Searcharxiv⌕ Search

arXiv subjects

Haizhou Li

Publications and source records attributed to Haizhou Li.

At least 19 recordsLinked to original sources
arXiv2026

AdoDAS: A Privacy-Preserving Multimodal Challenge for Adolescent Depression, Anxiety, and Stress Assessment

Adolescent depression, anxiety, and stress (D/A/S) call for scalable tools that complement, rather than replace, professional evaluation. Under a privacy-preserving policy, the AdoDAS Grand Challenge withholds minors' raw recordings and distributes anonymized audio-visual representations and ASR-derived text. Its 6,000 participants provide 24,000 segments across one scripted-reading and three open-response sessions. Two tracks assess multi-task binary D/A/S screening and ordinal prediction of 21 DASS-21 item responses. From 191 registrations, the final leaderboards included 95 eligible screening teams and 64 item-prediction teams. Audio-visual baselines achieved 0.4604 mean F1 and 0.2675 mean Quadratic Weighted Kappa; leading submissions reached 0.5921 and 0.2776. Representative systems emphasize cross-session modelling, temporal multimodal fusion, psychometric structure, and task-aware calibration.

cs.MM↗
arXiv2026

What Did I Just Say? Self-Listening for Full-Duplex Speech Models

Full-duplex spoken language models can listen and speak simultaneously, enabling them to handle interruptions and backchannels in human conversation. However, text generation, speech synthesis, and audio playback proceed asynchronously. As a result, what a model believes it has said may not match what has actually been played to the user. We refer to the problem of recovering from an interruption while remaining aware of the model's realized speech as anchor interruption. To address this problem, we propose Self-Listening, a full-duplex modeling approach that interleaves user speech, model text, and the model's played speech. By feeding the realized speech output back to the model as an input stream, self-listening grounds interruption recovery in what the user has actually heard. We further introduce AnchorSpeech, a collection with homogeneous training and test splits for tracking which items of structured ordered responses have actually been spoken. AnchorSpeech-test evaluates whether a model can respond consistently with the last completed item before an interruption. Experiments show that, compared with full-duplex baselines, models equipped with self-listening mechanism achieve better anchoring performance.

cs.SD↗
arXiv2026

Diagnose, Then Refine: A Closed-Loop TTS System with AudioLLM-Guided Correction

Current TTS systems typically rely on open-loop, single-pass generation and can produce sporadic local prosodic defects, such as misplaced stress, unnatural pauses, or flattened intonation, that utterance-level metrics often fail to expose. We present LoopTTS, a judge-guided Filter-Judge-Refiner framework for recovering low-quality TTS outputs diagnosed by an AudioLLM. Given an initial utterance from a base TTS model, an AudioLLM Judge identifies salient prosodic issues and generates structured refine instructions; a Refiner, our fine-grained instruction-following TTS model, then performs guided expressive re-synthesis conditioned on the initial utterance, target text, and instruction. To train the Refiner, we construct Refiner-DB, a 42K-example AudioLLM-annotated dataset with word-level prosodic weak supervision. Human evaluation on diagnosed low-quality utterances shows that LoopTTS can detect perceptually salient errors and correct them with the Refiner, outperforming raw generated audio and practical open-loop re-generation baselines in recovery quality. The Refiner also demonstrates stronger instruction-following ability for stress and pause control in targeted prosody modification.

cs.SD↗
arXiv2026

WeSep: A Modular and Cue-Composable Framework for Target Speaker Extraction

The study of Target Speaker Extraction (TSE) aims to isolate a desired speaker from overlapping speech mixture given auxiliary cues. Existing systems are typically designed for specific cue types, limiting flexibility when cue availability varies across scenarios. We present WeSep, a unified framework that reformulates TSE as a heterogeneous cue-conditioned learning problem. In WeSep, cue modules and separator backbones are decoupled through standardized interfaces, enabling configurable cue injection and flexible integration of diverse modalities. The design enables systematic study of cue structure, intra- and cross-modal interaction, and dynamic cue availability within a shared optimization framework, facilitating adaptation to real-world conditions. Experiments across enrollment, spatial, visual, and textual cues reveal modality-dependent characteristics and demonstrate stable optimization under heterogeneous cue availability. The toolkit will be publicly available.

eess.AS↗
arXiv2026

Let Me Look at You: Advanced Facial Expression Modeling for Conversational Speech Synthesis

