arXiv subjects

Yoshiki Masuyama

Publications and source records attributed to Yoshiki Masuyama.

At least 19 recordsLinked to original sources

arXiv2026

Evaluating Inference-time Algorithms for Semantic Sound Scene Segmentation

Spatial semantic segmentation of sound scenes (S5) involves the detection and extraction of target sound events in audio files. However, in typical detection-extraction pipelines, errors in the detection module propagate to the extraction module, degrading overall performance. In this work, we develop a multichannel detection-extraction model and evaluate inference-time algorithms to improve the class detection and target sound extraction in a multi-stage setup. We evaluate two fitness functions: binary cross entropy and mixture consistency; two relabeling strategies: naive and conditional confusion matrix relabeling; and three source estimate evaluation models: a multi-label classifier, a fine-tuned single-source classifier, and an off-the-shelf audio judge. We thoroughly evaluate the impact of these design choices on the DCASE 2025 Task 4 dataset, and validate entropy-based gating of inference-time updates on the held-out evaluation set, laying the groundwork for inference-time updates of S5 systems in real-world scenarios.

eess.AS↗

arXiv2026

Transcript-Supervised Post-Training of Generative Speech Enhancement on Real Recordings via Reinforce Adjoint Matching

We adapt Reinforce Adjoint Matching (RAM), a reward-based post-training method, to generative speech enhancement (SE). Starting from a pretrained SE model, RAM tilts the model's conditional distribution toward outputs with higher reward. During training, the current model generates enhanced speech on-policy, evaluates each generated endpoint with a potentially non-differentiable reward, and analytically re-noises the endpoint to construct inputs for a reward-guided regression objective. This enables post-training directly on real recordings using weak supervision, such as text transcripts, without requiring paired clean speech targets or reward gradients. We investigate word error rate (WER)-based post-training and whether recognition performance can be improved without compromising perceptual speech quality. Experiments on real CHiME-4 recordings reduce WER by 5.08 percentage points relative to pretrained FlowSE without reducing any of the reported non-intrusive speech quality metrics. A subjective listening test at the default reward scale finds no statistically significant preference between the post-trained and pretrained models.

eess.AS↗

arXiv2026

Anomalous Sound Detection Meets Noise-Aware Self-Supervised Learning

In this paper, we introduce noise-aware self-supervised learning (NA-SSL) models for noise-aware anomalous sound detection (NA-ASD). NA-ASD is an ASD task with two-channel audio recordings, where one microphone is located close to the target machine and the other is located farther away to capture noise. For this task, we simulate two-channel recordings using diverse audio datasets and train NA-SSL models to extract clean SSL representations of the close-microphone signal by using the far-microphone recording dominated by background noise as auxiliary information. The NA-SSL models are then used as frontends in the standard ASD framework. Our experimental evaluation on the DCASE 2026 Challenge Task 2 development dataset demonstrates the effectiveness of the NA-SSL framework across three base SSL models (BEATs, EAT, and Dasheng), both with and without discriminative fine-tuning. Furthermore, the challenge results proved the effectiveness of the proposed approach, where the NA-BEATs system won the challenge by a large margin, achieving an official score of 70.24%, while the second-place system achieved 65.46%.

eess.AS↗

arXiv2026

Downstream-Task-Aware Unified Source Separation

Task-aware unified source separation (TUSS) enables a single model to handle diverse separation tasks by conditioning on input prompts. However, conventional TUSS does not account for downstream task requirements, such as whether the enhanced speech will be used for human listening or automatic speech recognition (ASR). In this paper, we propose a prompt extension framework for TUSS that incorporates downstream task information into the input prompts and switches the loss function according to the given prompt during training, enabling outputs with different signal characteristics at inference time. Specifically, we introduce an ASR-dedicated prompt paired with a regularized loss function that reduces speech artifacts to improve ASR robustness, while the standard prompt is paired with the conventional SNR loss function. Experiments on the LibriSpeech and JNAS corpora demonstrate that the proposed joint-training scheme enables a single model to improve ASR performance over noisy input across a wide range of SNR conditions by selecting the ASR-dedicated prompt, while maintaining general speech enhancement quality when the standard prompt is used.

eess.AS↗

arXiv2026

NABEATs: Noise-Aware Audio Representation Learning

We propose the concept of noise-aware audio self-supervised learning (SSL), whose goal is to encode audio mixtures while suppressing undesired noise, and present Noise-Aware BEATs (NABEATs) as a BEATs-based realization of this framework. Audio SSL models are designed to handle a wide range of audio signals. Consequently, under noisy conditions, they cannot effectively focus on the target sounds relevant to a downstream task, resulting in degraded performance. To address this issue, NABEATs is trained to estimate clean BEATs representations from a noisy audio signal with an auxiliary reference noise input. This reference noise enables the model to account for specific noise characteristics at inference time, thereby achieving better generalization across operating environments. Our experimental evaluations demonstrate that NABEATs significantly improves performance of various downstream tasks under noisy conditions and also generalizes well to unseen noise types.

