arXiv subjects

Haoqin Sun

Publications and source records attributed to Haoqin Sun.

At least 19 recordsLinked to original sources

arXiv2026

Marco-Voice Technical Report

This paper presents a multifunctional speech synthesis system that integrates voice cloning and emotion control speech synthesis within a unified framework. The goal of this work is to address longstanding challenges in achieving highly expressive, controllable, and natural speech generation that faithfully preserves speaker identity across diverse linguistic and emotional contexts. Our approach introduces an effective speaker-emotion disentanglement mechanism with in-batch contrastive learning, enabling independent manipulation of speaker identity and eemotional style, as well as rotational emotional embedding integration method for smooth emotion control. To support comprehensive training and evaluation, we construct CSEMOTIONS, a high-quality emotional speech dataset containing 10 hours of Mandarin speech from ten professional speakers across seven emotional categories. Extensive experiments demonstrate that our system, Marco-Voice, achieves substantial improvements in both objective and subjective metrics. Comprehensive evaluations and analysis were conducted, results show that MarcoVoice delivers competitive performance in terms of speech clarity and emotional richness, representing a substantial advance in the field of expressive neural speech synthesis. Our code and dataset are publicly available at https://github.com/AIDC-AI/Marco-Voice and https://huggingface.co/datasets/AIDC-AI/CSEMOTIONS respectively.

cs.CL↗

arXiv2026

WildElder: A Chinese Elderly Speech Dataset from the Wild with Fine-Grained Manual Annotations

Elderly speech poses unique challenges for automatic processing due to age-related changes such as slower articulation and vocal tremors. Existing Chinese datasets are mostly recorded in controlled environments, limiting their diversity and real-world applicability. To address this gap, we present WildElder, a Mandarin elderly speech corpus collected from online videos and enriched with fine-grained manual annotations, including transcription, speaker age, gender, and accent strength. Combining the realism of in-the-wild data with expert curation, WildElder enables robust research on automatic speech recognition and speaker profiling. Experimental results reveal both the difficulties of elderly speech recognition and the potential of WildElder as a challenging new benchmark. The dataset and code are available at https://github.com/NKU-HLT/WildElder.

cs.SD↗

arXiv2026

SpeechLLM-as-Judges: Towards General and Interpretable Speech Quality Evaluation

Generative speech technologies are progressing rapidly, but evaluating the perceptual quality of synthetic speech remains a core challenge. Existing methods typically rely on scalar scores or binary decisions, which lack interpretability and generalization across tasks and languages. We present SpeechLLM-as-Judges, a new paradigm for enabling large language models (LLMs) to conduct structured and explanation-based speech quality evaluation. To support this direction, we introduce SpeechEval, a large-scale dataset containing 32,207 multilingual speech clips and 128,754 annotations spanning four tasks: quality assessment, pairwise comparison, improvement suggestion, and deepfake detection. Based on this resource, we develop SQ-LLM, a speech-quality-aware LLM trained with chain-of-thought reasoning and reward optimization to improve capability. Experimental results show that SQ-LLM delivers strong performance across tasks and languages, revealing the potential of this paradigm for advancing speech quality evaluation. The relevant code, models, and data are publicly available at https://github.com/NKU-HLT/SpeechLLM-as-Judges.

cs.SD↗

arXiv2026

ECHO: Towards Emotionally Appropriate and Contextually Aware Interactive Head Generation

