arXiv subjects

Haibin Wu

Publications and source records attributed to Haibin Wu.

At least 19 recordsLinked to original sources

arXiv2026

GSPIM: A Temporal-Locality-Aware 4DGS Accelerator for PIM-Enabled Edge Devices

4D Gaussian Splatting (4DGS) enables high-quality real-time novel-view synthesis for dynamic scenes, supporting free-viewpoint video, mobile XR, and autonomous systems at the edge. Methods using explicit 4D distributions, keyframe interpolation, or anchor binding share two GPU data-movement bottlenecks. Temporal filtering follows model record loading, wasting LPDDR5 bandwidth on inactive data. Frame-isolated execution also overlooks highly overlapping active sets and depth relationships across adjacent frames, reloading shared attributes when working sets exceed on-chip cache capacity. To address these bottlenecks, we present GSPIM, a temporal-locality-aware 4DGS accelerator for PIM-enabled edge devices. Polymorphic PIM adapts a shared near-memory datapath to representation-specific field layouts and selection procedures. It filters and compacts valid data into contiguous inputs before the GPU accesses complete attributes, reducing ineffective transfers. Multi-Frame Rendering Dataflow reuses active attributes and stable depth relationships within a temporal window, reducing repeated work across frames. Hybrid Dataflow Scheduling overlaps near-memory data preparation with GPU rendering to reduce waiting. Evaluation combines a GPU-PIM model calibrated to Jetson AGX Orin 64 GB with a 1z DRAM physical implementation of the added circuits. Across three 4DGS methods and six dynamic scenes, GSPIM achieves a 4.15x geometric-mean speedup and a 4.99x geometric-mean energy-efficiency improvement over a fully optimized frame-by-frame GPU baseline. The maximum scene-level PSNR difference is 0.011 dB, and the added physical footprint is 18.7172 square millimeters across 32 LPDDR5 dies.

cs.AR↗

arXiv2026

Observation of Scaling of Higher-Order Flow in a Unitary Fermi Gas

Collective flow emerging from spatially anisotropic many-body systems is a fundamental manifestation of strongly interacting quantum matter, from ultracold quantum gases to the quark-gluon plasma created in relativistic heavy-ion collisions. Yet how collective flow emerges across different spatial harmonics and how dissipation modifies its evolution remain largely unexplored. Here we investigate the nonequilibrium expansion of a unitary Fermi gas initially confined in nearly homogeneous potentials with engineered angular deformations. By suddenly releasing the confinement, we resolve anisotropic flow harmonics up to the seventh order. Remarkably, after normalization and rescaling by the characteristic expansion timescale, the different harmonics and system sizes exhibit a universal early-time evolution. At longer times, this universality breaks down and we observe an approximately quadratic dependence of the harmonic attenuation on harmonic order, consistent with viscous acoustic scaling. Furthermore, temperature-dependent measurements reveal the role of shear viscosity in the dissipative evolution of higher-order flow. Our results open a new route to exploring the interplay between universal hydrodynamic expansion and dissipative transport, connecting collective dynamics in ultracold quantum gases with anisotropic flow in strongly interacting nuclear matter.

cond-mat.quant-gas↗

arXiv2026

SCARF: A Scene-Adaptive Depth-Guided G-3DGS Encoder Accelerator with Semantic Reuse and Fused Dataflow

Depth-guided, cost-volume-based Generalizable 3D Gaussian Splatting (G-3DGS) encoders reconstruct scenes as sets of Gaussian primitives directly from multi-view images without requiring per-scene optimization, thereby facilitating feed-forward novel-view synthesis on edge computing platforms. However, their shared encoder architecture presents two primary bottlenecks. First, the per-pixel depth search disregards semantic similarity within the 2D feature space, causing depth search operations to account for over 65% of memory traffic due to redundant exhaustive candidate scans. Second, the sequential pipeline of depth prediction followed by Gaussian generation neglects local 3D geometric continuity, resulting in more than 52% of generated Gaussians being redundant prior to instantiation. In this paper, we introduce SCARF, a dataflow-co-designed accelerator that aligns each bottleneck with a corresponding scene-level regularity. To mitigate the first bottleneck, Feature Similarity Depth Reuse reconceptualizes depth search as a problem of semantic locality: depth consistency is determined by affinity in feature space rather than physical address proximity. It transforms exhaustive per-pixel depth searches into anchor-centered local searches. To overcome the second bottleneck, Scene-Adaptive Early Sparsification disrupts the conventional serial depth-to-materialization boundary by probing each tile to infer local scene regularity. It then selectively activates only the minimally sufficient generation pathway, eliminating redundant Gaussian computations before primitive instantiation. On a 27.8 square millimeter 28 nm post-layout design, SCARF delivers a 2.94x geometric-mean end-to-end speedup with maximum PSNR degradation below 0.072%, 2.23 inferences per joule, and 34.5x GPU energy efficiency.

