Publications

(2026). DualTurn: Learning Turn-Taking from Dual-Channel Generative Speech Pretraining. Interspeech 2026 (Submitted).

PDF

(2024). SpeechLLM: Multi-Modal LLM for Speech Understanding. Model Release.

Code GitHub HuggingFace

(2023). Improving spoken language identification with MAP-Mix. ICASSP 2023.

PDF arXiv

(2023). Improving end-to-end spoken language understanding with prosodic attention and distillation. Interspeech 2023.

PDF arXiv

(2022). Skit-S2I: An Indian Accented Speech to Intent Dataset. arXiv 2022.

PDF Code arXiv

(2021). Learning speaker representation with semi-supervised learning approach for speaker profiling. arXiv 2021.

PDF arXiv

(2021). RL based framework to generate optimal data quality remediation sequence for machine learning. SIGMOD.

(2020). Towards Automated Deep Learning: Analysis of the AutoDL challenge series 2019. PMLR.

PDF Source Document

(2019). Overview and unifying conceptualization of Automated Machine Learning. ADS 2019, Germany.

(2019). Convolutional Feature Extraction and Neural Arithmetic Logic Units for Stock Prediction. Springer-CCIS.

PDF Slides Source Document Pre Print