Preethi Jyothi

Post-ASR Correction in Hindi: Comparing Language Models and Large Language Models in Low-Resource Scenarios EACL 2026 Improving Language Identification for Code-Switched Speech: The Pivotal Role of Accented English EACL 2026 SrcMix: Mixing of Related Source Languages Benefits Extremely Low-resource Machine Translation EACL 2026 AMPS: ASR with Multimodal Paraphrase Supervision NAACL 2025 DeFT-X: Denoised Sparse Fine-Tuning for Zero-Shot Cross-Lingual Transfer EMNLP 2025 LASER: An LLM-based ASR Scoring and Evaluation Rubric EMNLP 2025 Language-Specific Neurons Do Not Facilitate Cross-Lingual Transfer NAACL 2025 LexGen: Domain-aware Multilingual Lexicon Generation ACL 2025 LoFTI: Localization and Factuality Transfer to Indian Locales ACL 2025 LEVOS: Leveraging Vocabulary Overlap with Sanskrit to Generate Technical Lexicons in Indian Languages ACL 2025 CoSTA: Code-Switched Speech Translation using Aligned Speech-Text Interleaving COLING 2025 Zero-Shot Cross-Lingual Transfer using Prefix-Based Adaptation EMNLP 2025 Cross-lingual Transfer Dynamics in BLOOMZ: Insights into Multilingual Generalization EMNLP 2025 RECAST: Retrieval-Augmented Contextual ASR via Decoder-State Keyword Spotting EMNLP 2025 DIMSIM: Distilled Multilingual Critics for Indic Text Simplification ACL 2024 Translation Errors Significantly Impact Low-Resource Languages in Cross-Lingual Learning EACL 2024 MULTI-CONVFORMER: Extending Conformer with Multiple Convolution Kernels INTERSPEECH 2024 STORiCo: Storytelling TTS for Hindi with Character Voice Modulation EACL 2024 Improving Self-supervised Pre-training using Accent-Specific Codebooks INTERSPEECH 2024 Emotion Arithmetic: Emotional Speech Synthesis via Weight Space Interpolation INTERSPEECH 2024 DictDis: Dictionary Constrained Disambiguation for Improved NMT EMNLP 2024 SALSA: Speedy ASR-LLM Synchronous Aggregation INTERSPEECH 2024 WikiDO: A New Benchmark Evaluating Cross-Modal Retrieval for Vision-Language Models NIPS 2024 Parameter-efficient Adaptation of Multilingual Multimodal Models for Low-resource ASR EMNLP 2024 In-context Mixing (ICM): Code-mixed Prompts for Multilingual LLMs ACL 2024 Boosting Zero-Shot Crosslingual Performance using LLM-Based Augmentations with Effective Data Selection ACL 2024 Part-of-speech Tagging for Extremely Low-resource Indian Languages ACL 2024 Zero-shot Cross-lingual Transfer With Learned Projections Using Unlabeled Target-Language Data ACL 2023 Improving Pretraining Techniques for Code-Switched NLP ACL 2023 DITTO: Data-efficient and Fair Targeted Subset Selection for ASR Accent Adaptation ACL 2023 Adversarial Training for Low-Resource Disfluency Correction ACL 2023 Accented Speech Recognition With Accent-specific Codebooks EMNLP 2023 Speech-enriched Memory for Inference-time Adaptation of ASR Models to Word Dictionaries EMNLP 2023 DISCO: A Large Scale Human Annotated Corpus for Disfluency Correction in Indo-European Languages EMNLP 2023 In-Situ Text-Only Adaptation of Speech Models with Low-Overhead Speech Imputations ICLR 2023 Temporally Aligning Long Audio Interviews with Questions: A Case Study in Multimodal Data Integration IJCAI 2023 Unsupervised Code-switched Text Generation from Parallel Text INTERSPEECH 2023 DisfluencyFixer: A tool to enhance Language Learning through Speech To Speech Disfluency Correction INTERSPEECH 2023 Improving RNN-Transducers with Acoustic LookAhead