Publications

19 research publications spanning speech synthesis, speech recognition, and conversational AI. Full list on Google Scholar.

---

Premier International Conferences

INTERSPEECH 2024 – Kos Island, Greece

• A Unified Approach to Multilingual ASR with Improved Language Identification for Indic Languages
• Speaker Personalization for ASR using Weight-Decomposed Low-Rank Adaptation

ICASSP 2024 – IEEE International Conference on Acoustics, Speech, and Signal Processing, Seoul, Korea

• Robust Speaker Personalisation Using Generalized Low-Rank Adaptation for ASR

INTERSPEECH 2018 – Hyderabad, India

• Code-switching in Indic Speech Synthesisers

INTERSPEECH 2017 – Stockholm, Sweden

• Deep Learning Techniques in Tandem with Signal Processing Cues for Phonetic Segmentation for TTS in Indian Languages
• TBT: Toolkit to Build TTS – A High Performance Framework to Build Multiple Language HTS Voice (Show & Tell)

TSD 2016 – International Conference on Text, Speech, and Dialogue, Brno, Czech Republic

• A Unified Parser for Developing Indian Language Text to Speech Synthesizers

---

Journal

Speech Communication (Elsevier, 2020)

• Significance of Spectral Cues in Automatic Speech Segmentation for Indian Language Speech Synthesizers

---

Workshops

SSW 2025 – 13th Speech Synthesis Workshop, Leeuwarden, Netherlands

• Fricatives in Modern Text-to-Speech Synthesizers

SSW 2021 – Speech Synthesis Workshop, Hungary

• Non-native English Lexicon Creation for Bilingual Speech Synthesis

---

National Conferences

NCC 2024 – National Conference on Communications, IIT Madras, Chennai, India

• Robust Speech Recognition Using Meta-Learning for Low-Resource Accents

SLTU 2018 – Spoken Language Technologies for Under-Resourced Languages, Gurugram, India

• Signal Processing Cues to Improve ASR for Low Resource Indian Languages

GCCS 2017 – Global Conference on Cyberspace, New Delhi, India

• Speech Synthesis in Indian Languages and Future Perspectives

FRSM 2017 – Frontiers of Research in Speech and Music, Rourkela, India

• A Hybrid Approach to Neural Networks Based Speech Segmentation

CBBLR 2016 – Community-based Building of Language Resources, Brno, Czech Republic

• Resources for Indian Languages

---

Challenge

Blizzard Challenge 2015

• Blizzard Challenge 2015 Submission by DONLab, IIT Madras

---

Thesis

M.S. Thesis, IIT Madras (2019)

• A Unified Approach to Speech Synthesis in Indian Languages Supervised by Prof. Hema A. Murthy

---

Preprints

• An ASR Guided Speech Intelligibility Measure for TTS Model Selection (arXiv, 2020)
• Context-based Out-of-Vocabulary Word Recovery for ASR Systems in Indian Languages (arXiv, 2022)