Siddhant Arora

PhD student@Carnegie Mellon University·美国·OpenReview

研究方向

Spoken Dialogue Systems · Speech Language Models · Speech Processing · Spoken Language Understanding · Information retrieval · Knowledge Base Completion

6.0

WearVox: An Egocentric Multichannel Voice Assistant Benchmark for Wearables

ICLR 2026Poster

4.5

BLAB: Brutally Long Audio Bench

ICLR 2026Rejected

3.0

Stream RAG: Instant and Accurate Spoken Dialogue Systems with Streaming Tool Usage

ICLR 2026Rejected

一作

7.6

ARECHO: Autoregressive Evaluation via Chain-Based Hypothesis Optimization for Speech Multi-Metric Estimation

NeurIPS 2025Spotlight

7.0

Context-aware Dynamic Pruning for Speech Foundation Models

ICLR 2025Poster

三作

7.0

Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks

ICLR 2025Poster

5.8

Talking Turns: Benchmarking Audio Foundation Models on Turn-Taking Dynamics

合作者 (20)