INTERSPEECH 2023 Narrator or Character: Voice Modulation in an Expressive Multi-speaker TTS INTERSPEECH 2023 Zero-shot Disfluency Detection for Indian Languages COLING 2022 SPLICEOUT: A Simple and Efficient Audio Augmentation Method INTERSPEECH 2022 Linguistically Informed Post-processing for ASR Error correction in Sanskrit INTERSPEECH 2022 VAgyojaka: An Annotating and Post-Editing Tool for Automatic Speech Recognition INTERSPEECH 2022 CoCoa: An Encoder-Decoder Model for Controllable Code-switched Generation EMNLP 2022 Partitioned Gradient Matching-based Data Subset Selection for Compute-Efficient Robust ASR Training EMNLP 2022 Accurate Online Posterior Alignments for Principled Lexically-Constrained Decoding ACL 2022 Aligning Multilingual Embeddings for Improved Code-switched Natural Language Understanding COLING 2022 MUCS 2021: Multilingual and Code-Switching ASR Challenges for Low Resource Indian Languages INTERSPEECH 2021 Reduce and Reconstruct: ASR for Low-Resource Phonetic Languages INTERSPEECH 2021 Meta-Learning for Effective Multi-task and Multilingual Modelling EACL 2021 The Effect of Pretraining on Extractive Summarization for Scientific Documents NAACL 2021 Perturb, Predict & Paraphrase: Semi-Supervised Learning using Noisy Student for Image Captioning IJCAI 2021 Automatic Speech Recognition in Sanskrit: A New Speech Corpus and Modelling Insights ACL 2021 From Machine Translation to Code-Switching: Generating High-Quality Code-Switched Text IJCNLP 2021 Automatic Speech Recognition in Sanskrit: A New Speech Corpus and Modelling Insights IJCNLP 2021 Low Resource ASR: The Surprising Effectiveness of High Resource Transliteration INTERSPEECH 2021 Cross-Modal Learning for Audio-Visual Video Parsing INTERSPEECH 2021 From Machine Translation to Code-Switching: Generating High-Quality Code-Switched Text ACL 2021 Disfluency Correction using Unsupervised and Semi-supervised Learning EACL 2021 The Effectiveness of Intermediate-Task Training for Code-Switched Natural Language Understanding EMNLP 2021 Generating Fluent Translations from Disfluent Text Without Access to Fluent References: IIT Bombay@IWSLT2020 ACL 2020 Black-Box Adaptation of ASR for Accented Speech INTERSPEECH 2020 Caption Alignment for Low Resource Audio-Visual Data INTERSPEECH 2020 Improving Low Resource Code-Switched ASR Using Augmented Code-Switched TTS INTERSPEECH 2020 How Accents Confound: Probing for Accent Information in End-to-End Speech Recognition Systems ACL 2020 Cross-Lingual Training for Automatic Question Generation ACL 2019 Exploiting Monolingual Speech Corpora for Code-Mixed Speech Recognition INTERSPEECH 2019 Revisiting the Importance of Encoding Logic Rules in Sentiment Classification EMNLP 2018 Code-switched Language Models Using Dual RNNs and Same-Source Pretraining EMNLP 2018 Time Aggregation Operators for Multi-label Audio Event Detection INTERSPEECH 2018 Dual Language Models for Code Switched Speech Recognition INTERSPEECH 2018 Improved Accented Speech Recognition Using Accent Embeddings and Multi-task Learning INTERSPEECH 2018 Generalizing Across Domains via Cross-Gradient Training ICLR 2018 Automatic Speech Recognition Using Probabilistic Transcriptions in Swahili, Amharic, and Dinka INTERSPEECH 2016 Large-scale discriminative language model reranking for voice-search NAACL 2012 Investigations into the Crandem Approach to Word Recognition NAACL 2010