SA
Siddhant Arora
eess.AScs.CLcs.SDcs.AIcs.LGcs.DBcs.MMcs.CVcs.IRstat.ML
On Valency
published · living versionsW_x8yufh22·v1 · currentpublished
MP-Bench: Evaluating Voice Agents as a Multiparty Conversation Participant
with Yi-Jen Shih, Shih-Yun Shan Kuan, Guan-Ting Lin, Kai-Wei Chang +5
1 version
Preprints & journals
65 papers in the corpus · 2019–2026MP-Bench: Evaluating Voice Agents as a Multiparty Conversation Participant2609.13076v1 · Yi-Jen Shih, Shih-Yun Shan Kuan, Guan-Ting Lin et al.2026 · 0 citationsarXivon Valency
An Efficient vLLM-Based Inference Pipeline for Unified Audio Understanding and Generation2607.02119v1 · Haoran Wang, Jinchuan Tian, Siddhant Arora et al.2026 · 0 citationsarXiv
Bagpiper-TTS: Natural Language Guided Universal Speech Synthesis2606.22811v1 · Jinchuan Tian, Haoran Wang, Siddhant Arora et al.2026 · 0 citationsarXiv
ESPnet3: Infrastructure for Scalable Speech and Audio Research in the Foundation Model Era2606.21854v1 · Masao Someki, Alexander Polok, Carlos Carvalho et al.2026 · 0 citationsarXiv
Evaluating Large Language Models Abilities for Addressee, Turn-change, and Next Speaker Prediction in Meetings2606.17542v1 · Ryo Fukuda, Takatomo Kano, Siddhant Arora et al.2026 · 0 citationsarXiv
PlanRAG-Audio: Planning and Retrieval Augmented Generation for Long-form Audio Understanding2605.20414v2 · Masao Someki, Chien-yu Huang, Siddhant Arora et al.2026 · 0 citationsarXiv
Bagpiper: Solving Open-Ended Audio Tasks via Rich Captions2602.05220v4 · Jinchuan Tian, Haoran Wang, Bo-Hao Su et al.2026 · 0 citationsarXiv
Optimizing Conversational Quality in Spoken Dialogue Systems with Reinforcement Learning from AI Feedback2601.19063v1 · Siddhant Arora, Jinchuan Tian, Jiatong Shi et al.2026 · 0 citationsarXiv
WearVox: An Egocentric Multichannel Voice Assistant Benchmark for Wearables2601.02391v1 · Zhaojiang Lin, Yong Xu, Kai Sun et al.2025 · 0 citationsarXiv
Full-Duplex-Bench-v2: A Multi-Turn Evaluation Framework for Duplex Dialogue Systems with an Automated Examiner2510.07838v2 · Guan-Ting Lin, Shih-Yun Shan Kuan, Jiatong Shi et al.2025 · 0 citationsarXiv
Stream RAG: Instant and Accurate Spoken Dialogue Systems with Streaming Tool Usage2510.02044v1 · Siddhant Arora, Haidar Khan, Kai Sun et al.2025 · 0 citationsarXiv
Chain-of-Thought Reasoning in Streaming Full-Duplex End-to-End Spoken Dialogue Systems2510.02066v1 · Siddhant Arora, Jinchuan Tian, Hayato Futami et al.2025 · 0 citationsarXiv
Spiralformer: Low Latency Encoder for Streaming Speech Recognition with Circular Layer Skipping and Early Exiting2510.00982v1 · Emiru Tsunoo, Hayato Futami, Yosuke Kashiwagi et al.2025 · 0 citationsarXiv
Benchmarking Training Paradigms, Dataset Composition, and Model Scaling for Child ASR in ESPnet2508.16576v1 · Anyu Ying, Natarajan Balaji Shankar, Chyi-Jiunn Lin et al.2025 · 2 citationsarXiv
AURA: Agent for Understanding, Reasoning, and Automated Tool Use in Voice-Driven Tasks2506.23049v1 · Leander Melroy Maben, Gayathri Ganesh Lakshmy, Srijith Radhakrishnan et al.2025 · 1 citationarXiv
