arXiv subjects

Kazuhiro Nakadai

Publications and source records attributed to Kazuhiro Nakadai.

At least 19 recordsLinked to original sources

arXiv2026

UNITE-AUDIO: Joint Learning of Continuous Tokenization and Latent Flow Matching for Text-to-Audio Generation

Text-to-audio (TTA) generation aims to synthesize realistic audio that faithfully reflects natural-language descriptions. Most TTA systems adopt a two-stage latent paradigm: an audio tokenizer is optimized for reconstruction and then frozen, after which a generative model is trained in the resulting latent space. However, reconstruction-oriented representations may be suboptimal for generation, motivating joint representation and generative learning. To this end, we introduce Unite-Audio, to our knowledge, is the first to jointly learn continuous audio representations and latent flow matching for TTA. By coupling reconstruction with self-supervised generative prediction, Unite-Audio allows the generative objective to directly shape the latent space rather than treating it as a fixed intermediate representation. We further employ Flow-GRPO post-training to improve text-conditioned generation. Experiments show competitive TTA performance with a compact latent flow model, while ablation studies confirm the benefit of jointly learning the audio representation and generative model. Audio samples are available at https://runwushi.github.io/Unite-Audio.

eess.AS↗

arXiv2026

Joint Residual Reweighting for Classifier Free Guidance in Flow-Matching Zero-Shot TTS

Classifier-free guidance (CFG) is widely used in flow-matching-based zero-shot text-to-speech (TTS), where generation is conditioned on text content and a speech prompt. Standard CFG uses a single guidance weight for their joint conditional effect, while branch-selective guidance emphasizes text or speaker conditioning and can introduce a trade-off between text accuracy and speaker similarity. In this paper, we revisit CFG under independently masked conditions and decompose the guidance field into text, speaker, and joint residuals. We show that condition-specific branch differences couple the joint residual with the corresponding text or speaker residual under a shared weight. Trajectory analysis further shows that the joint residual varies over flow time and contains information that cannot be represented by reweighting the text and speaker residuals alone. Based on these observations, we propose joint residual reweighting, which assigns independent weights to the three residuals. Experiments on F5-TTS, CosyVoice2, and GLM-TTS across three evaluation sets show overall improvements in speaker similarity and text accuracy over the default CFG settings without retraining.

eess.AS↗

arXiv2026

Unsupervised Single-Channel Speech Separation with Diffusion under Speaker-Embedding Guidance

Speech separation is a fundamental task in audio processing, typically addressed with fully supervised systems trained on paired mixtures. While effective, such systems typically rely on synthetic data pipelines, which may not reflect real-world conditions. Instead, we revisit the source-model paradigm, training a diffusion generative model solely on anechoic speech and formulating separation as a diffusion inverse problem. However, unconditional diffusion models lack speaker-level conditioning, they can capture local acoustic structure but produce temporally inconsistent speaker identities in separated sources. To address this limitation, we propose Speaker-Embedding guidance that, during the reverse diffusion process, maintains speaker coherence within each separated track while driving embeddings of different speakers further apart. In addition, we propose a new separation-oriented solver tailored for speech separation, and both strategies effectively enhance performance on the challenging task of unsupervised source-model-based speech separation, as confirmed by extensive experimental results. Audio samples and code are available at https://runwushi.github.io/UnSepDiff_demo.

eess.AS↗

arXiv2026

Exploring Efficient Waveform Diffusion Models for Foley Sound Generation

Recent advances in diffusion models have enabled high-fidelity Foley sound generation directly in the waveform space. Existing waveform diffusion models primarily rely on time-domain architectures, such as CNN-based U-Nets and DiffWave-style models, or frequency-domain Transformers modeling temporal dependencies. However, these systems are typically built with large model capacities and substantial computational costs, leaving compact and efficient waveform diffusion architectures largely underexplored. In this work, we introduce a Dual-Path (DP) architecture for waveform diffusion that performs dimension-wise self-attention along both subband and frame axes in the time-frequency domain. This DP design enables fine-grained temporal-spectral modeling while maintaining high efficiency. Based on the proposed DP backbone, we develop two variants: DP-DiT and DP-U-Net. Experiments on the DCASE and FSD-Kaggle2018 datasets demonstrate their superior performance. Notably, the 3M parameter variant achieves performance comparable to models with more than 50M parameters. Audio samples are available at https://samplesdemo.github.io/DP-Foley/.