Conversational Speech Synthesis is a fundamental component of human-computer interaction, aiming to generate contextually appropriate, expressive, and empathetic speech. However, facial expressions encode subtle and rich affective cues that are crucial for empathetic speech interaction, whereas existing approaches often overlook this important modality. In addition, the lack of large-scale natural conversational datasets with both speech and visual modalities also limits the development of visual affect understanding in conversational settings.To address these limitations, we propose FacialTalker, a facial-expression-aware CSS framework built upon a large language model backbone. To efficiently encode facial expressions, we propose AUTokenizer, a single-codebook visual tokenizer that discretizes each frame-level facial expression into a compact token, trained with supervision from combinations of facial Action Units. We further introduce a dual direct preference optimization (DualDPO) strategy, which extends the DPO by jointly imposing preference constraints on both visual and speech token sequences, to enhance the model's understanding of facial expressions and speech semantics in multimodal conversational contexts. Moreover, we construct VSDD-1K, a large-scale multimodal dialogue dataset collected through a fully automated pipeline from real-world Internet conversations, comprising over 1,033 hours of synchronized speaker videos and speech, with more than 85\% of frames containing valid faces. Extensive objective and subjective experiments demonstrate that FacialTalker consistently outperforms strong baselines in facial-expression perception and speech synthesis quality, generating speech that is more natural, expressive, and better aligned with the conversational context. The results also validate the effectiveness of our training strategy and dataset construction pipeline.

cs.HC↗
arXiv2026

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD

Full-parameter post-training of trillion-parameter-scale MoE models introduces substantial system-level challenges for large-scale distributed training, including severe memory pressure, non-overlapped communication overhead, and inefficient kernel execution. While most large-scale LLM training systems are built around GPU-based clusters, this report presents an end-to-end optimization practice on the Ascend NPU SuperPOD. Using the DeepSeek-V4 model family as the target workload, we develop a hierarchical optimization framework spanning model-level parallelism, computation-communication orchestration, and low-level kernel execution. The resulting system achieves 34.22% Model FLOPs Utilization (MFU) with a 2.93x improvement over the open-source baseline recipe while maintaining training stability. Building on this optimized infrastructure, we further establish a CPT and SFT workflow for complex Operations Research (OR) tasks. We refer to the integrated framework as SLAI T-Rex. Using DeepSeek-V4-Flash, we develop OR-oriented CPT and SFT data pipelines that combine collected domain resources with solver-verified synthetic optimization documents. The resulting dataset contains 10K high-quality SFT samples spanning four task categories and three problem representations. The specialized model achieves the highest average zero-shot Pass@1 score among the evaluated models, reaching 71.81% and outperforming GPT-5.4-Mini and the base DeepSeek-V4-Flash model by 3.98 and 11.27 percentage points, respectively. Overall, this work demonstrates a full-stack pathway from efficient trillion-parameter model post-training on Ascend infra to domain-specialized Flash models for solver-grounded mathematical modeling, advancing frontier-model systems for complex reasoning.

cs.CL↗
arXiv2026

AuEmoChat: Authentic Emotion Understanding and Rendering for Conversational Speech Synthesis

Conversational Speech Synthesis (CSS) aims to synthesize speech with human-like emotional expression and contextual consistency in user-agent interactions. Existing CSS methods struggle to render authentic human emotions due to limited predefined emotion label spaces (e.g., seven emotion categories), while redundant multimodal tokens in multi-turn dialogue history interfere with context understanding. To address these issues, we propose AuEmoChat, a CSS framework for authentic emotion understanding and rendering. First, we develop AuEmoCodec, which learns a discrete authentic emotion token space from large-scale emotional speech via finite scalar quantization, enabling a more authentic emotion representation than limited basic emotion categories. Furthermore, we propose AuEmoToMe, an authentic-emotion-guided token merging algorithm that merges redundant tokens in multimodal dialogue history while preserving emotion-relevant context. We integrate it into an autoregressive text-speech model to predict the target authentic emotion token and speech tokens. Finally, we propose Authentic Emotion Flow Matching, which renders speech by jointly conditioning on merged dialogue context, target authentic emotion, and acoustic priors. Extensive experiments on the NCSSD-EmCap dataset demonstrate that AuEmoChat outperforms state-of-the-art CSS baselines and generates more expressive and authentic emotional speech. The code and speech demos will be available at: https://github.com/AI-S2-Lab/AuEmoChat.

cs.SD↗
arXiv2026

SLT 2026 REAL-TSE Challenge: Real-world Target Speaker Extraction from Conversational Recordings

