Searcharxiv⌕ Search

arXiv subjects

Zengrui Jin

Publications and source records attributed to Zengrui Jin.

At least 19 recordsLinked to original sources
arXiv2026

FSA-GRPO: Teaching Auditory LLMs to Use Few-Shot Demonstrations

Few-shot prompting provides an effective way to adapt auditory large language models to low-resource tasks such as children's speech recognition. However, most auditory large language models are not explicitly trained to perform inference in this demonstration-conditioned format, limiting the extent to which they can benefit from In-Context Learning (ICL). To address this limitation, we introduce Few-Shot Aware GRPO (FSA-GRPO), an RL-based post-training recipe that uses a specially designed reward to encourage the model to leverage few-shot demonstrations, thereby strengthening its few-shot adaptation ability. Notably, training with only 2k high-resource adult ASR utterances improves the model's general few-shot adaptation ability, yielding gains not only in children's speech recognition (53.9% relative WER reduction without any in-domain training) but also in multilingual ASR (including low-resource languages), speech translation, and audio understanding. We further study data selection and the weight and similarity cutoffs of the auxiliary reward to identify an effective training recipe. Our experiments show that when in-domain data are unavailable or cannot be used for training, FSA-GRPO is more effective than direct tuning on related out-of-domain data.

eess.AS↗
arXiv2026

MetaSICL: Globalizing Auditory LLMs for Underserved Speakers and Languages via Meta Speech In-Context Learning

Generative AI for speech and audio is increasingly expected to serve users across languages, cultures, and communities, yet current auditory Large Language Models (LLMs) are still largely trained and evaluated on high-resource data. Globalizing such systems requires handling low-resource settings, where the target speakers, languages, or tasks are poorly represented in training data. In these regimes, collecting enough labeled in-domain data is often impractical, and the small corpora available may still under-represent the test distribution, making direct fine-tuning brittle under domain shift. In-Context Learning (ICL) offers an alternative: instead of updating model parameters for every underserved community, an auditory LLM can adapt at inference time by conditioning on a few local demonstrations. However, vanilla speech ICL remains limited because most auditory LLMs are not explicitly trained to use such demonstrations effectively. We address this gap with Meta Speech In-Context Learning (MetaSICL), a post-training recipe that strengthens an auditory LLM's in-context adaptation ability using only abundant high-resource speech data. Although MetaSICL never trains on the target low-resource domains, it improves performance across two backbones on children's ASR, audio understanding/reasoning, and speech translation and ASR in directions and languages unseen in post-training. We further study the case where some in-domain data is available, using low-resource language ASR as a case study, since recognition for underserved languages is central to globalizing generative AI. Here, using MetaSICL as a warmup for in-domain reinforcement learning yields the strongest results, outperforming direct fine-tuning across five typologically diverse languages. Overall, MetaSICL offers a practical route toward globalizing auditory LLMs by building inference-time adaptation into the model.

cs.SD↗
arXiv2026

Optimising Neural Speech Codecs for 300bps Communication using Reinforcement Learning

In bandwidth-constrained communication such as satellite and underwater channels, speech must often be transmitted at ultra-low bitrates where intelligibility is the primary objective. At such extreme compression levels, codecs trained with acoustic reconstruction losses tend to allocate bits to perceptual detail, leading to substantial degradation in word error rate (WER). This paper proposes ClariCodec, a neural speech codec operating at 300 bits per second (bps) that reformulates quantisation as a stochastic policy, enabling reinforcement learning (RL)-based optimisation of intelligibility. Specifically, the encoder is fine-tuned using WER-driven rewards while the acoustic reconstruction pipeline remains frozen. Even without RL, ClariCodec achieves 4.64% WER on the LibriSpeech test-clean set at 300 bps, already competitive with codecs operating at higher bitrates. Further RL fine-tuning reduces WER to 3.55% on test-clean, corresponding to a 23.5% relative reduction while preserving perceptual quality. In addition, we adapt ClariCodec to a streaming configuration and show that the proposed RL-based optimisation remains effective under streaming constraints, achieving 4.53% WER on test-clean with a theoretical latency of 374 ms.

