Publications

2023

  • A. Mittal, S. Sarawagi, P. Jyothi
    In-Situ Text-Only Adaptation of Speech Models with Low-Overhead Speech Imputations
    paper Proceedings of ICLR (The Eleventh International Conference on Learning Representations), 2023
  • B. Yan, M. Wiesner, O. Klejch, P. Jyothi, S. Watanabe
    Towards Zero-shot Code-switched Speech Recognition
    paper Proceedings of ICASSP (48th International Conference on Acoustics, Speech and Language Processing), 2023.
  • P. S. Pasi, K. Battepati, P. Jyothi, G. Ramakrishnan, M. K. Singh, T. Mahapatra
    Temporally Aligning Audio Interviews with Questions: A Case Study in Multimodal Data Integration
    pdf Proceedings of IJCAI (32nd International Joint Conference on Artificial Intelligence), 2023.
  • R. Das*, S. Ranjan*, S. Pathak, P. Jyothi (*Joint first author)
    Improving Pretraining Techniques for Code-Switched NLP
    pdf Proceedings of ACL (61st Annual Meeting of the Association for Computational Linguistics), 2023.
    Received an Outstanding Paper Award.
  • U. Deb, R. Parab, P. Jyothi
    Zero-shot Cross-lingual Transfer Using Target Language Projections
    pdf Proceedings of ACL (61st Annual Meeting of the Association for Computational Linguistics), 2023.
  • S. Kothwade, A. Reddy, D. Chandra Sekhara, M. Kothyari, R. Iyer, G. Ramakrishnan, P. Jyothi
    DITTO: Data-efficient and Fair Targeted Subset Selection for ASR Accent Adaptation
    pdf Proceedings of ACL (61st Annual Meeting of the Association for Computational Linguistics), 2023.
  • V. Bhat, P. Jyothi, P. Bhattacharyya
    Adversarial Training for Low-Resource Disfluency Correction
    pdf Proceedings of ACL (61st Annual Meeting of the Association for Computational Linguistics) Findings, 2023.
  • T. Pavan Kalyan, Preeti Rao, Preethi Jyothi, Pushpak Bhattacharyya
    Narrator or Character: Voice Modulation in an Expressive Multi-speaker TTS
    pdf Proceedings of Interspeech (24th Annual Conference of ISCA), 2023.
  • Vinit Unni, Ashish Mittal, Preethi Jyothi, Sunita Sarawagi
    Improving RNN-Transducers with Acoustic LOOKAHEAD
    pdf Proceedings of Interspeech (24th Annual Conference of ISCA), 2023.
  • Jie Chi, Brian Lu, Jason Eisner, Peter Bell, Preethi Jyothi, Ahmed M. Ali
    Unsupervised Code-switched Text Generation from Parallel Text
    pdf Proceedings of Interspeech (24th Annual Conference of ISCA), 2023.
  • D. Prabhu, P. Jyothi, S. Ganapathy, V. Unni
    Accented Speech Recognition With Accent-specific Codebooks
    pdf code/dataset Accepted to EMNLP 2023 (Conference on Empirical Methods in Natural Language Processing), Singapore, 2023.
  • A. Mittal, S. Sarawagi, P. Jyothi, G. Saon, G. Kurata
    Speech-enriched Memory for Inference-time Adaptation of ASR Models to Word Dictionaries
    TBA Accepted to EMNLP 2023 (Conference on Empirical Methods in Natural Language Processing), Singapore, 2023.
  • V. Bhat, P. Jyothi, P. Bhattacharyya
    DISCO: A Large Scale Human Annotated Corpus for Disfluency Correction in Indo-European Languages
    TBA Accepted to EMNLP 2023 (Conference on Empirical Methods in Natural Language Processing) Findings, Singapore, 2023.
  • Rohan Shah, Preethi Jyothi
    Surprisingly Simple Adapter Ensembling for Zero-shot Cross-lingual Sequence Tagging
    pdf Practical ML for Developing Countries Workshop, ICLR 2023.