eess.AS↗

arXiv2026

From Sign Language Generation to Humanoid Execution: Vision-Language Guided Retargeting with Collision Mitigation

Recent sign language generation (SLG) systems increasingly output dense 3D body representations, which better preserve full-body kinematics and geometry for downstream embodiment on humanoid robots. However, these generated motions frequently exhibit self-intersections such as hand-hand and hand-torso penetration. While such artifacts may be tolerated in offline rendering, they become critical in humanoid execution as they lead to infeasible inverse-kinematics (IK) solutions, collisions, and unstable retargeted trajectories. We present a system-level framework that bridges SLG outputs to humanoid joint-space execution via two components. First, we introduce a volumetric SMPL-X collision-mitigation module that projects generated signing motions toward physically plausible configurations while minimally deviating from the original trajectory. Second, we propose a vision-language-guided retargeting algorithm built on an IK backbone: a VLM serves as a visual critic over rendered humanoid motion, identifies embodiment-specific failure modes, and triggers targeted task-space corrections. Our results highlight collision handling and perception-guided refinement as key missing components for reliable humanoid signing.

cs.RO↗

arXiv2026

What Do Neural Networks Learn for TDOA Estimation? A Cross-Architecture Probing Study

Neural networks outperform classical GCC-PHAT for Time-Difference-of-Arrival (TDOA) estimation in noise and reverberation, yet their internal strategy remains unexplored. To uncover it, we turn GCC-PHAT's mathematical steps into diagnostic targets, probing hidden layers of three architectures (MLP, CNN, Transformer) and complementing with gradient attribution and causal frequency masking. We find that cross-power computation consistently emerges across all architectures and conditions, while PHAT whitening, the defining step of GCC-PHAT, fails to emerge. Instead, networks learn a magnitude-aware frequency weighting that preserves per-frequency reliability information discarded by PHAT. This makes PHAT an information bottleneck: removing it from both classical and neural GCC pipelines improves performance under additive noise. On real-world reverberant data, PHAT remains the best classical weighting, but end-to-end networks achieve lower error by learning data-adaptive weighting.

cs.SD↗

arXiv2026

Fast-SDE: Efficient Single-Microphone Sound Source Distance Estimation in Reverberant Environments

Sound source distance estimation (SDE) is a critical capability in human-robot interaction. An inappropriate interaction distance not only reduces the reliability of speech acquisition and understanding, but also compromises the naturalness and comfort of the interaction. Most existing SDE methods rely on microphone arrays, however, multi-microphone systems typically require careful hardware synchronization, geometric calibration, and additional space and computational resources, which limits applicability to size-constrained and computability-limited embodied platforms. To alleviate these issues, we propose Fast-SDE, a lightweight single-microphone SDE framework that is suited for deployment on robot platforms with limited computational resources and strict size constraints. Specifically, Fast-SDE employs a subband-based backbone that decomposes the frequency axis into multiple subbands, rather than processing the entire spectrum with a wide full-band backbone. A shared subband encoder then maps each subband to a compact latent representation and learns the relationship between acoustic structure and time-frequency patterns. Finally, a lightweight regression head converts the fused subband representations into the estimated distance. Extensive simulation and real-world experiments demonstrate the merits of the proposed method. To benefit the broader research community, we have open-sourced our code at https://github.com/JiangWAV/FAST-SDE.

cs.SD↗

arXiv2026

Weakly Supervised Detection and Temporal Localization of Whale Calls in Long-Duration Bioacoustic Data