cs.SD↗
arXiv2026

SPEAR: A Unified SSL Framework for Learning Speech and Audio Representations

Self-supervised learning (SSL) has significantly advanced acoustic representation learning. However, most existing models are optimised for either speech or audio event understanding, resulting in a persistent gap between these two domains. We address this gap with SPEAR (SPEech and Audio Representations), a self-supervised framework that distils complementary knowledge from a speech-focused SSL teacher and a general-audio SSL teacher into a single unified model. SPEAR applies multi-codebook vector quantisation to continuous teacher representations to produce fine-grained discrete tokens that capture both semantic and acoustic information. To effectively integrate these heterogeneous representations, SPEAR jointly predicts them given a masked input with an asymmetric pre-training loss. We further improve robustness in complex sound scenes through a novel token mixing mechanism. Extensive experiments demonstrate that SPEAR consistently outperforms existing unified speech and audio models. SPEAR establishes a new state-of-the-art on the SUPERB benchmark, surpassing WavLM Large on 12 of 15 tasks, while achieving competitive performance on the HEAR benchmark. These results position SPEAR as a versatile foundation for general-purpose speech and audio representation learning. The code and pre-trained models will be released.

eess.AS↗
arXiv2026

Augmenting Dysarthric Speech Severity Assessment with MOS Supervision

Dysarthria is a speech disorder marked by reduced intelligibility and communicative effectiveness. Automatic utterance-level assessment of dysarthric speech can support scalable speech monitoring and therapy-related analysis. Yet training such systems is bottlenecked by the scarcity of clinically annotated dysarthric speech. This work proposes to augment dysarthric speech assessment using data from speech synthesis evaluations, specifically human-annotated utterances with Mean Opinion Score (MOS) labels from the QualiSpeech corpus. Experiments show that fine-tuning on speech synthesis assessment data consistently improves performance on both intelligibility and naturalness prediction, while joint training yields gains primarily on naturalness. These results suggest that synthesis artifacts and dysarthric speech share perceptual commonalities, and speech synthesis evaluation corpora offer a practical augmentation source that reduces reliance on scarce clinical annotations.

eess.AS↗
arXiv2026

Explainable and Trustworthy Speech Emotion Recognition Using Confidence Score and Reinforcement Learning Rectified Speech Emotion Descriptors

Explainable and trustworthy speech emotion recognition (SER) remains a challenging task to date, largely due to the scarcity of SER data with reliable speech emotion descriptor (SED) labels, such as prosodic features and speaker traits. This paper presents a confidence score and reinforcement learning (RL) based on-the-fly SED rectification approach for post-training SER systems on automatically annotated SED labels. Experiments on IEMOCAP and MELD suggest that explainable SER systems incorporating the proposed confidence score and RL-based SED rectification approach consistently outperform baselines without data selection or SED rectification. The best performing system, which integrates both components, surpasses the baseline without data selection and SED rectification, achieving SER gains of 2.9% and 3.3% absolute (3.7% and 5.4% relative) on IEMOCAP and MELD benchmarks, respectively.

cs.SD↗
arXiv2026

UNISON: A Unified Sound Generation and Editing Framework via Deep LLM Fusion

We present UNISON, a latent diffusion framework that unifies speech generation, sound generation, and audio editing within a single model. A single model handles text-to-audio, text-to-speech, zero-shot speaker cloning, mixed speech-and-sound generation, scene-level audio editing, speech-in-scene editing, and timed temporal composition, all of which share a single set of weights. Our architecture features two core designs: (1) Layer-wise deep LLM fusion, which injects hidden states from uniformly sampled layers of a frozen MLLM into corresponding MM-DiT blocks via learned projections, providing depth-matched semantic conditioning that improves instruction following over single-layer baselines; and (2) a unified multi-task architecture where task identity is encoded solely by a channel-wise mask and source audio is provided through VAE-encoded channel concatenation. Training is stabilized by an online GPU-side multi-task data synthesis pipeline with task-homogeneous batching and a two-stage curriculum. With 621M--732M trainable parameters, UNISON achieves results competitive with or exceeding task-specialist models across evaluated domains, while being roughly $4\times$ smaller than comparable unified systems.

eess.AS↗
arXiv2026

JAEGER: Joint 3D Audio-Visual Grounding and Reasoning in Simulated Physical Environments