2022

  • S. Chatterjee, S. Sarawagi, P. Jyothi
    Accurate Online Posterior Alignments for Principled Lexically-Constrained Decoding
    pdf Proceedings of ACL-IJCNLP (60th Annual Meeting of the Association for Computational Linguistics), 2022
  • B. Fazili, P. Jyothi
    Aligning Multilingual Embeddings for Improved Code-switched Natural Language Understanding
    pdf Proceedings of COLING (29th International Conference on Computational Linguistics), 2022
  • R. Kundu, P. Jyothi, P. Bhattacharyya
    Zero-shot Disfluency Detection for Indian Languages
    pdf dataset Proceedings of COLING (29th International Conference on Computational Linguistics), 2022
  • S. Mondal, Ritika, S. Pathak, P. Jyothi, A. Raghuveer
    COCOA: An Encoder-Decoder Model for Controllable Code-switched Generation
    pdf dataset Proceedings of EMNLP 2022 (Conference on Empirical Methods in Natural Language Processing), Abu Dhabi, 2022.
  • A. Mittal*, D. Sivasubramanian*, R. Iyer, P. Jyothi, G. Ramakrishnan (*Joint first author)
    Partitioned Gradient Matching-based Data Subset Selection for Compute-Efficient Robust ASR Training
    pdf Proceedings of EMNLP 2022 (Conference on Empirical Methods in Natural Language Processing) Findings, Abu Dhabi, 2022.
  • V. Unni, S. Khare, A. Mittal, P. Jyothi, S. Sarawagi, S. Bharadwaj
    Adaptive Discounting of Implicit Language Models in RNN-Transducers
    pdf Proceedings of ICASSP (47th International Conference on Acoustics, Speech and Language Processing), 2022.
  • A. Jain, P. R. Samala, D. Mittal, P. Jyothi, M. Singh
    SpliceOut: A Simple and Efficient Audio Augmentation Method
    pdf Proceedings of Interspeech (23rd Annual Conference of ISCA), 2022.
  • R. Kumar, D. Adiga, R. Ranjan, A. Krishna, G. Ramakrishnan, P. Goyal, P. Jyothi
    Linguistically Informed Post-processing for ASR Error correction in Sanskrit
    pdf Proceedings of Interspeech (23rd Annual Conference of ISCA), 2022.

2021

  • A. Prasad, M. A. Rehan, S. Pathak, P. Jyothi
    The Effectiveness of Intermediate-Task Training for Code-Switched Natural Language Understanding
    pdf Proceedings of Workshop on Multilingual Representation Learning, EMNLP 2021.
    Received an Honorable Mention Award.
  • A. Diwan, P. Jyothi
    Reduce and Reconstruct: ASR for Low-Resource Phonetic Languages
    pdf Proceedings of Interspeech (22nd Annual Conference of ISCA), 2021.
    Nominated for a Best Student Paper Award.
  • S. Khare, A. Mittal, A. Diwan, S. Sarawagi, P. Jyothi, S. Bharadwaj
    Low Resource ASR: The surprising effectiveness of High Resource Transliteration
    pdf Proceedings of Interspeech (22nd Annual Conference of ISCA), 2021.
  • J. Lamba, J. Akula, Abhishek, R. Dabral, G. Ramakrishnan, P. Jyothi
    Cross-Modal learning for Audio-Visual Video Parsing
    pdf Proceedings of Interspeech (22nd Annual Conference of ISCA), 2021.
  • A. Diwan, R. Vaideeswaran, S. Shah, A. Singh et al.
    Multilingual and code-switching ASR challenges for low resource Indian languages
    pdf Proceedings of Interspeech (22nd Annual Conference of ISCA), 2021.
  • I. Tarunesh, S. Kumar, P. Jyothi
    From Machine Translation to Code-Switching: Generating High-Quality Code-Switched Text
    pdf code dataset Proceedings of ACL-IJCNLP (59th Annual Meeting of the Association for Computational Linguistics), 2021
  • D. Adiga, R. Kumar, A. Krishna, P. Jyothi, G. Ramakrishnan, P. Goyal
    Automatic Speech Recognition in Sanskrit: A New Speech Corpus and Modelling Insights
    pdf Proceedings of ACL-IJCNLP (59th Annual Meeting of the Association for Computational Linguistics) Findings, 2021
  • A. Jain, P. R. Samala, P. Jyothi, D. Mittal, M. Singh
    Perturb, Predict & Paraphrase: Semi-Supervised Learning using Noisy Student for Image Captioning
    pdf code Proceedings of IJCAI (30th International Joint Conference on Artificial Intelligence), 2021.
  • Y. Gupta, P. S. Ammanamanchi, S. Bordia, A. Manoharan, D. Mittal, R. Pasunuru, M. Shrivastava, M. Singh, M. Bansal, P. Jyothi
    The Effect of Pretraining on Extractive Summarization for Scientific Documents
    pdf Proceedings of the Second Workshop on Scholarly Document Processing, NAACL 2021.
  • A. Jain, M. Kothyari, V. Kumar, P. Jyothi, G. Ramakrishnan, S. Chakrabarti
    Select, Substitute, Search: A new Benchmark for Knowledge-Augmented Visual Question Answering
    pdf Proceedings of SIGIR (44th International ACM SIGIR Conference on Research and Development in Information Retrieval), 2021.
  • A. Prasad, P. Jyothi, R. Velmurugan
    An Investigation of End-to-End Models for Robust Speech Recognition
    pdf code Proceedings of ICASSP (46th International Conference on Acoustics, Speech and Language Processing), 2021.
  • A. Awasthi, A. Kansal, S. Sarawagi, P. Jyothi
    Error-driven Fixed-budget ASR Personalization for Accented Speakers
    pdf Proceedings of ICASSP (46th International Conference on Acoustics, Speech and Language Processing), 2021.
  • V. Kurmi, V. Bajaj, B. Patro, V. K. Subramanian, V. Namboodiri, P. Jyothi
    Collaborative Learning to Generate Audio-Video Jointly
    pdf Proceedings of ICASSP (46th International Conference on Acoustics, Speech and Language Processing), 2021.
  • N. Saini, D. Trivedi, S. Khare, T. Dhamecha, P. Jyothi, S. Bharadwaj, P. Bhattacharyya
    Disfluency Correction using Unsupervised and Semi-supervised Learning
    pdf Proceedings of EACL (16th Conference of the European Chapter of the Association for Computational Linguistics), 2021.
  • I. Tarunesh, S. Khyalia, V. Kumar, G. Ramakrishnan, P. Jyothi
    Meta-Learning for Effective Multi-task and Multilingual Modelling
    pdf Proceedings of EACL (16th Conference of the European Chapter of the Association for Computational Linguistics), 2021.