In natural face-to-face interaction, participants seamlessly alternate between speaking and listening, producing facial behaviors (FBs) that are finely informed by long-range context and naturally exhibit contextual appropriateness and emotional rationality. Interactive Head Generation (IHG) aims to synthesize lifelike avatar head video emulating such capabilities. Existing IHG methods typically condition on dual-track signals (i.e., human user's behaviors and pre-defined audio for avatar) within a short temporal window, jointly driving generation of avatar's audio-aligned lip articulation and non-verbal FBs. However, two main challenges persist in these methods: (i) the reliance on short-clip behavioral cues without long-range contextual modeling leads them to produce facial behaviors lacking contextual appropriateness; and (ii) the entangled, role-agnostic fusion of dual-track signals empirically introduces cross-signal interference, potentially compromising lip-region synchronization during speaking. To this end, we propose ECHO, a novel IHG framework comprising two key components: a Long-range Contextual Understanding (LCU) component that facilitates contextual understanding of both behavior-grounded dynamics and linguistic-driven affective semantics to promote contextual appropriateness and emotional rationality of synthesized avatar FBs; and a block-wise Spatial-aware Decoupled Cross-attention Modulation (SDCM) module, that preserves self-audio-driven lip articulation while adaptively integrating user contextual behavioral cues for non-lip facial regions, complemented by our designed two-stage training paradigm, to jointly enhance lip synchronization and visual fidelity. Extensive experiments demonstrate the effectiveness of proposed components and ECHO's superior IHG performance.

cs.CV↗

arXiv2026

Speech-XL: Towards Long-Form Speech Understanding in Large Speech Language Models

Despite the growing success of Large Speech Language Models (LSLMs) in processing short-term acoustic signals, their extension to long-form audio understanding is severely bottlenecked. This limitation stems from the limited context length and the exorbitant memory footprints required for long-form inference. In this work, we propose Speech-XL, a new model that capitalizes on the intrinsic key-value (KV) sparsification capacity of Large Language Models (LLMs) to achieve high-ratio speech input compression. Specifically, we introduce a novel special token, the Speech Summarization Token (SST), for each speech interval to encapsulate the intra-interval speech information into its associated KV pairs. The SST module is trained via instruction fine-tuning, employing a curriculum learning strategy where the SST learns to compress information in a progressive manner--advancing from low-ratio (simple) to high-ratio (challenging) compression. Despite utilizing significantly less training data than other baselines, our model achieves highly competitive performance on major benchmarks, including LongSpeech and AUDIOMARATHON. By addressing the long-standing bottlenecks in long-form audio modeling, our approach offers a novel perspective on the condensation of extensive acoustic sequences.

cs.SD↗

arXiv2026

AudioEval: Automatic Dual-Perspective and Multi-Dimensional Evaluation of Text-to-Audio-Generation

Text-to-audio (TTA) generation is advancing rapidly, but evaluation remains challenging because human listening studies are expensive and existing automatic metrics capture only limited aspects of perceptual quality. We introduce AudioEval, a large-scale TTA evaluation dataset with 4,200 generated audio samples (11.7 hours) from 24 systems and 126,000 ratings collected from both experts and non-experts across five dimensions: enjoyment, usefulness, complexity, quality, and text alignment. Using AudioEval, we benchmark diverse automatic evaluators to compare perspective- and dimension-level differences across model families. We also propose Qwen-DisQA as a strong reference baseline: it jointly processes prompts and generated audio to predict multi-dimensional ratings for both annotator groups, modeling rater disagreement via distributional prediction and achieving strong performance. We will release AudioEval to support future research in TTA evaluation.

cs.SD↗

arXiv2026

Reflecting Twice before Speaking with Empathy: Self-Reflective Alternating Inference for Empathy-Aware End-to-End Spoken Dialogue

End-to-end Spoken Language Models (SLMs) hold great potential for paralinguistic perception, and numerous studies have aimed to enhance their capabilities, particularly for empathetic dialogue. However, current approaches largely depend on rigid supervised signals, such as ground-truth response in supervised fine-tuning or preference scores in reinforcement learning. Such reliance is fundamentally limited for modeling complex empathy, as there is no single "correct" response and a simple numerical score cannot fully capture the nuances of emotional expression or the appropriateness of empathetic behavior. To address these limitations, we sequentially introduce EmpathyEval, a descriptive natural-language-based evaluation model for assessing empathetic quality in spoken dialogues. Building upon EmpathyEval, we propose ReEmpathy, an end-to-end SLM that enhances empathetic dialogue through a novel Empathetic Self-Reflective Alternating Inference mechanism, which interleaves spoken response generation with free-form, empathy-related reflective reasoning. Extensive experiments demonstrate that ReEmpathy substantially improves empathy-sensitive spoken dialogue by enabling reflective reasoning, offering a promising approach toward more emotionally intelligent and empathy-aware human-computer interactions.