Current audio-visual large language models (AV-LLMs) are predominantly restricted to 2D perception, relying on RGB video and monaural audio. This design choice introduces a fundamental dimensionality mismatch that precludes reliable source localization and spatial reasoning in complex 3D environments. We address this limitation by presenting JAEGER, a framework that extends AV-LLMs to 3D space, to enable joint spatial grounding and reasoning through the integration of RGB-D observations and multi-channel first-order ambisonics. A core contribution of our work is the neural intensity vector (Neural IV), a learned spatial audio representation that encodes robust directional cues to enhance direction-of-arrival estimation, even in adverse acoustic scenarios with overlapping sources. To facilitate large-scale training and systematic evaluation, we propose SpatialSceneQA, a benchmark of 61k instruction-tuning samples curated from simulated physical environments. Extensive experiments demonstrate that our approach consistently surpasses 2D-centric baselines across diverse spatial perception and reasoning tasks, underscoring the necessity of explicit 3D modelling for advancing AI in physical environments. Our source code, pre-trained model checkpoints, and datasets are available at https://github.com/liuzhan22/JAEGER.

cs.CV↗
arXiv2026

ClariCodec: Optimising Neural Speech Codes for 200bps Communication using Reinforcement Learning

In bandwidth-constrained communication such as satellite and underwater channels, speech must often be transmitted at ultra-low bitrates where intelligibility is the primary objective. At such extreme compression levels, codecs trained with acoustic reconstruction losses tend to allocate bits to perceptual detail, leading to substantial degradation in word error rate (WER). This paper proposes ClariCodec, a neural speech codec operating at 200 bit per second (bps) that reformulates quantisation as a stochastic policy, enabling reinforcement learning (RL)-based optimisation of intelligibility. Specifically, the encoder is fine-tuned using WER-driven rewards while the acoustic reconstruction pipeline remains frozen. Even without RL, ClariCodec achieves 3.68% WER on the LibriSpeech test-clean set at 200 bps, already competitive with codecs operating at higher bitrates. Further RL fine-tuning reduces WER to 3.20% on test-clean and 8.93% on test-other, corresponding to a 13% relative reduction while preserving perceptual quality.

cs.SD↗
arXiv2026

Towards Fine-Grained and Multi-Granular Contrastive Language-Speech Pre-training

Modeling fine-grained speaking styles remains challenging for language-speech representation pre-training, as existing speech-text models are typically trained with coarse captions or task-specific supervision, and scalable fine-grained style annotations are unavailable. We present FCaps, a large-scale dataset with fine-grained free-text style descriptions, encompassing 47k hours of speech and 19M fine-grained captions annotated via a novel end-to-end pipeline that directly grounds detailed captions in audio, thereby avoiding the error propagation caused by LLM-based rewriting in existing cascaded pipelines. Evaluations using LLM-as-a-judge demonstrate that our annotations surpass existing cascaded annotations in terms of correctness, coverage, and naturalness. Building on FCaps, we propose CLSP, a contrastive language-speech pre-trained model that integrates global and fine-grained supervision, enabling unified representations across multiple granularities. Extensive experiments demonstrate that CLSP learns fine-grained and multi-granular speech-text representations that perform reliably across global and fine-grained speech-text retrieval, zero-shot paralinguistic classification, and speech style similarity scoring, with strong alignment to human judgments. Code and dataset are publicly available at https://github.com/yfyeung/CLSP.

eess.AS↗
arXiv2026

Multiplexing Neural Audio Watermarks

Audio watermarking is essential for verifying speech authenticity, yet single-watermark schemes often struggle against sophisticated distortions such as neural reconstruction and adversarial attacks. To address this limitation, we introduce a multiplexing paradigm that combines multiple watermarking techniques to leverage their inherent complementarities. We explore both parallel and sequential multiplexing strategies and propose perceptual-adaptive time-frequency multiplexing (PA-TFM), a robust training-free approach. To further enhance performance, we introduce MaskNet, a novel model-based framework designed to learn effective time-domain multiplexing. Experimental results on the LibriSpeech and Common Voice datasets under 14 diverse attack types, including high-strength white-box and neural reconstruction attacks, demonstrate that both PA-TFM and MaskNet considerably outperform existing single-watermark baselines, establishing a resilient paradigm for real-world audio protection.