2020

  • K. Khandelwal, P. Jyothi, A. Awasthi and S. Sarawagi
    Black-box Adaptation of ASR for Accented Speech
    pdf code Proceedings of Interspeech (21st Annual Conference of ISCA), 2020.
  • Y. Sharma, B. Abraham, K. Taneja, P. Jyothi
    Improving Low Resource Code-switched ASR using Augmented Code-switched TTS
    pdf Proceedings of Interspeech (21st Annual Conference of ISCA), 2020.
  • V. R. Konda, M. Warialani, R. P. Achari, V. Bhatnagar, J. Akula, P. Jyothi, G. Ramakrishnan, G. Haffari and P. Singh
    Caption Alignment for Low Resource Audio-visual Data
    pdf Proceedings of Interspeech (21st Annual Conference of ISCA), 2020.
  • A. Prasad, P. Jyothi
    How Accents Confound: Probing for Accent Information in End-to-End Speech Recognition Systems
    pdf code Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL), 2020.
  • V. Unni*, N. Joshi*, P. Jyothi (*Joint first author)
    Coupled Training of Sequence-to-sequence Models for Accented Speech Recognition
    pdf Proceedings of ICASSP 2020 (45th International Conference on Acoustics, Speech and Language Processing), 2020.
  • B. Abraham, D. Goel, D. Siddarth, K. Bali, M. Chopra, M. Choudhury, P. Joshi, P. Jyothi, S. Sitaram, V. Seshadri
    Crowdsourcing Speech Data for Low-Resource Languages from Low-Income Workers
    pdf Proceedings of the 12th Conference on Language Resources and Evaluation (LREC), 2020.
  • N. Saini, J. Khatri, P. Jyothi, P. Bhattacharyya
    Generating Fluent Translations from Disfluent Text Without Access to Fluent References: IIT Bombay@IWSLT 2020
    pdf Proceedings of the 17th International Conference on Spoken Language Translation (IWSLT), ACL 2020.

2019

  • V. Kumar, N. Joshi, A. Ghosh, G. Ramakrishnan, P. Jyothi
    Cross-Lingual Training for Automatic Question Generation
    pdf Proceedings of ACL 2019 (57th Annual Meeting of the Association for Computational Linguistics), Florence, 2019.
  • K. Taneja, S. Guha, P. Jyothi, B. Abraham
    Exploiting Monolingual Speech Corpora for Code-mixed Speech Recognition
    pdf Proceedings of Interspeech 2019 (20th Annual Conference of ISCA), Graz, 2019.