cs.CL↗

arXiv2025

DIFFA: Large Language Diffusion Models Can Listen and Understand

Recent advances in large language models (LLMs) have shown remarkable capabilities across textual and multimodal domains. In parallel, diffusion-based language models have emerged as a promising alternative to the autoregressive paradigm, offering improved controllability, bidirectional context modeling, and robust generation. However, their application to the audio modality remains underexplored. In this work, we introduce \textbf{DIFFA}, the first diffusion-based large audio-language model designed to perform spoken language understanding. DIFFA integrates a frozen diffusion language model with a lightweight dual-adapter architecture that bridges speech understanding and natural language reasoning. We employ a two-stage training pipeline: first, aligning semantic representations via an ASR objective; then, learning instruction-following abilities through synthetic audio-caption pairs automatically generated by prompting LLMs. Despite being trained on only 960 hours of ASR and 127 hours of synthetic instruction data, DIFFA demonstrates competitive performance on major benchmarks, including MMSU, MMAU, and VoiceBench, outperforming several autoregressive open-source baselines. Our results reveal the potential of diffusion-based language models for efficient and scalable audio understanding, opening a new direction for speech-driven AI. Our code will be available at https://github.com/NKU-HLT/DIFFA.git.

cs.SD↗

arXiv2025

MECap-R1: Emotion-aware Policy with Reinforcement Learning for Multimodal Emotion Captioning

Speech Emotion Captioning (SEC) has emerged as a notable research direction. The inherent complexity of emotional content in human speech makes it challenging for traditional discrete classification methods to provide an adequate representation. Consequently, utilizing natural language to describe speech emotions presents a novel avenue for more effectively capturing and expressing affect. In this paper, we propose MECap-R1, a pioneering emotion-aware policy with reinforcement learning for multimodal emotion captioning. By employing Group Relative Policy Optimization with emotion-aware reward (Emo-GRPO), the framework precisely captures the emotion and semantic features, thereby addressing the shortcomings of rigid rules in handling the dynamic and flexible nature of captions. Experimental results on the EmotionTalk dataset demonstrate that MECap-R1 performs well in generating emotion descriptions and achieves substantial gains in both accuracy and diversity.

cs.SD↗

arXiv2025

Omni-CLST: Error-aware Curriculum Learning with guided Selective chain-of-Thought for audio question answering

With the rapid progress of large audio-language models (LALMs), audio question answering (AQA) has emerged as a challenging task requiring both fine-grained audio understanding and complex reasoning. While current methods mainly rely on constructing new datasets via captioning or reasoning traces, existing high-quality AQA data remains underutilized. To address this, we propose Omni-CLST, an error-aware Curriculum Learning framework with guided Selective Chain-of-Thought. The framework efficiently leverages existing high-quality dataset through two key strategies: an error-aware curriculum that organizes samples by difficulty, and a guided thought dropout mechanism that focuses reasoning on challenging cases. Experiments show that Omni-CLST achieves 73.80% on MMAU-mini and a new state of the art of 64.30% on MMAR, demonstrating robust generalization in multimodal audio-language understanding.

cs.SD↗

arXiv2025

FELLE: Autoregressive Speech Synthesis with Token-Wise Coarse-to-Fine Flow Matching