cs.AR↗

arXiv2026

What Does LALM Post-training Learn? Rethinking Audio Understanding and Reasoning Capabilities

Post-training often improves the performance of large audio-language models on audio understanding and reasoning benchmarks. However, these improvements may reflect adaptation to specific question formats, such as multiple-choice questions, rather than genuine advances in audio understanding and reasoning capabilities. To investigate what LALMs actually learn from post-training, we conduct controlled experiments that disentangle improvements in audio understanding from adaptation to specific question formats. Across different models and post-training methods, we find that much of the reported improvement persists even without informative audio, but largely disappears when the question format changes. These findings suggest that post-training often teaches models to exploit task-specific textual cues and answer patterns rather than developing generalizable audio understanding and reasoning capabilities.

cs.SD↗

arXiv2026

The NVVSpeech Challenge 2026: Overview and Lessons for Speech Understanding and Generation with Nonverbal Vocalizations

Nonverbal vocalizations (NVVs), such as laughter and sighs, convey meaning alongside words. NVV-aware speech systems must recognize and generate these events while preserving lexical accuracy and perceptual quality. Yet differences in annotation, resources, and evaluation complicate comparisons, and aggregate scores can obscure specific weaknesses. We review ten system descriptions from the NVVSpeech Challenge 2026, covering understanding and generation in Chinese and English across 16 event categories. Our analysis examines supervision construction, task adaptation, and inference-time or preference-based feedback. Results reveal persistent recognition difficulties with breath and gasp and trade-offs between event recognition and lexical accuracy, as well as between generation intelligibility and acoustic quality, with human listening providing complementary evaluation evidence. These findings identify priorities for advancing NVV-aware speech understanding, controllable generation, and comparable evaluation.

cs.SD↗

arXiv2026

Beyond Words: Towards Effective Modeling of Non-Verbal Vocalizations in ASR

Modern automatic speech recognition (ASR) systems excel at transcribing lexical content but often omit nonverbal vocalizations (NVs), such as laughter, breaths, coughs, and cries, that carry conversational and affective information. Modeling NVs in ASR is challenging because NV annotations are sparse and highly long-tailed, with frequent categories such as breaths and laughter dominating rarer events such as cries and coughs. We study three data-centric strategies for improving low-resource NV recognition: (1) a two-stage curriculum that first maps all NV events to a generic token and then fine-tunes on target categories; (2) inter-token transfer from high-resource events, such as laughter and breath, to rare events, such as crying; and (3) voice-conversion augmentation with class balancing. Experiments show that shared acoustic structure across vocal events can be exploited to improve rare-category detection while preserving lexical ASR quality.

eess.AS↗

arXiv2026

EmoRES-TTS: Residual-Enhanced Vector Steering for Emotional Speech Generation

Emotion-conditioned text-to-speech (TTS) models may fail to express the requested emotion reliably, and improving controllability by additional training is costly in both computation and emotion-labeled speech training data. We therefore study vector steering, a training-free approach that modifies the internal representations of a frozen model. CoCoEmo, a conventional vector steering method for emotion TTS, treats each emotion vector as an indivisible direction controlled by a single global strength, limiting adherence to the requested emotion. In this work, we first discover that an emotion vector can be decomposed into a shared component that moves speech away from neutral expression and a residual component that directs generation toward the requested emotion. Building on this finding, we propose Emotion Residual-Enhanced Steering for TTS (EmoRES), a novel method that controls the two components without retraining the backbone. On IEMOCAP, EmoRES outperforms CoCoEmo across all four objective emotion metrics on the IndexTTS-2 and CosyVoice2 backbones. Rank correlation improves by 26.13 and 12.97 percentage points, corresponding to relative gains of 118.8% and 33.1%, while emotion hit rate improves by 12.95 and 6.92 points, corresponding to relative gains of 20.1% and 9.8%. Human evaluation further shows a relative improvement up to 35.0% in the rate at which listeners correctly identified the dominant requested emotion and up to a 17.3% improvement in fidelity, while listeners prefer EmoRES for naturalness in up to 63.8% of pairwise comparisons. Component ablations further demonstrate that effective control benefits from preserving the shared component while strengthening the residual of the emotion steering vectors.