We introduce the REAL-TSE Challenge, an IEEE SLT 2026 satellite challenge on target speaker extraction~(TSE) from real conversational recordings. Given a multi-speaker mixture and one or more enrollment utterances from a target speaker, participating systems must recover only the target speech. Unlike simulated read-speech benchmarks, REAL-TSE evaluates Mandarin and English recordings that contain natural overlap, reverberation, noise, channel mismatch, and conversational dynamics. The challenge defines two complementary tracks: an Online track for low-latency streaming extraction and an Offline track for full-context processing. Systems are evaluated with Token Error Rate (TER), Speaker Similarity (SpkSim), DNSMOS, and target-speaker activity F1. This overview paper describes the task definition, datasets, baselines, evaluation protocol, submitted systems, condition-wise findings, and lessons for future real-world TSE benchmarks.

eess.AS↗
arXiv2026

Hierarchical Acoustic-Semantic Modeling: Modality Separation and Semantic Coherence for Full-Duplex SLMs

Developing seamless, high-performance, native intelligent full-duplex Spoken Language Models (SLMs) remains a critical challenge and long-standing goal for the speech and NLP community. Despite notable progress, recent endeavors are fundamentally constrained by severe modality interference, which causes substantial knowledge degradation and compromises semantic integrity -- ultimately making full-duplex SLMs feel unnatural and unintelligent. In this paper, through an exhaustive fine-grained analysis of model optimization dynamics, we uncover the root cause of such performance degradation, revealing that modality interference arises from inherent gradient conflicts between acoustic and semantic modeling when the two modalities are forced to share a deep parameter space. Guided by this key insight, we introduce Lychee-FD, a native end-to-end full-duplex framework designed to mitigate modality interference. Importantly, we propose a hierarchical parameter separation strategy that decouples conflicting modalities in deep layers while preserving cross-modality coherence via a dedicated semantic alignment channel. Extensive experiments on multiple full-duplex benchmarks demonstrate that our method significantly advances the state of the art, yielding substantial improvements in both speech intelligence (+7.4% on Spoken QA) and full-duplex interaction fluidity (+28.5% on FullDuplexBench 1.5) without compromising inference efficiency. To the best of our knowledge, this work is the first to achieve two key advances: 1) uncovering and elucidating the root cause of modality interference in full-duplex SLMs, and 2) designing an elegant hierarchical model together with a practical solution for seamless, high-performance, native intelligent full-duplex SLMs.

cs.CL↗
arXiv2026

TokAN: Accent Normalization Using Self-Supervised Speech Tokens

Accent normalization (AN) seeks to convert non-native (L2) accented speech into standard (L1) speech while preserving speaker identity. The current techniques either require naturally recorded parallel L1-L2 speech for training, or suffer from quality degradation when supervised by synthesized targets. In this paper, we present TokAN, a token-based accent normalization framework that operates on self-supervised discrete speech tokens extracted from a L1-L2 jointly trained vector-quantization (VQ) tokenizer, without the need of synthetic supervisory speech. An autoregressive encoder-decoder model performs token-to-token conversion, translating L2-accented token sequences into the tokens of standard voice. We also introduce reinforcement learning (RL) post-training based on Group Relative Policy Optimization (GRPO), using word error rate and accent classifier confidence as complementary rewards. A non-autoregressive flow-matching synthesizer recovers the Mel-spectrogram from the converted tokens, conditioned on the source speaker embedding. We also develop a flow-matching duration predictor that supports total-duration-aware synthesis, making TokAN applicable to duration-critical tasks such as voice dubbing and live casting. Experiments on seven English accents demonstrate that TokAN reduced the word error rate from 12.40% to 9.89% after supervised fine-tuning, and further to 9.23% after RL post-training, consistently outperforming frame-to-frame, direct flow-matching, and prompt-based token-conversion baselines in terms of accent reduction and intelligibility.

cs.SD↗
arXiv2026

SelectTSL: Prompt-Guided Selective Target Sound Localization in Complex Scenarios

Humans can selectively attend to a target sound and estimate its direction in complex scenarios, whereas such selective localization remains challenging for current deep learning-based systems. Sound source localization (SSL) has achieved remarkable success with deep learning, yet most methods localize all active sources without selectivity. Conversely, target sound extraction (TSE) extracts sources using multimodal prompts but typically fails to preserve the multichannel spatial information required for accurate localization. To bridge this gap, we formulate the task of prompt-guided selective target sound localization and propose SelectTSL, an end-to-end architecture that localizes only the user-specified target in multi-source acoustic scenes. Specifically, we design a target-aware selective localization strategy that employs a Prompt-Guided Selective Attention Module (PGSA) to generate prompt-informed embeddings. These embeddings guide an inter-channel phase difference (IPD) enhancer to refine raw phase cues, fusing with target magnitudes to jointly estimate direction of arrival (DoA) and target-source cardinality, i.e., the number of target sound sources. This coupled design effectively focuses on the user-specified target spatial cues for selective localization and also handles time-varying numbers of target sources. Extensive experiments on both synthetic data and real-world recordings demonstrate that our proposed method consistently outperforms other baselines and exhibits robust generalization to real acoustic environments.