2018

  • K. Krishna, P. Jyothi, M. Iyyer
    Revisiting the Importance of Encoding Logic Rules in Sentiment Classification
    pdf code Proceedings of EMNLP 2018 (Conference on Empirical Methods in Natural Language Processing), Brussels, 2018.
  • S. Garg*, T. Parekh*, P. Jyothi (*Joint first author)
    Code-switched Language Models Using Dual RNNs and Same-Source Pretraining
    pdf Proceedings of EMNLP 2018 (Conference on Empirical Methods in Natural Language Processing), Brussels, 2018.
  • A. Jain, M. Upreti, P. Jyothi.
    Improved Accented Speech Recognition Using Accent Embeddings and Multi-task Learning
    pdf Proceedings of Interspeech 2018 (19th Annual Conference of ISCA), Hyderabad, 2018.
  • S. Garg, T. Parekh, P. Jyothi
    Dual Language Models for Code Switched Speech Recognition
    pdf Proceedings of Interspeech 2018 (19th Annual Conference of ISCA), Hyderabad, 2018.
  • P. Joshi, D. Gautam, G. Ramakrishnan, P. Jyothi
    Time Aggregation Operators for Multi-label Audio Event Detection
    pdf Proceedings of Interspeech 2018 (19th Annual Conference of ISCA), Hyderabad, 2018.
  • S. Shankar, V. Piratla, S. Chakrabarti, S. Chaudhuri, P. Jyothi, S. Sarawagi
    Generalizing Across Domains via Cross-Gradient Training
    pdf Proceedings of 6th International Conference on Learning Representations (ICLR), Vancouver, 2018

2017

  • A. Siddhant, P. Jyothi, S. Ganapathy
    Leveraging Native Language Speech for Accent Identification using Deep Siamese Networks
    pdf IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), Okinawa, 2017.
  • M. Hasegawa-Johnson, P. Jyothi, W. Chen, V. H. Do
    Mismatched crowdsourcing: Mining latent skills to acquire speech transcriptions
    paper Proceedings of Asilomar, 2017.
  • P. Jyothi, M. Hasegawa-Johnson
    Low-resource Grapheme-to-phoneme Conversion using Recurrent Neural Networks
    pdf Proceedings of ICASSP 2017 (42nd International Conference on Acoustics, Speech and Language Processing), New Orleans, 2017.
  • M. Hasegawa-Johnson, P. Jyothi, D. McCloy, M. Mirbagheri, G. di Liberto, A. Das, B. Ekin, C. Liu, V. Manohar, H. Tang, E. C. Lalor, N. Chen, P. Hager, T. Kekona, R. Sloan, and A. K. C. Lee
    ASR for Under-Resourced Languages from Probabilistic Transcription
    pdf IEEE/ACM Trans. Audio, Speech and Language 25(1):46-59, 2017.

2016

  • W. Chen, M. Hasegawa-Johnson, N. Chen, P. Jyothi, L. Varshney
    Mismatched Crowdsourcing with Clustering-based Phonetic Projection for Low-resourced ASR
    6th Workshop on South and Southeast Asian Natural Language Processing, COLING, Osaka, 2016.
  • A. Das*, P. Jyothi*, M. Hasegawa-Johnson (*Joint first author)
    Automatic speech recognition using Probabilistic Transcriptions in Swahili, Amharic, and Dinka
    pdf Interspeech 2016 (17th Annual Conference of ISCA), San Francisco, 2016.
  • X. Kong, P. Jyothi, M. Hasegawa-Johnson
    Performance Improvement of Probabilistic Transcriptions with Language-Specific Constraints
    paper SLTU 2016 (5th International Workshop on Spoken Language Technologies for Under-resourced Languages), Indonesia, 2016.
  • K. Livescu, P. Jyothi, E. Fosler-Lussier
    Articulatory Feature-based Pronunciation Modeling
    paper Computer Speech and Language, 36, 212-232, 2016.
  • C. Liu*, P. Jyothi*, H. Tang, V. Manohar, R. Sloan, T. Kekona, M. Hasegawa-Johnson, S. Khudanpur
    (*Joint first author) Adapting ASR for Under-resourced Languages Using Mismatched Transcriptions
    pdf ICASSP 2016 (41st International Conference on Acoustics, Speech and Language Processing), Beijing, 2016.
    Received Speech and Language Processing Student Paper Award.
  • L. Varshney, P. Jyothi, M. Hasegawa-Johnson
    Language Coverage for Mismatched Crowdsourcing
    pdf ITA 2016 (2016 Information Theory Applications Workshop), San Diego, 2016.