To advance continuous-valued token modeling and temporal-coherence enforcement, we propose FELLE, an autoregressive model that integrates language modeling with token-wise flow matching. By leveraging the autoregressive nature of language models and the generative efficacy of flow matching, FELLE effectively predicts continuous-valued tokens (mel-spectrograms). For each continuous-valued token, FELLE modifies the general prior distribution in flow matching by incorporating information from the previous step, improving coherence and stability. Furthermore, to enhance synthesis quality, FELLE introduces a coarse-to-fine flow-matching mechanism, generating continuous-valued tokens hierarchically, conditioned on the language model's output. Experimental results demonstrate the potential of incorporating flow-matching techniques in autoregressive mel-spectrogram modeling, leading to significant improvements in TTS generation quality, as shown in https://aka.ms/felle.

cs.CL↗

arXiv2025

TTA-Bench: A Comprehensive Benchmark for Evaluating Text-to-Audio Models

Text-to-Audio (TTA) generation has made rapid progress, but current evaluation methods remain narrow, focusing mainly on perceptual quality while overlooking robustness, generalization, and ethical concerns. We present TTA-Bench, a comprehensive benchmark for evaluating TTA models across functional performance, reliability, and social responsibility. It covers seven dimensions including accuracy, robustness, fairness, and toxicity, and includes 2,999 diverse prompts generated through automated and manual methods. We introduce a unified evaluation protocol that combines objective metrics with over 118,000 human annotations from both experts and general users. Ten state-of-the-art models are benchmarked under this framework, offering detailed insights into their strengths and limitations. TTA-Bench establishes a new standard for holistic and responsible evaluation of TTA systems. The dataset and evaluation tools are open-sourced at https://nku-hlt.github.io/tta-bench/.

cs.SD↗

arXiv2025

Learning Personalised Human Internal Cognition from External Expressive Behaviours for Real Personality Recognition

Automatic real personality recognition (RPR) aims to evaluate human real personality traits from their expressive behaviours. However, most existing solutions generally act as external observers to infer observers' personality impressions based on target individuals' expressive behaviours, which significantly deviate from their real personalities and consistently lead to inferior recognition performance. Inspired by the association between real personality and human internal cognition underlying the generation of expressive behaviours, we propose a novel RPR approach that efficiently simulates personalised internal cognition from easy-accessible external short audio-visual behaviours expressed by the target individual. The simulated personalised cognition, represented as a set of network weights that enforce the personalised network to reproduce the individual-specific facial reactions, is further encoded as a novel graph containing two-dimensional node and edge feature matrices, with a novel 2D Graph Neural Network (2D-GNN) proposed for inferring real personality traits from it. To simulate real personality-related cognition, an end-to-end strategy is designed to jointly train our cognition simulation, 2D graph construction, and personality recognition modules.

cs.CV↗

arXiv2025

EmotionTalk: An Interactive Chinese Multimodal Emotion Dataset With Rich Annotations

In recent years, emotion recognition plays a critical role in applications such as human-computer interaction, mental health monitoring, and sentiment analysis. While datasets for emotion analysis in languages such as English have proliferated, there remains a pressing need for high-quality, comprehensive datasets tailored to the unique linguistic, cultural, and multimodal characteristics of Chinese. In this work, we propose \textbf{EmotionTalk}, an interactive Chinese multimodal emotion dataset with rich annotations. This dataset provides multimodal information from 19 actors participating in dyadic conversational settings, incorporating acoustic, visual, and textual modalities. It includes 23.6 hours of speech (19,250 utterances), annotations for 7 utterance-level emotion categories (happy, surprise, sad, disgust, anger, fear, and neutral), 5-dimensional sentiment labels (negative, weakly negative, neutral, weakly positive, and positive) and 4-dimensional speech captions (speaker, speaking style, emotion and overall). The dataset is well-suited for research on unimodal and multimodal emotion recognition, missing modality challenges, and speech captioning tasks. To our knowledge, it represents the first high-quality and versatile Chinese dialogue multimodal emotion dataset, which is a valuable contribution to research on cross-cultural emotion analysis and recognition. Additionally, we conduct experiments on EmotionTalk to demonstrate the effectiveness and quality of the dataset. It will be open-source and freely available for all academic purposes. The dataset and codes will be made available at: https://github.com/NKU-HLT/EmotionTalk.