cs.SD↗
arXiv2026

FlexiSLM: A Spoken Language Model with Dynamic and Controllable Frame Rates

Spoken language models (SLMs) extend LLMs to speech input and output. Existing SLMs represent speech at fixed frame rates (e.g., 25 or 12.5 Hz), ignoring the time-varying information density of speech and offering limited flexibility to trade off quality for speed at inference time. Recent audio tokenizer research has proposed dynamic-frame-rate speech coding, which exploits this non-uniformity and enables two new capabilities: very low average frame rates and frame-rate controllability. However, this technique has not yet been applied to SLMs. We introduce FlexiSLM, the first SLM with dynamic and controllable frame rates. FlexiSLM uses the pretrained FlexiCodec to obtain dynamic speech output tokens. The main contributions of this work are threefold: (1) integrating and validating this dynamic-rate representation within a multi-task, speech-to-speech SLM architecture; (2) extending it to frame compression on the input side; and (3) introducing direct frame-rate conditioning to enable accurate and controllable SLM inference. FlexiSLM outperforms fixed-frame-rate 7B models including Qwen2.5-Omni and Kimi-Audio at its 12.5 Hz and 6.25 Hz operating points. We further verify that FlexiSLM can be accurately steered down to 4.0 Hz; at 6.25 Hz, it roughly halves inference time relative to 12.5 Hz while retaining strong speech-to-speech quality. Audio samples are available at: https://flexislm.github.io. Code and data are available at: https://github.com/AmphionTeam/FlexiSLM.

cs.SD↗
arXiv2026

Emo-LiPO: Listwise Preference Optimization for Fine-Grained Emotion Intensity Control in LLM-based Text-to-Speech

Large language model (LLM)-based text-to-speech (TTS) systems enable prompt-conditioned emotional control but struggle with fine-grained emotion intensity due to the semantic -- acoustic gap between text and speech. To address this challenge, we formulate emotion intensity control in LLM-based TTS as a learning-to-rank problem and propose Emo-LiPO, a listwise preference optimization framework that aligns prompt-conditioned speech generation with relative emotion intensity expressed in text. Emo-LiPO explicitly models global intensity ordering within each emotion under fixed transcripts, enabling more faithful and continuous emotional expression. We further construct ESD-plus, a multi-speaker dataset with explicit emotion intensity variations, to support fine-grained emotion modeling and evaluation. Experiments on ESD-plus demonstrate that Emo-LiPO significantly improves emotion accuracy and intensity controllability over both supervised- and DPO-based LLM TTS baselines, with particularly pronounced gains at high intensity levels.

cs.SD↗
arXiv2026

BiEAR: A Human Auditory-Inspired Adaptive Binaural Front-end for Multi-Speaker Localisation and Distance Estimation

We present BiEAR, a human auditory-inspired adaptive binaural front-end for multi-speaker localisation and distance estimation. Inspired by medial olivocochlear (MOC) feedback in human hearing, BiEAR uses a neural controller to adaptively adjust the frequency selectivity of a binaural auditory filterbank during inference. This yields time-frequency adaptive representations for ears, enabling the model to respond to changing acoustic conditions. We evaluate BiEAR on multi-speaker localisation and distance estimation in anechoic and real-room environments. Results show that the adaptive front-end improves localisation accuracy and robustness to unseen speakers and rooms compared with commonly used fixed binaural front-ends. Visualisation and analysis of learned filter adaptations show that BiEAR emphasises informative frequency bands over time. These findings suggest that adaptive, biologically inspired binaural front-ends can improve machine hearing robustness in complex acoustic scenes.