eess.AS↗
arXiv2026

Audio-Conditioned Diffusion LLMs for ASR and Deliberation Processing

Diffusion-based large language models (DLLMs) have recently attracted growing interest as an alternative to autoregressive decoders. In this work, we present an empirical study on using the diffusion-based large language model LLaDA for automatic speech recognition (ASR). We first investigate its use as an external deliberation-based processing module for Whisper-LLaMA transcripts. By leveraging the bidirectional attention and denoising capabilities of LLaDA, we explore random masking, low-confidence masking, and semi-autoregressive strategies, showing that Whisper-LLaDA substantially reduces WER compared with the baseline. On LibriSpeech, the best cascade system achieves 2.25%/4.94% WER on test-clean/test-other, representing a 12.3% relative improvement over the Whisper-LLaMA baseline on the test-other split. In contrast, a plain-text LLaDA without acoustic features fails to improve accuracy, highlighting the importance of audio-conditioned embeddings. We further evaluate Whisper-LLaDA as a standalone decoder for ASR with diffusion-based and semi-autoregressive decoding. Most experimental configurations achieve faster inference than the Whisper-LLaMA baseline, although recognition accuracy is slightly lower. These findings offer an empirical view of diffusion-based LLMs for ASR and point to promising directions for improvements. Code and model are open-sourced at https://github.com/liuzhan22/Diffusion-ASR.

eess.AS↗
arXiv2026

sleep2vec: Unified Cross-Modal Alignment for Heterogeneous Nocturnal Biosignals

Tasks ranging from sleep staging to clinical diagnosis traditionally rely on standard polysomnography (PSG) devices, bedside monitors and wearable devices, which capture diverse nocturnal biosignals (e.g., EEG, EOG, ECG, SpO$_2$). However, heterogeneity across devices and frequent sensor dropout pose significant challenges for unified modelling of these multimodal signals. We present \texttt{sleep2vec}, a foundation model for diverse and incomplete nocturnal biosignals that learns a shared representation via cross-modal alignment. \texttt{sleep2vec} is contrastively pre-trained on 42,249 overnight recordings spanning nine modalities using a \textit{Demography, Age, Site \& History-aware InfoNCE} objective that incorporates physiological and acquisition metadata (\textit{e.g.}, age, gender, recording site) to dynamically weight negatives and mitigate cohort-specific shortcuts. On downstream sleep staging and clinical outcome assessment, \texttt{sleep2vec} consistently outperforms strong baselines and remains robust to any subset of available modalities and sensor dropout. We further characterize, to our knowledge for the first time, scaling laws for nocturnal biosignals with respect to modality diversity and model capacity. Together, these results show that unified cross-modal alignment, coupled with principled scaling, enables label-efficient, general-purpose modelling of real-world nocturnal biosignals.

cs.LG↗
arXiv2026

Speech-Audio Compositional Attacks on Multimodal LLMs and Their Mitigation with SALMONN-Guard

Recent progress in LLMs has enabled understanding of audio signals, but has also exposed new safety risks arising from complex audio inputs that are inadequately handled by current safeguards. We introduce SACRED-Bench (Speech-Audio Composition for RED-teaming) to evaluate the robustness of LLMs under complex audio-based attacks. Unlike existing perturbation-based methods that rely on noise optimization or white-box access, SACRED-Bench exploits speech-audio composition to enable effective black-box attacks. SACRED-Bench adopts three composition mechanisms: (a) overlap of harmful and benign speech, (b) mixture of benign speech with harmful non-speech audio, and (c) multi-speaker dialogue. These mechanisms focus on evaluating safety in settings where benign and harmful intents co-occur within a single auditory scene. Moreover, questions in SACRED-Bench are designed to implicitly refer to content in the audio, such that no explicit harmful information appears in the text prompt alone. Experiments demonstrate that even Gemini 2.5 Pro, a state-of-the-art proprietary LLM with safety guardrails fully enabled, still exhibits a 66% attack success rate. To bridge this gap, we propose SALMONN-Guard, the first guard model that jointly inspects speech, audio, and text for safety judgments, reducing the attack success rate to 20%. Our results highlight the need for audio-aware defenses to ensure the safety of multimodal LLMs. The dataset and SALMONN-Guard checkpoints can be found at https://huggingface.co/datasets/tsinghua-ee/SACRED-Bench.

cs.SD↗
arXiv2026

Discovery and Reinforcement of Tool-Integrated Reasoning Chains via Rollout Trees