Passive acoustic monitoring (PAM) systems generate continuous recordings spanning months, yet automated bioacoustic analysis of whale calls requires two separate annotation efforts: binary presence labels for classification and precise temporal boundaries for localization. A binary label for a multi-minute recording can be assigned in seconds, but timestamping every call within it requires hours of expert effort. Providing both is infeasible at operational scale. We present DSMIL-LocNet, a weakly supervised multiple instance learning (MIL) framework that performs both classification and temporal localization using only recording-level presence/absence labels. Our dual-stream architecture integrates spectral and temporal features to process recordings of 2--30 minutes without the temporal compression that degrades existing CNN methods on long inputs. On the AcousticTrends BlueFinLibrary, DSMIL-LocNet achieves F1 scores of 0.88--0.91 on recordings of 300--1800s, where fully supervised CNN baselines degrade to 0.19--0.64. It also provides temporal localization that these baselines cannot produce without frame-level annotation. Code: https://github.com/Ragib-Amin-Nihal/DSMIL-Loc

cs.SD↗

arXiv2026

Ecologically-Constrained Task Arithmetic for Multi-Taxa Bioacoustic Classifiers Without Shared Data

Training data for bioacoustics is scattered across taxa, regions, and institutions. Centralizing it all is often infeasible. We show that independently fine-tuned BEATs encoders can be composed into a unified 661-species classifier via task vector arithmetic without sharing data. We find that bioacoustic task vectors are near-orthogonal (cosine 0.01-0.09). Their separation aligns closely with spectral distribution distance, a gradient consistent with the acoustic niche hypothesis. This geometry makes simple averaging optimal while sign-conflict methods reduce accuracy by one to six percentage points. Composition also creates an asymmetric gap: species-rich groups lose accuracy relative to joint training while underrepresented taxa gain, a redistribution useful for equitable biodiversity monitoring. We verify linear mode connectivity across all taxonomic pairs, demonstrate zero-shot transfer to new regions, and identify domain negation as a boundary condition where composition fails. These results enable a collaborative paradigm for bioacoustics where institutions share only task vectors to assemble multi-taxa classifiers, preserving data privacy.

cs.SD↗

arXiv2026

The Talking Robot: Distortion-Robust Acoustic Models for Robot-Robot Communication

We present Artoo, a learned acoustic communication system for robots that replaces hand-designed signal processing with end-to-end co-trained neural networks. Our system pairs a lightweight text-to-speech (TTS) transmitter (1.18M parameters) with a conformer-based automatic speech recognition (ASR) receiver (938K parameters), jointly optimized through a differentiable channel. Unlike human speech, robot-to-robot communication is paralinguistics-free: the system need not preserve timbre, prosody, or naturalness, only maximize decoding accuracy under channel distortion. Through a three-phase co-training curriculum, the TTS transmitter learns to produce distortion-robust acoustic encodings that surpass the baseline under noise, achieving 8.3% CER at 0 dB SNR. The entire system requires only 2.1M parameters (8.4 MB) and runs in under 13 ms end-to-end on a CPU, making it suitable for deployment on resource-constrained robotic platforms.

cs.RO↗

arXiv2026

Pattern Enhanced Multi-Turn Jailbreaking: Exploiting Structural Vulnerabilities in Large Language Models

Large language models (LLMs) remain vulnerable to multi-turn jailbreaking attacks that exploit conversational context to bypass safety constraints gradually. These attacks target different harm categories through distinct conversational approaches. Existing multi-turn methods often rely on heuristic or ad hoc exploration strategies, providing limited insight into underlying model weaknesses. The relationship between conversation patterns and model vulnerabilities across harm categories remains poorly understood. We propose Pattern Enhanced Chain of Attack (PE-CoA), a framework of five conversation patterns to construct multi-turn jailbreaks through natural dialogue. Evaluating PE-CoA on twelve LLMs spanning ten harm categories, we achieve state-of-the-art performance, uncovering pattern-specific vulnerabilities and LLM behavioral characteristics: models exhibit distinct weakness profiles, defense to one pattern does not generalize to others, and model families share similar failure modes. These findings highlight limitations of safety training and indicate the need for pattern-aware defenses. Code available on: https://github.com/Ragib-Amin-Nihal/PE-CoA

