Speech.ai
Overview
End-to-end speech and audio processing: automatic speech recognition, text-to-speech synthesis, speaker and language identification, and low-resource multilingual speech technologies.
Location
CC 402
Principal Investigators
Recent Publications
-
Dynamic Multi-Expert Projectors with Stabilized Routing for Multilingual Speech Recognition
Isha Pandey, Ashish Mittal, Vartul Bahuguna, Ganesh Ramakrishnan
arXiv preprint · 2026
-
Improving Language Identification for Code-Switched Speech: The Pivotal Role of Accented English
Adyasha Patra, Dhiraj Kumar Sah, Preethi Jyothi
Findings of the Association for Computational Linguistics: EACL (EACL Findings) · 2026
-
Linguistically informed automatic speech recognition in Sanskrit
Rishabh Kumar, Devaraja Adiga, Rishav Ranjan, Amrith Krishna, Ganesh Ramakrishnan, Pawan Goyal, Preethi Jyothi
Computer Speech & Language (CSL) · 2026
-
Post-ASR Correction in Hindi: Comparing Language Models and Large Language Models in Low-Resource Scenarios
Rishabh Kumar, Amrith Krishna, Ganesh Ramakrishnan, Preethi Jyothi
Conference of the European Chapter of the Association for Computational Linguistics (EACL) · 2026
-
BlockDecoder: Boosting ASR Decoders with Context and Merger Modules
Darshan Prabhu, Preethi Jyothi
Conference on Neural Information Processing Systems (NeurIPS) · 2025
-
CoSTA: Code-Switched Speech Translation using Aligned Speech-Text Interleaving
Bhavani Shankar, Preethi Jyothi, Pushpak Bhattacharyya
International Conference on Computational Linguistics (COLING) · 2025
-
LASER: An LLM-based ASR Scoring and Evaluation Rubric
Amruta Parulekar, Preethi Jyothi
Conference on Empirical Methods in Natural Language Processing (EMNLP) · 2025
-
RECAST: Retrieval-Augmented Contextual ASR via Decoder-State Keyword Spotting
Ashish Mittal, Sunita Sarawagi, Preethi Jyothi
Findings of the Association for Computational Linguistics: EMNLP (EMNLP Findings) · 2025
-
SKIP-SALSA: Skip Synchronous Fusion of ASR LLM Decoders
Ashish Mittal, Darshan Prabhu, Sunita Sarawagi, Preethi Jyothi
Interspeech · 2025
-
AMPS: ASR with Multimodal Paraphrase Supervision
Abhishek Gupta, Amruta Parulekar, Sameep Chattopadhyay, Preethi Jyothi
arXiv preprint · 2024