arXiv preprint arXiv:2111.09296, 2021
10602021
Learning audio-visual speech representation by masked multimodal cluster prediction
B Shi, WN Hsu, K Lakhotia, A Mohamed
arXiv preprint arXiv:2201.02184, 2022
4912022
On generative spoken language modeling from raw audio
K Lakhotia, E Kharitonov, WN Hsu, Y Adi, A Polyak, B Bolte, TA Nguyen, ...
Transactions of the Association for Computational Linguistics 9, 1336-1354, 2021
4712021
Speech resynthesis from discrete disentangled self-supervised representations
A Polyak, Y Adi, J Copet, E Kharitonov, K Lakhotia, WN Hsu, A Mohamed, ...
arXiv preprint arXiv:2104.00355, 2021
4062021
Text-free prosody-aware generative spoken language modeling
E Kharitonov, A Lee, A Polyak, Y Adi, J Copet, K Lakhotia, TA Nguyen, ...
Proceedings of the 60th Annual Meeting of the Association for Computational …, 2022
1612022
SUPERB-SG: Enhanced speech processing universal performance benchmark for semantic and generative capabilities
HS Tsai, HJ Chang, WC Huang, Z Huang, K Lakhotia, S Yang, S Dong, ...
Proceedings of the 60th Annual Meeting of the Association for Computational …, 2022
1222022
Salient phrase aware dense retrieval: can a dense retriever imitate a sparse one?
X Chen, K Lakhotia, B Oguz, A Gupta, P Lewis, S Peshterliev, Y Mehdad, ...
Findings of the Association for Computational Linguistics: EMNLP 2022, 250-262, 2022
782022
Domain-matched pre-training tasks for dense retrieval
B Oguz, K Lakhotia, A Gupta, P Lewis, V Karpukhin, A Piktus, X Chen, ...
Findings of the Association for Computational Linguistics: NAACL 2022, 1524-1534, 2022
662022
A large-scale evaluation of speech foundation models
S Yang, HJ Chang, Z Huang, AT Liu, CI Lai, H Wu, J Shi, X Chang, ...
IEEE/ACM Transactions on Audio, Speech, and Language Processing 32, 2884-2899, 2024
622024
K.-t. Lee, D
S Yang, PH Chi, YS Chuang, CIJ Lai, K Lakhotia, YY Lin, AT Liu, J Shi, ...
R. Liu, Z. Huang, S. Dong, S.-W. Li, S. Watanabe, A. Mohamed, and H.-y. Lee …, 2021
452021
Fid-ex: Improving sequence-to-sequence models for extractive rationale generation
K Lakhotia, B Paranjape, A Ghoshal, S Yih, Y Mehdad, S Iyer
Proceedings of the 2021 Conference on Empirical Methods in Natural Language …, 2021
342021
textless-lib: A library for textless spoken language processing
E Kharitonov, J Copet, K Lakhotia, TA Nguyen, P Tomasello, A Lee, ...
Proceedings of the 2022 Conference of the North American Chapter of the …, 2022
262022
Pytext: A seamless path from nlp research to production
A Aly, K Lakhotia, S Zhao, M Mohit, B Oguz, A Arora, S Gupta, C Dewan, ...
arXiv preprint arXiv:1812.08729, 2018
172018
Quaser: Question answering with scalable extractive rationalization
A Ghoshal, S Iyer, B Paranjape, K Lakhotia, SW Yih, Y Mehdad
Proceedings of the 45th International ACM SIGIR Conference on Research and …, 2022
82022
HuBERT: self-supervised speech representation learning by masked prediction of hidden units. IEEE/ACM Tran Audio, Speech, Lang Process
WN Hsu, B Bolte, YHH Tsai, K Lakhotia, R Salakhutdinov, A Mohamed
22021
Virtual Assistant That Provides Answers Based On Past Conversations
K Lakhotia, D Savenkov, S Gupta
2023
Zadání diplomové práce
WN Hsu, B Bolte, YHH Tsai, K Lakhotia, R Salakhutdinov, A Mohamed, ...
The system can't perform the operation now. Try again later.
Articles 1–20