3 citations · 9 across the 21 of their papers we have counts for
22 papers
Fish Audio Drama 3 Technical Report
Dawei Han, Shidong Li, Shijia Liao +13
We introduce Fish Audio Drama 3, an open-source speech generation model that turns text into directed performances, built on a 35B-parameter mixture-of-experts backbone that activa…
LongWoF-Bench: Evaluating EvoMap Genes for Verifiable Long-Workflow Tasks
Xiao Zhang, Qumeng Sun, Jiahao Li +5
Large language models are increasingly expected to execute complex workflows whose success depends on maintaining interdependent constraints and producing artifacts that satisfy st…
AutoResearch: Insight In, Hallucination Out
Yiming Ren, Xiang Liu, Bruno +5
Autonomous research systems are increasingly capable of executing long research workflows, yet automation alone does not ensure that the resulting process remains scientifically gr…
ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition
Qingjian Lin, Yuxin Li, Haoyang Zhang +14
Audio-encoder-LLM-decoder architectures have become the dominant paradigm for modern automatic speech recognition (ASR), improving transcription quality through large-scale languag…
DuplexSLA: A Full-Duplex Spoken Language Model with Synchronized Speech, Language, and Action
Haoyang Zhang, Jun Chen, Donghang Wu +13
Recent advances in spoken dialogue language models have shifted from turn-based to full-duplex designs, where the model continuously listens to the user while generating responses.…
From Procedural Skills to Strategy Genes: Towards Experience-Driven Test-Time Evolution
Junjie Wang, Yiming Ren, Haoyang Zhang
This beta technical report asks how reusable experience should be represented so that it can function as effective test-time control and as a substrate for iterative evolution. We…
Step-Audio-R1.5 Technical Report
Yuxin Zhang, Xiangyu Tony Zhang, Daijiao Liu +16
Recent advancements in large audio language models have extended Chain-of-Thought (CoT) reasoning into the auditory domain, enabling models to tackle increasingly complex acoustic…
The WER Trap: Shattering the Illusion of Unified Tokens in Speech Language Models
Xiangyu Zhang, Yuxin Li, Haoyang Zhang +5
The pursuit of a "unified" discrete token for both speech understanding and generation has led the Speech Language Model (SLM) community to heavily rely on Word Error Rate (WER) --…
StepAudio 2.5 Technical Report
Bin Lin, Bo Zhao, Boyong Wu +98
Unified audio-language modeling has emerged as a prominent trend in modern speech systems, promising to bring the reasoning capabilities of large language models to auditory tasks.…
Boosting Omni-Modal Language Models: Staged Post-Training with Visually Debiased Evaluation
Che Liu, Lichao Ma, Xiangyu Tony Zhang +4
Omni-modal language models are intended to jointly understand audio, visual inputs, and language, but benchmark gains can be inflated when visual evidence alone is enough to answer…
CoWork-X: Experience-Optimized Co-Evolution for Multi-Agent Collaboration System
Zexin Lin, Jiachen Yu, Haoyang Zhang +5
Large language models are enabling language-conditioned agents in interactive environments, but highly cooperative tasks often impose two simultaneous constraints: sub-second real-…
DepFlow: Disentangled Speech Generation to Mitigate Semantic Bias in Depression Detection
Yuxin Li, Xiangyu Zhang, Yifei Li +4
Speech is a scalable and non-invasive biomarker for early mental health screening. However, widely used depression datasets like DAIC-WOZ exhibit strong coupling between linguistic…
Step-Audio-R1 Technical Report
Fei Tian, Xiangyu Tony Zhang, Yuxin Zhang +14
Recent advances in reasoning models have demonstrated remarkable success in text and vision domains through extended chain-of-thought deliberation. However, a perplexing phenomenon…
MULTI-Bench: A Multi-Turn Interactive Benchmark for Assessing Emotional Intelligence ability of Spoken Dialogue Models
Yayue Deng, Guoqiang Hu, Haiyang Sun +6
Spoken Dialogue Models (SDMs) have advanced rapidly, yet their ability to sustain genuinely interactive multi-turn conversations remains underexplored, as most benchmarks focus on…
Mind-Paced Speaking: A Dual-Brain Approach to Real-Time Reasoning in Spoken Language Models
Donghang Wu, Haoyang Zhang, Jun Chen +9
Real-time Spoken Language Models (SLMs) struggle to leverage Chain-of-Thought (CoT) reasoning due to the prohibitive latency of generating the entire thought process sequentially.…
Chronological Thinking in Full-Duplex Spoken Dialogue Language Models
Donghang Wu, Haoyang Zhang, Chen Chen +8
Recent advances in spoken dialogue language models (SDLMs) reflect growing interest in shifting from turn-based to full-duplex systems, where the models continuously perceive user…
Code-switching Speech Recognition Under the Lens: Model- and Data-Centric Perspectives
Hexin Liu, Haoyang Zhang, Qiquan Zhang +4
Code-switching automatic speech recognition (CS-ASR) presents unique challenges due to language confusion introduced by spontaneous intra-sentence switching and accent bias that bl…
Step-Audio 2 Technical Report
Boyong Wu, Chao Yan, Chen Hu +106
This paper presents Step-Audio 2, an end-to-end multi-modal large language model designed for industry-strength audio understanding and speech conversation. By integrating a latent…
NTU Speechlab LLM-Based Multilingual ASR System for Interspeech MLC-SLM Challenge 2025
Yizhou Peng, Bin Wang, Yi-Wen Chao +5
This report details the NTU Speechlab system developed for the Interspeech 2025 Multilingual Conversational Speech and Language Model (MLC-SLM) Challenge (Task I), where we achieve…
Impact of Frame Rates on Speech Tokenizer: A Case Study on Mandarin and English
Haoyang Zhang, Hexin Liu, Xiangyu Zhang +7
The speech tokenizer plays a crucial role in recent speech tasks, generally serving as a bridge between speech signals and language models. While low-frame-rate codecs are widely e…
Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction
Ailin Huang, Boyong Wu, Bruce Wang +142
Real-time speech interaction, serving as a fundamental interface for human-machine collaboration, holds immense potential. However, current open-source models face limitations such…
GameGPT: Multi-agent Collaborative Framework for Game Development
Dake Chen, Haoyang Zhang, Hanbin Wang +3
The large language model (LLM) based agents have demonstrated their capacity to automate and expedite software development processes. In this paper, we focus on game development an…