OpusLM: A Family of Open Unified Speech Language Models2506.17611v1 · Jinchuan Tian, William Chen, Yifan Peng et al.2025 · 3 citationsarXiv
Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs2506.10299v1 · Hayato Futami, Emiru Tsunoo, Yosuke Kashiwagi et al.2025 · 1 citationarXiv
Chain-of-Thought Training for Open E2E Spoken Dialogue Systems2506.00722v1 · Siddhant Arora, Jinchuan Tian, Hayato Futami et al.2025 · 2 citationsarXiv
ARECHO: Autoregressive Evaluation via Chain-Based Hypothesis Optimization for Speech Multi-Metric Estimation2505.24518v2 · Jiatong Shi, Yifan Cheng, Bo-Hao Su et al.2025 · 1 citationarXiv
BLAB: Brutally Long Audio Bench2505.03054v2 · Orevaoghene Ahia, Martijn Bartelds, Kabir Ahuja et al.2025 · 1 citationarXiv
On The Landscape of Spoken Language Models: A Comprehensive Survey2504.08528v2 · Siddhant Arora, Kai-Wei Chang, Chung-Ming Chien et al.2025 · 3 citationsarXiv
ESPnet-SDS: Unified Toolkit and Demo for Spoken Dialogue Systems2503.08533v1 · Siddhant Arora, Yifan Peng, Jiatong Shi et al.2025 · 3 citationsarXiv
Talking Turns: Benchmarking Audio Foundation Models on Turn-Taking Dynamics2503.01174v1 · Siddhant Arora, Zhiyun Lu, Chung-Cheng Chiu et al.2025 · 1 citationarXiv
ESPnet-SpeechLM: An Open Speech Language Model Toolkit2502.15218v2 · Jinchuan Tian, Jiatong Shi, William Chen et al.2025 · 5 citationsarXiv
VERSA: A Versatile Evaluation Toolkit for Speech, Audio, and Music2412.17667v2 · Jiatong Shi, Hye-jin Shim, Jinchuan Tian et al.2024 · 20 citationsarXiv
Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks2411.05361v2 · Chien-yu Huang, Wei-Chih Chen, Shu-wen Yang et al.2024 · 0 citationsarXiv
Hypothesis Clustering and Merging: Novel MultiTalker Speech Recognition with Speaker Tokens2409.15732v1 · Yosuke Kashiwagi, Hayato Futami, Emiru Tsunoo et al.2024 · 0 citationsarXiv
Task Arithmetic for Language Expansion in Speech Translation2409.11274v3 · Yao-Fei Cheng, Hayato Futami, Yosuke Kashiwagi et al.2024 · 0 citationsarXiv
ESPnet-EZ: Python-only ESPnet for Easy Fine-tuning and Integration2409.09506v1 · Masao Someki, Kwanghee Choi, Siddhant Arora et al.2024 · 1 citationarXiv
Decoder-only Architecture for Streaming End-to-end Speech Recognition2406.16107v2 · Emiru Tsunoo, Hayato Futami, Yosuke Kashiwagi et al.2024 · 9 citationsarXiv
Finding Task-specific Subnetworks in Multi-task Spoken Language Understanding Model2406.12317v1 · Hayato Futami, Siddhant Arora, Yosuke Kashiwagi et al.2024 · 1 citationarXiv
Rapid Language Adaptation for Multilingual E2E Speech Recognition Using Encoder Prompting2406.12611v1 · Yosuke Kashiwagi, Hayato Futami, Emiru Tsunoo et al.2024 · 3 citationsarXiv
On the Evaluation of Speech Foundation Models for Spoken Language Understanding2406.10083v1 · Siddhant Arora, Ankita Pasad, Chung-Ming Chien et al.2024 · 5 citationsarXiv
TMT: Tri-Modal Translation between Speech, Image, and Text by Processing Different Modalities as Different Languages2402.16021v2 · Minsu Kim, Jee-weon Jung, Hyeongseop Rha et al.2024 · 2 citationsarXiv