cs.SD↗

arXiv2026

The ISCSLP 2026 Real-World Audio-Visual Speech Enhancement Challenge: A Benchmark with Natural Mixtures and Degraded Video

Audio-visual speech enhancement (AVSE) uses a target speaker's visible articulation to recover that speaker's voice from overlapped speech. Yet most evaluation protocols rely on synthetic mixtures and reliable video. The ISCSLP 2026 Real-World AVSE Challenge addresses both gaps. Track~1 combines naturally recorded two-talker mixtures, which lack a clean reference, with reference-available remixes of the same speakers; Track~2 additionally degrades the target video in five ways and adds 3-m far-field recordings. Sixteen and twelve teams were ranked on speaker-disjoint test data by rank averaging over waveform fidelity, predicted quality, transcription accuracy, and speaker similarity. On Track~1 remixes, the best system reaches 12.7~dB SI-SDR and 0.85 STOI, but natural recordings remain harder: even the lowest CER rises from 9.0\% to 14.7\%. The leading systems use video mainly for speaker attribution rather than signal reconstruction, and the top two lose under 0.5~dB SI-SDR on Track~2. UTMOS and DNSMOS rank systems differently from the other metrics, so no single metric captures target-speech recovery. We release the baselines, evaluator, and official results.

eess.AS↗

arXiv2026

Phonon heat transport with squeezing-based symmetry breaking

The controllability of phonon thermal transport is fundamental for numerous technologies, from cooling high-performance chips to managing heat in quantum computing. Despite extensive efforts, on-demand, real-time control of phonon heat flow remains elusive, being fundamentally constrained by the temperature gradient. Here we achieve this long-sought phonon heat transport by introducing a novel mechanism using quantum squeezing in a cavity optomechanical system. We find that phonon squeezing of near-ground-state mechanical resonators via an optomechanically induced parametric process breaks the continuous U(1) rotation symmetry in phase space, and consequently the symmetry in the heat current structure. We reveal that heat flow under a constant temperature gradient can be deterministically amplified, reduced, or even reversed, a capability previously unattainable. With phonon squeezing, we achieve over twentyfold amplification of heat flow and reversal within 30 milliseconds. Importantly, quantum discord analysis reveals a direct connection between heat flow reversal and quantum correlation. Our results establish quantum squeezing as a versatile platform for on-demand phononic thermal control, opening avenues for active heat management in quantum devices and thermal logic circuits.

physics.optics↗

arXiv2026

CodecFake+: Codec-Based Resynthesized Data as a Proxy for Detecting CodecFake Speech

With the rapid advancement of neural audio codecs, codec-based speech generation (CoSG) systems have become highly powerful. Unfortunately, CoSG also enables the creation of highly realistic deepfake speech, making it easier to mimic an individual's voice and spread misinformation. We refer to this emerging deepfake speech generated by CoSG systems as CodecFake. Detecting such CodecFake is an urgent challenge, yet most existing systems primarily focus on detecting fake speech generated by traditional speech synthesis models. In this paper, we introduce CodecFake+, a large-scale dataset designed to advance CodecFake detection. To our knowledge, CodecFake+ is the largest dataset encompassing the most diverse range of codec architectures. The training set is generated through re-synthesis using 31 publicly available open-source codec models, while the evaluation set includes web-sourced data from 17 advanced CoSG models. We also propose a comprehensive taxonomy that categorizes codecs by their root components: vector quantizer, auxiliary objectives, and decoder types. Our proposed dataset and taxonomy enable detailed analysis at multiple levels to discern the key factors for successful CodecFake detection. At the individual codec level, we validate the effectiveness of using codec re-synthesized speech (CoRS) as training data for large-scale CodecFake detection. At the taxonomy level, we show that detection performance is strongest when the re-synthesis model incorporates disentanglement auxiliary objectives or a frequency-domain decoder. Furthermore, from the perspective of using all the CoRS training data, we show that our proposed taxonomy can be used to select better training data for improving detection performance. Overall, we envision that CodecFake+ will be a valuable resource for both general and fine-grained exploration to develop better anti-spoofing models against CodecFake.