eess.AS↗
arXiv2026

What Happens Before Decoding? Prefill Determines GUI Grounding in VLMs

Existing training-free approaches for GUI grounding often rely on multiple inference runs, such as iterative cropping or candidate aggregation, to identify target elements. Despite this additional computation, each forward pass still independently interprets the instruction and parses the visual layout, without enabling progressive interaction among visual tokens. In this paper, we study what happens during GUI grounding in Vision-Language Models (VLMs) and identify a previously overlooked bottleneck. We show that grounding follows a two-stage paradigm: the prefill stage determines candidate UI elements, while the decoding stage subsequently refines the final coordinates. This asymmetry establishes prefill as the critical step, as errors in candidate selection cannot be effectively corrected during decoding. Based on this observation, we propose Re-Prefill, a training-free method that revisits inference by introducing an attention-guided second prefill stage to refine target selection. Specifically, visual tokens that consistently receive high attention from the query position, i.e., the final token, across layers are extracted as a preliminary target hypothesis and appended to the input, together with the instruction hidden states, enabling the model to deeply re-think its decision before coordinate generation. Experiments across four VLMs and five benchmarks, including ScreenSpot-Pro, ScreenSpot-V2, OSWorld-G, UI-Vision, and MMBench-GUI, demonstrate consistent improvements without additional training, with gains of up to 4.3% on ScreenSpot-Pro. Code will be available at https://github.com/linjiaping1/Re-Prefill.

cs.CV↗
arXiv2026

Ti-Audio: The First Multi-Dialectal End-to-End Speech LLM for Tibetan

Recent advances in Speech Large Language Models (Speech-LLMs) have made significant progress, greatly enhancing multimodal interaction capabilities.However, their application in low-resource and dialect-diverse environments still faces challenges. The severe scarcity of Tibetan data, coupled with the phonetic differences among its major dialects (\"U-Tsang, Amdo, and Kham), is a prime example of this challenge. This paper proposes Ti-Audio, the first multi-dialectal end-to-end Speech-LLM for Tibetan. To efficiently align speech and text, we introduce a Dynamic Q-Former Adapter that extracts essential acoustic features from variable-length speech, ensuring stable cross-modal alignment even with limited data. At the data level, we leverage mutual assistance among related dialects to alleviate data scarcity and employ a temperature-based sampling strategy to maximize this synergy. Experimental results demonstrate that Ti-Audio achieves state-of-the-art performance on Tibetan benchmarks for automatic speech recognition and speech translation. Our work validates the effectiveness of cross-dialectal cooperation and provides a scalable paradigm for the development of Speech-LLM in low-resource scenarios.

cs.SD↗
arXiv2026

Bridging What the Model Thinks and How It Speaks: Expressive Speech Generation via Self-Aware Intent-Realization Alignment

Speech Language Models (SLMs) exhibit strong semantic understanding, yet often fail to translate this capacity into expressive acoustic realization, producing speech with flattened prosody and misaligned emotion. We identify this mismatch as the semantic understanding-acoustic realization gap. Existing approaches typically rely on externally specified proxies, such as emotion labels or style prompts, which require annotations and struggle to capture dynamically evolving expressive intent throughout dialogue. To overcome these limitations, we propose SASLM (Self-Aware Speech Language Model), a proxy-free framework that bridges what the model thinks and how it speaks through self-aware intent-realization alignment: (1) Intent-Aware Bridging self-distills expressive intent from the model's own evolving semantic generation states via a Variational Information Bottleneck (VIB), thereby guiding expressive speech realization without external expressive supervision; while (2) Realization-Aware Alignment reflectively aligns generated acoustics with intended expression through self-reward optimization, progressively improving intent-realization consistency during speech generation. Despite using only 3B parameters and 800 hours of expressive speech data, SASLM achieves state-of-the-art performance on EchoMind among open-source systems, surpassing models over 10 times larger and approaching commercial systems.

cs.CL↗
arXiv2026

AffectSpeech: A Large-Scale Emotional Speech Dataset with Fine-Grained Textual Descriptions for Speech Emotion Captioning and Synthesis

Emotion is essential in spoken communication, yet most existing frameworks in speech emotion modeling rely on predefined categories or low-dimensional continuous attributes, which offer limited expressive capacity. Recent advances in speech emotion captioning and synthesis have shown that textual descriptions provide a more flexible and interpretable alternative for representing affective characteristics in speech. However, progress in this direction is hindered by the lack of an emotional speech dataset aligned with reliable and fine-grained natural language annotations. To tackle this, we introduce AffectSpeech, a large-scale corpus of human-recorded speech enriched with structured descriptions for fine-grained emotion analysis and generation. Each utterance is characterized across six complementary dimensions, including sentiment polarity, open-vocabulary emotion captions, intensity level, prosodic attributes, prominent segments, and semantic content, enabling multi-granular modeling of vocal expression. To balance annotation quality and scalability, we adopt a human-LLM collaborative annotation pipeline that integrates algorithmic pre-labeling, multi-LLM description generation, and human-in-the-loop verification. Furthermore, these annotations are reformulated into diverse descriptive styles to enhance linguistic diversity and reduce stylistic bias in downstream modeling. Experimental results on speech emotion captioning and synthesis demonstrate that models trained on AffectSpeech consistently achieve superior performance across multiple evaluation settings.

eess.AS↗