OWSM v3.1: Better and Faster Open Whisper-Style Speech Models based on E-Branchformer2401.16658v3 · Yifan Peng, Jinchuan Tian, William Chen et al.2024 · 41 citationsarXiv
Phoneme-aware Encoding for Prefix-tree-based Contextual ASR2312.09582v1 · Hayato Futami, Emiru Tsunoo, Yosuke Kashiwagi et al.2023 · 8 citationsarXiv
UniverSLU: Universal Spoken Language Understanding for Diverse Tasks with Natural Language Instructions2310.02973v2 · Siddhant Arora, Hayato Futami, Jee-weon Jung et al.2023 · 6 citationsarXiv
Reproducing Whisper-Style Training Using an Open-Source Toolkit and Publicly Available Data2309.13876v3 · Yifan Peng, Jinchuan Tian, Brian Yan et al.2023 · 39 citationsarXiv
Semi-Autoregressive Streaming ASR With Label Context2309.10926v2 · Siddhant Arora, George Saon, Shinji Watanabe et al.2023 · 6 citationsarXiv
Dynamic-SUPERB: Towards A Dynamic, Collaborative, and Comprehensive Instruction-Tuning Benchmark for Speech2309.09510v2 · Chien-yu Huang, Ke-Han Lu, Shih-Heng Wang et al.2023 · 33 citationsarXiv
Decoder-only Architecture for Speech Recognition with CTC Prompts and Text Data Augmentation2309.08876v2 · Emiru Tsunoo, Hayato Futami, Yosuke Kashiwagi et al.2023 · 1 citationarXiv
Integration of Frame- and Label-synchronous Beam Search for Streaming Encoder-decoder Speech Recognition2307.12767v1 · Emiru Tsunoo, Hayato Futami, Yosuke Kashiwagi et al.2023 · 2 citationsarXiv
Integrating Pretrained ASR and LM to Perform Sequence Generation for Spoken Language Understanding2307.11005v1 · Siddhant Arora, Hayato Futami, Yosuke Kashiwagi et al.2023 · 4 citationsarXiv
BASS: Block-wise Adaptation for Speech Summarization2307.08217v1 · Roshan Sharma, Kenneth Zheng, Siddhant Arora et al.2023 · 3 citationsarXiv
Tensor decomposition for minimization of E2E SLU model toward on-device processing2306.01247v1 · Yosuke Kashiwagi, Siddhant Arora, Hayato Futami et al.2023 · 2 citationsarXiv
A Comparative Study on E-Branchformer vs Conformer in Speech Recognition, Translation, and Understanding Tasks2305.11073v1 · Yifan Peng, Kwangyoun Kim, Felix Wu et al.2023 · 11 citationsarXiv
The Pipeline System of ASR and NLU with MLM-based Data Augmentation toward STOP Low-resource Challenge2305.01194v2 · Hayato Futami, Jessica Huynh, Siddhant Arora et al.2023 · 5 citationsarXiv
A Study on the Integration of Pipeline and E2E SLU systems for Spoken Semantic Parsing toward STOP Quality Challenge2305.01620v2 · Siddhant Arora, Hayato Futami, Shih-Lun Wu et al.2023 · 2 citationsarXiv
Joint Modelling of Spoken Language Understanding Tasks with Integrated Dialog History2305.00926v1 · Siddhant Arora, Hayato Futami, Emiru Tsunoo et al.2023 · 3 citationsarXiv
SLUE Phase-2: A Benchmark Suite of Diverse Spoken Language Understanding Tasks2212.10525v2 · Suwon Shon, Siddhant Arora, Chyi-Jiunn Lin et al.2022 · 22 citationsarXiv
Career total: 87 works. 65 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.