cs.SD↗

arXiv2026

Mitigating Proxy-to-Wild Domain Gap in Deepfake Speech

Recent neural audio codec-based speech generation (CodecFake) produces highly realistic audio, posing a challenge to existing deepfake countermeasure models. While using codec resynthesized speech (CoRS) as proxy data improves performance, it often suffers from limited generalization. We propose Domain-Shift Feature Augmentation (DSFA), which simulates "in-the-wild" variations by transforming deterministic feature statistics into stochastic distributions during fine-tuning. To evaluate generalization, we further introduce Codec-based Speech Generation Extension Evaluation (CoSG ExtEval) dataset, a more challenging extension of the CoSG Eval (from CodecFake+) dataset, featuring 40 unseen generative models and long-form audio. Experimental results demonstrate that combining a post-trained SSL backbone with DSFA effectively narrows the proxy-to-wild domain gap. This approach achieves state-of-the-art performance across diverse CodecFake attacks in both CoSG Eval and CoSG ExtEval.

cs.SD↗

arXiv2026

JASTIN: Aligning LLMs for Zero-Shot Audio and Speech Evaluation via Natural Language Instructions

The rapid advancement of generative audio models has outpaced the development of robust evaluation methodologies. Existing objective metrics and general multimodal large language models (MLLMs) often struggle with domain generalization, zero-shot capabilities, and instructional flexibility. To address these bottlenecks, we propose JASTIN, a generalizable, instruction-driven audio evaluation framework that formulates audio assessment as a self-instructed reasoning task. JASTIN bridges a frozen high-performance audio encoder with a fine-tuned LLM backbone via a trainable audio adapter. To ensure robust zero-shot generalization, we introduce a comprehensive instruction following data preparation pipeline, incorporating Multi-Source, Multi-Task, Multi-Calibration, and Multi-Description data. Experimental results demonstrate that JASTIN achieves state-of-the-art Pearson and Spearman correlations with human subjective ratings. It consistently outperforms general MLLMs across speech, sound, music, and out-of-domain evaluation tasks without the need for task-specific retraining.

eess.AS↗

arXiv2026

Enhancing Conversational TTS with Cascaded Prompting and ICL-Based Online Reinforcement Learning

Conversational AI has made significant progress, yet generating expressive and controllable text-to-speech (TTS) remains challenging. Specifically, controlling fine-grained voice styles and emotions is notoriously difficult and typically requires massive amounts of heavily annotated training data. To overcome this data bottleneck, we present a scalable, data-efficient cascaded framework that pairs textual style tokens with human-curated, high-quality audio prompts. This approach enables single-shot adaptation to fine-grained speaking styles and character voices. In the context of TTS, this audio prompting acts as In-Context Learning (ICL), guiding the model's prosody and timbre without requiring massive parameter updates or large-scale retraining. To further enhance generation quality and mitigate hallucinations, we introduce a novel ICL-based online reinforcement learning (RL) strategy. This strategy directly optimizes the autoregressive prosody model using subjective aesthetic rewards while being constrained by Connectionist Temporal Classification (CTC) alignment to preserve intelligibility. Comprehensive human perception evaluations demonstrate significant improvements in both the naturalness and expressivity of the synthesized speech, establishing the efficacy of our ICL-based online RL approach.

