Прати
Preethi Jyothi
Preethi Jyothi
Associate Professor of Computer Science and Engineering, Indian Institute of Technology Bombay
Верификована је имејл адреса на cse.iitb.ac.in
Наслов
Навело
Навело
Година
Generalizing across domains via cross-gradient training
S Shankar, V Piratla, S Chakrabarti, S Chaudhuri, P Jyothi, S Sarawagi
arXiv preprint arXiv:1804.10745, 2018
6172018
Improved Accented Speech Recognition Using Accent Embeddings and Multi-task Learning.
A Jain, M Upreti, P Jyothi
Interspeech, 2454-2458, 2018
1342018
Multilingual and code-switching ASR challenges for low resource Indian languages
A Diwan, R Vaideeswaran, S Shah, A Singh, S Raghavan, S Khare, ...
arXiv preprint arXiv:2104.00235, 2021
932021
Cross-lingual training for automatic question generation
V Kumar, N Joshi, A Mukherjee, G Ramakrishnan, P Jyothi
arXiv preprint arXiv:1906.02525, 2019
692019
Conditional random fields in speech, audio, and language processing
E Fosler-Lussier, Y He, P Jyothi, R Prabhavalkar
Proceedings of the IEEE 101 (5), 1054-1075, 2013
492013
From machine translation to code-switching: Generating high-quality code-switched text
I Tarunesh, S Kumar, P Jyothi
arXiv preprint arXiv:2107.06483, 2021
472021
Code-switched Language Models Using Dual RNNs and Same-Source Pretraining
S Garg, T Parekh, P Jyothi
Proceedings of the 2018 Conference on Empirical Methods in Natural Language …, 2018
472018
Low Resource ASR: The Surprising Effectiveness of High Resource Transliteration.
S Khare, AR Mittal, A Diwan, S Sarawagi, P Jyothi, S Bharadwaj
Interspeech, 1529-1533, 2021
452021
Acquiring speech transcriptions using mismatched crowdsourcing
P Jyothi, M Hasegawa-Johnson
Proceedings of the AAAI Conference On Artificial Intelligence 29 (1), 2015
442015
ASR for under-resourced languages from probabilistic transcription
MA Hasegawa-Johnson, P Jyothi, D McCloy, M Mirbagheri, GM Di Liberto, ...
IEEE/ACM Transactions on Audio, Speech, and Language Processing 25 (1), 50-63, 2016
432016
How accents confound: Probing for accent information in end-to-end speech recognition systems
A Prasad, P Jyothi
Proceedings of the 58th annual meeting of the association for computational …, 2020
382020
Discriminative language modeling using simulated ASR errors.
P Jyothi, E Fosler-Lussier
Interspeech, 1049-1052, 2010
372010
Select, substitute, search: A new benchmark for knowledge-augmented visual question answering
A Jain, M Kothyari, V Kumar, P Jyothi, G Ramakrishnan, S Chakrabarti
Proceedings of the 44th International ACM SIGIR Conference on Research and …, 2021
362021
Error correction in asr using sequence-to-sequence models
S Dutta, S Jain, A Maheshwari, S Pal, G Ramakrishnan, P Jyothi
arXiv preprint arXiv:2202.01157, 2022
342022
Adapting ASR for under-resourced languages using mismatched transcriptions
C Liu, P Jyothi, H Tang, V Manohar, R Sloan, T Kekona, ...
2016 IEEE International Conference on Acoustics, Speech and Signal …, 2016
312016
Automatic speech recognition in Sanskrit: A new speech corpus and modelling insights
D Adiga, R Kumar, A Krishna, P Jyothi, G Ramakrishnan, P Goyal
arXiv preprint arXiv:2106.05852, 2021
272021
Transcribing continuous speech using mismatched crowdsourcing.
P Jyothi, M Hasegawa-Johnson
INTERSPEECH, 2774-2778, 2015
272015
An investigation of end-to-end models for robust speech recognition
A Prasad, P Jyothi, R Velmurugan
ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021
262021
Exploiting Monolingual Speech Corpora for Code-Mixed Speech Recognition.
K Taneja, S Guha, P Jyothi, B Abraham
Interspeech, 2150-2154, 2019
232019
Dual language models for code switched speech recognition
S Garg, T Parekh, P Jyothi
arXiv preprint arXiv:1711.01048, 2017
222017
Систем тренутно не може да изврши ову радњу. Пробајте поново касније.
Чланци 1–20