Scholar
Siddhant Arora
Google Scholar ID: VGfczTIAAAAJ
Graduate Student, Carnegie Mellon University
Machine Learning
Speech Processing
Natural language processing
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
1,097
H-index
18
i10-index
27
Publications
20
Co-authors
27
list available
Contact
No contact links provided.
Publications
23 items
An Efficient vLLM-Based Inference Pipeline for Unified Audio Understanding and Generation
2026
Cited
0
Bagpiper-TTS: Natural Language Guided Universal Speech Synthesis
2026
Cited
0
ESPnet3: Infrastructure for Scalable Speech and Audio Research in the Foundation Model Era
2026
Cited
0
Evaluating Large Language Models Abilities for Addressee, Turn-change, and Next Speaker Prediction in Meetings
2026
Cited
0
Bagpiper: Solving Open-Ended Audio Tasks via Rich Captions
2026
Cited
0
Optimizing Conversational Quality in Spoken Dialogue Systems with Reinforcement Learning from AI Feedback
2026
Cited
0
Chain-of-Thought Reasoning in Streaming Full-Duplex End-to-End Spoken Dialogue Systems
2025
Cited
0
Stream RAG: Instant and Accurate Spoken Dialogue Systems with Streaming Tool Usage
2025
Cited
0
Load more
Resume (English only)
Co-authors
27 total
Shinji Watanabe
Carnegie Mellon University
Yifan Peng
NVIDIA
Co-author 3
Jiatong Shi (史嘉彤)
Carnegie Mellon University
Emiru Tsunoo
Sony Corp.
Hayato Futami
Sony Group Corporation
William Chen
Carnegie Mellon University
Jinchuan Tian
Language Technologies Institute, Carnegie Mellon University