cs.MM↗

arXiv2025

StreamMel: Real-Time Zero-shot Text-to-Speech via Interleaved Continuous Autoregressive Modeling

Recent advances in zero-shot text-to-speech (TTS) synthesis have achieved high-quality speech generation for unseen speakers, but most systems remain unsuitable for real-time applications because of their offline design. Current streaming TTS paradigms often rely on multi-stage pipelines and discrete representations, leading to increased computational cost and suboptimal system performance. In this work, we propose StreamMel, a pioneering single-stage streaming TTS framework that models continuous mel-spectrograms. By interleaving text tokens with acoustic frames, StreamMel enables low-latency, autoregressive synthesis while preserving high speaker similarity and naturalness. Experiments on LibriSpeech demonstrate that StreamMel outperforms existing streaming TTS baselines in both quality and latency. It even achieves performance comparable to offline systems while supporting efficient real-time generation, showcasing broad prospects for integration with real-time speech large language models. Audio samples are available at: https://aka.ms/StreamMel.

cs.SD↗

arXiv2025

RA-CLAP: Relation-Augmented Emotional Speaking Style Contrastive Language-Audio Pretraining For Speech Retrieval

The Contrastive Language-Audio Pretraining (CLAP) model has demonstrated excellent performance in general audio description-related tasks, such as audio retrieval. However, in the emerging field of emotional speaking style description (ESSD), cross-modal contrastive pretraining remains largely unexplored. In this paper, we propose a novel speech retrieval task called emotional speaking style retrieval (ESSR), and ESS-CLAP, an emotional speaking style CLAP model tailored for learning relationship between speech and natural language descriptions. In addition, we further propose relation-augmented CLAP (RA-CLAP) to address the limitation of traditional methods that assume a strict binary relationship between caption and audio. The model leverages self-distillation to learn the potential local matching relationships between speech and descriptions, thereby enhancing generalization ability. The experimental results validate the effectiveness of RA-CLAP, providing valuable reference in ESSD.

cs.SD↗

arXiv2025

Discrete Audio Representations for Automated Audio Captioning

Discrete audio representations, termed audio tokens, are broadly categorized into semantic and acoustic tokens, typically generated through unsupervised tokenization of continuous audio representations. However, their applicability to automated audio captioning (AAC) remains underexplored. This paper systematically investigates the viability of audio token-driven models for AAC through comparative analyses of various tokenization methods. Our findings reveal that audio tokenization leads to performance degradation in AAC models compared to those that directly utilize continuous audio representations. To address this issue, we introduce a supervised audio tokenizer trained with an audio tagging objective. Unlike unsupervised tokenizers, which lack explicit semantic understanding, the proposed tokenizer effectively captures audio event information. Experiments conducted on the Clotho dataset demonstrate that the proposed audio tokens outperform conventional audio tokens in the AAC task.

cs.SD↗

arXiv2025

MusicEval: A Generative Music Dataset with Expert Ratings for Automatic Text-to-Music Evaluation

The technology for generating music from textual descriptions has seen rapid advancements. However, evaluating text-to-music (TTM) systems remains a significant challenge, primarily due to the difficulty of balancing performance and cost with existing objective and subjective evaluation methods. In this paper, we propose an automatic assessment task for TTM models to align with human perception. To address the TTM evaluation challenges posed by the professional requirements of music evaluation and the complexity of the relationship between text and music, we collect MusicEval, the first generative music assessment dataset. This dataset contains 2,748 music clips generated by 31 advanced and widely used models in response to 384 text prompts, along with 13,740 ratings from 14 music experts. Furthermore, we design a CLAP-based assessment model built on this dataset, and our experimental results validate the feasibility of the proposed task, providing a valuable reference for future development in TTM evaluation. The dataset is available at https://www.aishelltech.com/AISHELL_7A.

cs.SD↗