2015

  • P. Jyothi, M. Hasegawa-Johnson
    Transcribing Continuous Speech Using Mismatched Crowdsourcing
    pdf Interspeech 2015 (16th Annual Conference of ISCA), Dresden, 2015.
  • P. Jyothi, M. Hasegawa-Johnson
    Improving Hindi Broadcast ASR by Adapting the Language Model and Pronunciation Model Using A Priori Syntactic and Morphophonemic Knowledge
    pdf Interspeech 2015 (16th Annual Conference of ISCA), Dresden, 2015.
  • P. Jyothi, M. Hasegawa-Johnson
    Acquiring Speech Transcriptions Using Mismatched Crowdsourcing
    pdf AAAI (29th AAAI Conference on Artificial Intelligence), Austin, 2015.
  • M. Hasegawa-Johnson, J. Cole, P. Jyothi, L. Varshney
    Models of Dataset Size, Question Design and Cross-Language Speech Perception for Speech Crowdsourcing Applications
    pdf Laboratory Phonology, 6(3-4):381-431, 2015.
  • T. Luchkina, V. Puri, P. Jyothi, J. Cole
    Prosodic and Structural Correlates of Perceived Prominence in Russian and Hindi
    ICPhS (18th International Congress of Phonetic Sciences), Glasgow, 2015.

2009-14

  • P. Jyothi, K. Livescu.
    Revisiting Word Neighborhoods for Speech Recognition.
    pdf demo MorphFSM 2014 (Joint meeting of SIGMORPHON and SIGFSM at the 52nd Annual Meeting of ACL), Baltimore, 2014.
  • P. Jyothi, J. Cole, M. Hasegawa-Johnson, V. Puri.
    An Investigation of Prosody in Hindi Narrative Speech.
    pdf Speech Prosody 2014 (7th Speech Prosody Conference), Dublin, 2014.
  • P. Jyothi, E. Fosler-Lussier, K. Livescu.
    Discriminative Training of WFST Factors with Application to Pronunciation Modeling.
    pdf Interspeech 2013 (14th Annual Conference of ISCA), Lyon, 2013.
  • E. Fosler-Lussier, P. Jyothi, J. Keshet, K. Livescu, R. Prabhavalkar, H. Tang.
    Discriminative Learning with Latent Articulatory Variables.
    pdf SPASR 2013 (Workshop on Speech Production in ASR at Interspeech), Lyon, 2013.
  • P. Jyothi, E. Fosler-Lussier and K. Livescu.
    Discriminatively Learning Factorized Finite State Pronunciation Models from Dynamic Bayesian Networks.
    pdf Interspeech 2012 (13th Annual Conference of ISCA), Portland, 2012.
    Received Best Student Paper Award.
  • E. Fosler-Lussier, Y. He, P. Jyothi, R. Prabhavalkar.
    Conditional Random Fields in Speech, Audio and Language Processing.
    pdf Proceedings of the IEEE, 101(5), 1054--1075, 2012.
  • P. Jyothi, L. Johnson, C. Chelba, and B. Strope.
    Large-scale Discriminative Language Model Reranking for Voice-Search.
    pdf WLM 2012 (Workshop on the Future of Language Modeling at 12th Annual Conference of NAACL-HLT), Montreal, 2012.
  • P. Jyothi, L. Johnson, C. Chelba, and B. Strope.
    Distributed Discriminative Language Models for Google Voice-Search.
    pdf ICASSP 2012 (37th International Conference on Acoustics, Speech and Language Processing), Kyoto, 2012.
  • P. Jyothi, K. Livescu, and E. Fosler-Lussier.
    Lexical Access Experiments with Context-Dependent Articulatory Feature-Based Models.
    pdf ICASSP 2011 (36th International Conference on Acoustics, Speech and Language Processing), Prague, 2011.
  • P. Jyothi and E. Fosler-Lussier.
    Discriminative Language Modeling Using Simulated ASR Errors.
    pdf Interspeech 2010 (11th Annual Conference of ISCA), Makuhari, 2010.
  • R. Prabhavalkar, P. Jyothi, W. Hartmann, J. Morris and E. Fosler-Lussier.
    Investigations into the Crandem Approach to Word Recognition.
    pdf NAACL-HLT 2010 (10th Annual Conference of NAACL-HLT), Los Angeles, 2010.
  • P. Jyothi and E. Fosler-Lussier.
    A Comparison of Audio-free Speech Recognition Error Prediction Methods.
    pdf Interspeech 2009 (10th Annual Conference of ISCA), Brighton, 2009.