2 citations · 4 across the 17 of their papers we have counts for
19 papers
Optimizing Conversational Quality in Spoken Dialogue Systems with Reinforcement Learning from AI Feedback
Siddhant Arora, Jinchuan Tian, Jiatong Shi +4
Reinforcement learning from human or AI feedback (RLHF/RLAIF) for speech-in/speech-out dialogue systems (SDS) remains underexplored, with prior work largely limited to single seman…
Do Neural Codecs Generalize? A Controlled Study Across Unseen Languages and Non-Speech Tasks
Shih-Heng Wang, Jiatong Shi, Jinchuan Tian +2
This paper investigates three crucial yet underexplored aspects of the generalization capabilities of neural audio codecs (NACs): (i) whether NACs can generalize to unseen language…
IKFST: IOO and KOO Algorithms for Accelerated and Precise WFST-based End-to-End Automatic Speech Recognition
Zhuoran Zhuang, Ye Chen, Chao Luo +5
End-to-end automatic speech recognition has become the dominant paradigm in both academia and industry. To enhance recognition performance, the Weighted Finite-State Transducer (WF…
PURE Codec: Progressive Unfolding of Residual Entropy for Speech Codec Learning
Jiatong Shi, Haoran Wang, William Chen +4
Neural speech codecs have achieved strong performance in low-bitrate compression, but residual vector quantization (RVQ) often suffers from unstable training and ineffective decomp…
BSCodec: A Band-Split Neural Codec for High-Quality Universal Audio Reconstruction
Haoran Wang, Jiatong Shi, Jinchuan Tian +3
Neural audio codecs have recently enabled high-fidelity reconstruction at high compression rates, especially for speech. However, speech and non-speech audio exhibit fundamentally…
Speech-DRAME: A Framework for Human-Aligned Benchmarks in Speech Role-Play
Jiatong Shi, Jionghao Han, Yichen Lu +6
Role-play has become a key testbed for generative models, expanding from text-only dialogue to multimodal interaction. Extending role-play to speech captures prosody, emotion, and…
Chain-of-Thought Reasoning in Streaming Full-Duplex End-to-End Spoken Dialogue Systems
Siddhant Arora, Jinchuan Tian, Hayato Futami +4
Most end-to-end (E2E) spoken dialogue systems (SDS) rely on voice activity detection (VAD) for turn-taking, but VAD fails to distinguish between pauses and turn completions. Duplex…
Full-Duplex-Bench-v2: A Multi-Turn Evaluation Framework for Duplex Dialogue Systems with an Automated Examiner
Guan-Ting Lin, Shih-Yun Shan Kuan, Jiatong Shi +4
While full-duplex speech agents enable natural, low-latency interaction by speaking and listening simultaneously, their consistency and task performance in multi-turn settings rema…
Reasoning Beyond Majority Vote: An Explainable SpeechLM Framework for Speech Emotion Recognition
Bo-Hao Su, Hui-Ying Shih, Jinchuan Tian +4
Speech Emotion Recognition (SER) is typically trained and evaluated on majority-voted labels, which simplifies benchmarking but masks subjectivity and provides little transparency…
OpusLM: A Family of Open Unified Speech Language Models
Jinchuan Tian, William Chen, Yifan Peng +9
This paper presents Open Unified Speech Language Models (OpusLMs), a family of open foundational speech language models (SpeechLMs) up to 7B. Initialized from decoder-only text lan…
Chain-of-Thought Training for Open E2E Spoken Dialogue Systems
Siddhant Arora, Jinchuan Tian, Hayato Futami +5
Unlike traditional cascaded pipelines, end-to-end (E2E) spoken dialogue systems preserve full differentiability and capture non-phonemic information, making them well-suited for mo…
MIKU-PAL: An Automated and Standardized Multi-Modal Method for Speech Paralinguistic and Affect Labeling
Yifan Cheng, Ruoyi Zhang, Jiatong Shi
Acquiring large-scale emotional speech data with strong consistency remains a challenge for speech synthesis. This paper presents MIKU-PAL, a fully automated multimodal pipeline fo…
ARECHO: Autoregressive Evaluation via Chain-Based Hypothesis Optimization for Speech Multi-Metric Estimation
Jiatong Shi, Yifan Cheng, Bo-Hao Su +6
Speech signal analysis poses significant challenges, particularly in tasks such as speech quality evaluation and profiling, where the goal is to predict multiple perceptual and obj…
SIFT-50M: A Large-Scale Multilingual Dataset for Speech Instruction Fine-Tuning
Prabhat Pandey, Rupak Vignesh Swaminathan, K V Vijay Girish +4
We introduce SIFT (Speech Instruction Fine-Tuning), a 50M-example dataset designed for instruction fine-tuning and pre-training of speech-text large language models (LLMs). SIFT-50…
ESPnet-SDS: Unified Toolkit and Demo for Spoken Dialogue Systems
Siddhant Arora, Yifan Peng, Jiatong Shi +9
Advancements in audio foundation models (FMs) have fueled interest in end-to-end (E2E) spoken dialogue systems, but different web interfaces for each system makes it challenging to…
ESPnet-SpeechLM: An Open Speech Language Model Toolkit
Jinchuan Tian, Jiatong Shi, William Chen +13
We present ESPnet-SpeechLM, an open toolkit designed to democratize the development of speech language models (SpeechLMs) and voice-driven agentic applications. The toolkit standar…
Balancing Speech Understanding and Generation Using Continual Pre-training for Codec-based Speech LLM
Jiatong Shi, Chunlei Zhang, Jinchuan Tian +4
Recent advances in speech language models (LLMs) have extended textual LLMs to the speech domain, but balancing speech understanding and generation remains challenging, especially…
Exploiting Longitudinal Speech Sessions via Voice Assistant Systems for Early Detection of Cognitive Decline
Kristin Qi, Jiatong Shi, Caroline Summerour +2
Mild Cognitive Impairment (MCI) is an early stage of Alzheimer's disease (AD), a form of neurodegenerative disorder. Early identification of MCI is crucial for delaying its progres…
Preference Alignment Improves Language Model-Based TTS
Jinchuan Tian, Chunlei Zhang, Jiatong Shi +4
Recent advancements in text-to-speech (TTS) have shown that language model (LM)-based systems offer competitive performance to their counterparts. Further optimization can be achie…