Siddhant Arora

Carnegie Mellon University — United States

Computer Science · Physical Sciences

11h-index411citations122works1.42yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Speech Recognition and Synthesis(52), Natural Language Processing Techniques(42), Speech and dialogue systems(37), Topic Modeling(33), Speech and Audio Processing(16)

Publications122 total

Bagpiper: Solving Open-Ended Audio Tasks via Rich Captions
arXiv (Cornell University)·2026Open Access
Bagpiper: Solving Open-Ended Audio Tasks via Rich Captions
ArXiv.org·2026Open Access
Optimizing Conversational Quality in Spoken Dialogue Systems with Reinforcement Learning from AI Feedback
ArXiv.org·2026Open Access
Optimizing Conversational Quality in Spoken Dialogue Systems with Reinforcement Learning from AI Feedback
arXiv (Cornell University)·2026Open Access
TMT: Tri-Modal Translation Between Speech, Image, and Text by Processing Different Modalities as Different Languages
IEEE Transactions on Multimedia·2026
WearVox: An Egocentric Multichannel Voice Assistant Benchmark for Wearables
ArXiv.org·2025Open Access
WearVox: An Egocentric Multichannel Voice Assistant Benchmark for Wearables
arXiv (Cornell University)·2025Open Access
Full-Duplex-Bench-v2: A Multi-Turn Evaluation Framework for Duplex Dialogue Systems with an Automated Examiner
arXiv (Cornell University)·2025Open Access
Stream RAG: Instant and Accurate Spoken Dialogue Systems with Streaming Tool Usage
arXiv (Cornell University)·2025Open Access
Chain-of-Thought Reasoning in Streaming Full-Duplex End-to-End Spoken Dialogue Systems
arXiv (Cornell University)·2025Open Access
Benchmarking Training Paradigms, Dataset Composition, and Model Scaling for Child ASR in ESPnet
2025Open Access
Benchmarking Training Paradigms, Dataset Composition, and Model Scaling for Child ASR in ESPnet
Lirias (KU Leuven)·2025Open Access
Recurrent basilar artery thrombectomy for pediatric vertebral dissection: illustrative case
Journal of Neurosurgery Case Lessons·2025Open Access
OpusLM: A Family of Open Unified Speech Language Models
2025
Scalable Spontaneous Speech Dataset (SSSD): Crowdsourcing Data Collection to Promote Dialogue Research
2025
Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs
2025
Chain-of-Thought Training for Open E2E Spoken Dialogue Systems
2025
Automated 3D room mapping and real-time corner detection for Android-based AR systems
Results in Engineering·2025Open Access
Enhanced urban driving scene segmentation using modified UNet with residual convolutions and attention guided skip connections
Discover Artificial Intelligence·2025Open Access
AURA: Agent for Understanding, Reasoning, and Automated Tool Use in Voice-Driven Tasks
ArXiv.org·2025· 1 citedOpen Access
page 1 of 7Next →

Frequent Co-authors

Shinji Watanabe(36), Yifan Peng(15), Hayato Futami(15), Emiru Tsunoo(15), Yosuke Kashiwagi(14), Brian Yan(8), Jee-weon Jung(8), Xuankai Chang(7), Jiatong Shi(6), Roshan Sharma(6), Siddharth Dalmia(5), Jinchuan Tian(5), William Chen(5), Jessica Huynh(5), Alan W. Black(4), Shih-Lun Wu(4), Srikanta Bedathur(4), Sahajal Dhooria(3), Ritesh Agarwal(3), Mandeep Garg(3)