eess.AS↗

arXiv2026

On The Landscape of Spoken Language Models: A Comprehensive Survey

The field of spoken language processing is undergoing a shift from training custom-built, task-specific models toward using and optimizing spoken language models (SLMs) which act as universal speech processing systems. This trend is similar to the progression toward universal language models that has taken place in the field of (text) natural language processing. SLMs include both "pure" language models of speech -- models of the distribution of tokenized speech sequences -- and models that combine speech encoders with text language models, often including both spoken and written input or output. Work in this area is very diverse, with a range of terminology and evaluation settings. This paper aims to contribute an improved understanding of SLMs via a unifying literature survey of recent work in the context of the evolution of the field. Our survey categorizes the work in this area by model architecture, training, and evaluation choices, and describes some key challenges and directions for future work.

cs.CL↗

arXiv2026

Joint Fullband-Subband Modeling for High-Resolution SingFake Detection

Rapid advances in singing voice synthesis have increased unauthorized imitation risks, creating an urgent need for better Singing Voice Deepfake (SingFake) Detection, also known as SVDD. Unlike speech, singing contains complex pitch, wide dynamic range, and timbral variations. Conventional 16 kHz-sampled detectors prove inadequate, as they discard vital high-frequency information. This study presents the first systematic analysis of high-resolution (44.1 kHz sampling rate) audio for SVDD. We propose a joint fullband-subband modeling framework: the fullband captures global context, while subband-specific experts isolate fine-grained synthesis artifacts unevenly distributed across the spectrum. Experiments on the WildSVDD dataset demonstrate that high-frequency subbands provide essential complementary cues. Our framework significantly outperforms 16 kHz-sampled models, proving that high-resolution audio and strategic subband integration are critical for robust in-the-wild detection.

cs.SD↗

arXiv2026

Aligning Paralinguistic Understanding and Generation in Speech LLMs via Multi-Task Reinforcement Learning

Speech large language models (LLMs) observe paralinguistic cues such as prosody, emotion, and non-verbal sounds--crucial for intent understanding. However, leveraging these cues faces challenges: limited training data, annotation difficulty, and models exploiting lexical shortcuts over paralinguistic signals. We propose multi-task reinforcement learning (RL) with chain-of-thought prompting that elicits explicit affective reasoning. To address data scarcity, we introduce a paralinguistics-aware speech LLM (PALLM) that jointly optimizes sentiment classification from audio and paralinguistics-aware response generation via a two-stage pipeline. Experiments demonstrate that our approach improves paralinguistics understanding over both supervised baselines and strong proprietary models (Gemini-2.5-Pro, GPT-4o-audio) by 8-12% on Expresso, IEMOCAP, and RAVDESS. The results show that modeling paralinguistic reasoning with multi-task RL is crucial for building emotionally intelligent speech LLMs.

cs.CL↗

arXiv2026

SLM-S2ST: A multimodal language model for direct speech-to-speech translation

Speech-aware language models (LMs) have demonstrated capabilities in understanding spoken language while generating text-based responses. However, enabling them to produce speech output efficiently and effectively remains a challenge. In this paper, we present SLM-S2ST, a multimodal LM for direct speech-to-speech translation (S2ST), built on the open-source Phi4-MM model. SLM-S2ST extends its predecessor by generating translated speech using an audio transformer head that predicts audio tokens with a delay relative to text tokens, followed by a streaming vocoder for waveform synthesis. Our experimental results on the CVSS-C dataset demonstrate SLM-S2ST's superior performance, significantly surpassing existing baseline models trained on the same dataset. Furthermore, when we scale up the training data and the model size, SLM-S2ST reaches on-par performance with the current SOTA model.

eess.AS↗

arXiv2026

Towards Efficient Speech-Text Jointly Decoding within One Speech Language Model

Speech language models (Speech LMs) enable end-to-end speech-text modeling within a single model, offering a promising direction for spoken dialogue systems. The choice of speech-text jointly decoding paradigm plays a critical role in performance, efficiency, and alignment quality. In this work, we systematically compare representative joint speech-text decoding strategies, including the interleaved, and parallel generation paradigms, under a controlled experimental setup using the same base language model, speech tokenizer and training data. Our results show that the interleaved approach achieves the best alignment. However it suffers from slow inference due to long token sequence length. To address this, we propose a novel early-stop interleaved (ESI) pattern that not only significantly accelerates decoding but also yields slightly better performance. Additionally, we curate high-quality question answering (QA) datasets to further improve speech QA performance.

eess.AS↗