Tool-Integrated Reasoning has emerged as a key paradigm to augment Large Language Models (LLMs) with computational capabilities, yet integrating tool-use into long Chain-of-Thought (long CoT) remains underexplored, largely due to the scarcity of training data and the challenge of integrating tool-use without compromising the model's intrinsic long-chain reasoning. In this paper, we introduce DART (Discovery And Reinforcement of Tool-Integrated Reasoning Chains via Rollout Trees), a reinforcement learning framework that enables spontaneous tool-use during long CoT reasoning without human annotation. DART operates by constructing dynamic rollout trees during training to discover valid tool-use opportunities, branching out at promising positions to explore diverse tool-integrated trajectories. Subsequently, a tree-based process advantage estimation identifies and credits specific sub-trajectories where tool invocation positively contributes to the solution, effectively reinforcing these beneficial behaviors. Extensive experiments on challenging benchmarks like AIME and GPQA-Diamond demonstrate that DART significantly outperforms existing methods, successfully harmonizing tool execution with long CoT reasoning.

cs.CL↗
arXiv2025

Towards Effective and Efficient Non-autoregressive decoders for Conformer and LLM-based ASR using Block-based Attention Mask

Automatic speech recognition (ASR) systems often rely on autoregressive (AR) Transformer decoder architectures, which limit efficient inference parallelization due to their sequential nature. To this end, non-autoregressive (NAR) approaches aim primarily to achieve significant decoding speedup while the maintaining recognition accuracy that is comparable to AR baselines. This paper proposes a novel NAR block-based attention mask decoder (AMD) that effectively improves decoding efficiency while maintaining ASR accuracy, and also offering flexibility in balancing the performance-efficiency trade-off on both Conformer and large language model (LLM)-based ASR systems. The proposed AMD performs parallel inference within contiguous blocks of output labels while maintaining monotonic left-to-right prediction between blocks. A one-pass beam search algorithm is designed to dynamically fuse Connectionist Temporal Classification (CTC), AR decoder, and AMD probabilities. Experiments are conducted on normal speech LS960 and DBank elderly speech across: a) The Conformer encoder-decoder ASR system with filterbank input features; b) its integration with WavLM features; and c) further advancement by integrating an LLM-based decoder. On the LS960 task, the proposed AMD empowered tripartite decoder achieves decoding speedup ratios of up to 1.44x, 1.55x, and 2.31x under the three model configurations over the CTC + AR baselines, without statistically significant WER increases. When operating with real-time factors (RTFs) comparable to the baselines, the tripartite decoder produces statistically significant WER reductions of 0.19%, 0.62% and 0.13% absolute (4.3%, 16.3%, and 3.8% relative). Similar improvements are also obtained on the DBank task.

eess.AS↗
arXiv2025

Augmenting Open-Vocabulary Dysarthric Speech Assessment with Human Perceptual Supervision

Dysarthria is a speech disorder characterized by impaired intelligibility and reduced communicative effectiveness. Automatic dysarthria assessment provides a scalable, cost-effective approach for supporting the diagnosis and treatment of neurological conditions such as Parkinson's disease, Alzheimer's disease, and stroke. This study investigates leveraging human perceptual annotations from speech synthesis assessment as reliable out-of-domain knowledge for dysarthric speech assessment. Experimental results suggest that such supervision can yield consistent and substantial performance improvements in self-supervised learning pre-trained models. These findings suggest that perceptual ratings aligned with human judgments from speech synthesis evaluations represent valuable resources for dysarthric speech modeling, enabling effective cross-domain knowledge transfer.

eess.AS↗
arXiv2025

Towards General Auditory Intelligence: Large Multimodal Models for Machine Listening and Speaking

In the era of large language models (LLMs) and artificial general intelligence (AGI), computer audition must evolve beyond traditional paradigms to fully leverage the capabilities of foundation models, towards more comprehensive understanding, more natural generation and more human-like interaction. Audio, as a modality rich in semantic, emotional, and contextual cues, plays a vital role in achieving naturalistic and embodied machine intelligence. This survey provides a comprehensive review of recent progress in integrating audio into LLMs, with a focus on four key areas: audio comprehension, audio generation, speech-based interaction, and audio-visual understanding. We analyze how LLMs are reshaping audio perception and reasoning, enabling systems to understand sound at a deeper semantic level, generate expressive audio outputs, and engage in human-like spoken interaction. Furthermore, we explore how the fusion of audio and visual modalities enhances situational awareness and cross-modal reasoning, pushing the boundaries of multimodal intelligence. This survey not only synthesizes existing research but also identifies critical challenges and future directions for building audio-native AGI systems capable of perceiving, understanding, and interacting through sound as naturally as humans do.

eess.AS↗