cs.CL↗

arXiv2025

Unsupervised Single-Channel Audio Separation with Diffusion Source Priors

Single-channel audio separation aims to separate individual sources from a single-channel mixture. Most existing methods rely on supervised learning with synthetically generated paired data. However, obtaining high-quality paired data in real-world scenarios is often difficult. This data scarcity can degrade model performance under unseen conditions and limit generalization ability. To this end, in this work, we approach this problem from an unsupervised perspective, framing it as a probabilistic inverse problem. Our method requires only diffusion priors trained on individual sources. Separation is then achieved by iteratively guiding an initial state toward the solution through reconstruction guidance. Importantly, we introduce an advanced inverse problem solver specifically designed for separation, which mitigates gradient conflicts caused by interference between the diffusion prior and reconstruction guidance during inverse denoising. This design ensures high-quality and balanced separation performance across individual sources. Additionally, we find that initializing the denoising process with an augmented mixture instead of pure Gaussian noise provides an informative starting point that significantly improves the final performance. To further enhance audio prior modeling, we design a novel time-frequency attention-based network architecture that demonstrates strong audio modeling capability. Collectively, these improvements lead to significant performance gains, as validated across speech-sound event, sound event, and speech separation tasks.

eess.AS↗

arXiv2025

Dialect Identification Using Resource-Efficient Fine-Tuning Approaches

Dialect Identification (DI) is a task to recognize different dialects within the same language from a speech signal. DI can help to improve the downstream speech related tasks even when speakers have a strong dialect. However, fine-tuning a speech model for tasks like DI is expensive in terms of computation cost and memory requirement. Recent studies have explored fine-tuning pre-trained speech models for tasks like DI using Parameter-Efficient Fine-Tuning (PEFT) methods, which offer parameter efficiency but limited improvement in memory efficiency and training speed. To address these challenges, we explore Memory-Efficient Fine-Tuning (MEFT) methods, originally proposed for language processing, and apply them to the general-purpose pre-trained speech model. We then comprehensively analyze the GPU memory usage and fine-tuning speed based on various MEFT methods. As a case study, we fine-tune the Whisper model to identify six Mandarin subdialects from the KeSpeech dataset, reducing GPU memory usage by up to 73.25% and accelerating training speed by a factor of 2.1, while maintaining accuracy comparable to vanilla fine-tuning and PEFT methods.

cs.CL↗

arXiv2025

Cross-Attention with Confidence Weighting for Multi-Channel Audio Alignment

Multi-channel audio alignment is a key requirement in bioacoustic monitoring, spatial audio systems, and acoustic localization. However, existing methods often struggle to address nonlinear clock drift and lack mechanisms for quantifying uncertainty. Traditional methods like Cross-correlation and Dynamic Time Warping assume simple drift patterns and provide no reliability measures. Meanwhile, recent deep learning models typically treat alignment as a binary classification task, overlooking inter-channel dependencies and uncertainty estimation. We introduce a method that combines cross-attention mechanisms with confidence-weighted scoring to improve multi-channel audio synchronization. We extend BEATs encoders with cross-attention layers to model temporal relationships between channels. We also develop a confidence-weighted scoring function that uses the full prediction distribution instead of binary thresholding. Our method achieved first place in the BioDCASE 2025 Task 1 challenge with 0.30 MSE average across test datasets, compared to 0.58 for the deep learning baseline. On individual datasets, we achieved 0.14 MSE on ARU data (77% reduction) and 0.45 MSE on zebra finch data (18% reduction). The framework supports probabilistic temporal alignment, moving beyond point estimates. While validated in a bioacoustic context, the approach is applicable to a broader range of multi-channel audio tasks where alignment confidence is critical. Code available on: https://github.com/Ragib-Amin-Nihal/BEATsCA

cs.SD↗

arXiv2025

Knowledge-Augmented Vision Language Models for Underwater Bioacoustic Spectrogram Analysis

Marine mammal vocalization analysis depends on interpreting bioacoustic spectrograms. Vision Language Models (VLMs) are not trained on these domain-specific visualizations. We investigate whether VLMs can extract meaningful patterns from spectrograms visually. Our framework integrates VLM interpretation with LLM-based validation to build domain knowledge. This enables adaptation to acoustic data without manual annotation or model retraining.

cs.CV↗

arXiv2025

From Blurry to Brilliant Detection: YOLO-Based Aerial Object Detection with Super Resolution

Aerial object detection presents challenges from small object sizes, high density clustering, and image quality degradation from distance and motion blur. These factors create an information bottleneck where limited pixel representation cannot encode sufficient discriminative features. B2BDet addresses this with a two-stage framework that applies domain-specific super-resolution during inference, followed by detection using an enhanced YOLOv5 architecture. Unlike training-time super-resolution approaches that enhance learned representations, our method recovers visual information from each input image. The approach combines aerial-optimized SRGAN fine-tuning with architectural innovations including an Efficient Attention Module (EAM) and Cross-Layer Feature Pyramid Network (CLFPN). Evaluation across four aerial datasets shows performance gains, with VisDrone achieving 52.5% mAP using only 27.7M parameters. Ablation studies show that super-resolution preprocessing contributes +2.6% mAP improvement while architectural enhancements add +2.9%, yielding +5.5% total improvement over baseline YOLOv5. The method achieves computational efficiency with 53.8% parameter reduction compared to recent approaches while achieving strong small object detection performance.

cs.CV↗

arXiv2025

Single-Microphone-Based Sound Source Localization for Mobile Robots in Reverberant Environments

Accurately estimating sound source positions is crucial for robot audition. However, existing sound source localization methods typically rely on a microphone array with at least two spatially preconfigured microphones. This requirement hinders the applicability of microphone-based robot audition systems and technologies. To alleviate these challenges, we propose an online sound source localization method that uses a single microphone mounted on a mobile robot in reverberant environments. Specifically, we develop a lightweight neural network model with only 43k parameters to perform real-time distance estimation by extracting temporal information from reverberant signals. The estimated distances are then processed using an extended Kalman filter to achieve online sound source localization. To the best of our knowledge, this is the first work to achieve online sound source localization using a single microphone on a moving robot, a gap that we aim to fill in this work. Extensive experiments demonstrate the effectiveness and merits of our approach. To benefit the broader research community, we have open-sourced our code at https://github.com/JiangWAV/single-mic-SSL.

cs.RO↗

arXiv2025

Observability-Aware Active Calibration of Multi-Sensor Extrinsics for Ground Robots via Online Trajectory Optimization

Accurate calibration of sensor extrinsic parameters for ground robotic systems (i.e., relative poses) is crucial for ensuring spatial alignment and achieving high-performance perception. However, existing calibration methods typically require complex and often human-operated processes to collect data. Moreover, most frameworks neglect acoustic sensors, thereby limiting the associated systems' auditory perception capabilities. To alleviate these issues, we propose an observability-aware active calibration method for ground robots with multimodal sensors, including a microphone array, a LiDAR (exteroceptive sensors), and wheel encoders (proprioceptive sensors). Unlike traditional approaches, our method enables active trajectory optimization for online data collection and calibration, contributing to the development of more intelligent robotic systems. Specifically, we leverage the Fisher information matrix (FIM) to quantify parameter observability and adopt its minimum eigenvalue as an optimization metric for trajectory generation via B-spline curves. Through planning and replanning of robot trajectory online, the method enhances the observability of multi-sensor extrinsic parameters. The effectiveness and advantages of our method have been demonstrated through numerical simulations and real-world experiments. For the benefit of the community, we have also open-sourced our code and data at https://github.com/AISLAB-sustech/Multisensor-Calibration.

cs.RO↗