eess.AS↗

arXiv2026

Technical Report for MERL's Real-TSE Challenge Submission

Target speech extraction (TSE) has largely been dominated by neural network-based approaches trained and evaluated on synthetic fully overlapped data. The Real-TSE Challenge aims to advance performance on real-world far-field noisy and reverberant recordings. This technical report describes MERL's submission to the Real-TSE Challenge. Rather than proposing a novel model architecture, we built upon the baseline model and focused primarily on data preparation and cleaning. Our system was trained in four stages, beginning with pre-training on fully overlapped mixtures and simulated multi-talker conversations with noise and reverberation applied to both the mixture and the enrollment utterances. We then adapted the model to real-world conditions using noisy far-field recordings with pseudo-targets derived from processed close-talk microphone signals. Our submission achieved first place in the second track, demonstrating the critical importance of high-quality data preparation. Furthermore, we observed that DNSMOS and speaker similarity are susceptible to over-optimization, motivating an investigation of their robustness using adversarial attacks. The results show that both metrics can be driven to extreme values without degrading the token error rate or the VAD-based F1 score.

eess.AS↗

arXiv2026

Predictive-Generative Drift Decomposition for Speech Enhancement and Separation

We propose a plug-and-play framework for speech enhancement and separation that augments predictive methods with a generative speech prior. Our approach, termed Stochastic Interpolant Prior for Speech (SIPS), builds on stochastic interpolants and leverages their flexibility to bridge predictive and generative modeling. Specifically, we decompose the interpolation dynamics into a task-specific drift and a stochastic denoising component, allowing a predictive estimate to be integrated directly into the generative sampling process. This results in a mathematically grounded framework for combining strong pretrained predictors with the expressive power of generative models. To this end, we train a score model using only clean speech, yielding a degradation-agnostic prior that can be reused across tasks. During inference, the predictor provides a deterministic drift that steers the sampling process toward a task-consistent estimate, while the score model preserves perceptual naturalness. Unlike prior hybrid approaches, which typically rely on architecture-specific conditioning and are tied to particular predictors or degradation settings, SIPS provides a unified framework that generalizes across predictors and additive degradation tasks. We demonstrate its effectiveness for both speech enhancement and speech separation using recent predictors such as SEMamba and FlexIO. The proposed method consistently improves perceptual quality, achieving gains up +1.0 NISQA for speech separation.

eess.AS↗

arXiv2026

Velocity Potential Neural Field for Efficient Ambisonics Impulse Response Modeling

First-order Ambisonics (FOA) is a standard spatial audio format based on spherical harmonic decomposition. Its zeroth- and first-order components capture the sound pressure and particle velocity, respectively. Recently, physics-informed neural networks have been applied to the spatial interpolation of FOA signals, regularizing the network outputs based on soft penalty terms derived from physical principles, e.g., the linearized momentum equation. In this paper, we reformulate the task so that the predicted FOA signal automatically satisfies the linearized momentum equation. Our network approximates a scalar function called velocity potential, rather than the FOA signal itself. Then, the FOA signal can be readily recovered through the partial derivatives of the velocity potential with respect to the network inputs (i.e., time and microphone position) according to physics of sound propagation. By deriving the four channels of FOA from the single-channel velocity potential, the reconstructed signal follows the physical principle at any time and position by construction. Experimental results on room impulse response reconstruction confirm the effectiveness of the proposed framework.

cs.SD↗

arXiv2025

Robot Confirmation Generation and Action Planning Using Long-context Q-Former Integrated with Multimodal LLM

Human-robot collaboration towards a shared goal requires robots to understand human action and interaction with the surrounding environment. This paper focuses on human-robot interaction (HRI) based on human-robot dialogue that relies on the robot action confirmation and action step generation using multimodal scene understanding. The state-of-the-art approach uses multimodal transformers to generate robot action steps aligned with robot action confirmation from a single clip showing a task composed of multiple micro steps. Although actions towards a long-horizon task depend on each other throughout an entire video, the current approaches mainly focus on clip-level processing and do not leverage long-context information. This paper proposes a long-context Q-former incorporating left and right context dependency in full videos. Furthermore, this paper proposes a text-conditioning approach to feed text embeddings directly into the LLM decoder to mitigate the high abstraction of the information in text by Q-former. Experiments with the YouCook2 corpus show that the accuracy of confirmation generation is a major factor in the performance of action planning. Furthermore, we demonstrate that the long-context Q-former improves the confirmation and action planning by integrating VideoLLaMA3.

cs.RO↗

arXiv2025

SUNAC: Source-aware Unified Neural Audio Codec

Neural audio codecs (NACs) provide compact representations that can be leveraged in many downstream applications, in particular large language models. Yet most NACs encode mixtures of multiple sources in an entangled manner, which may impede efficient downstream processing in applications that need access to only a subset of the sources (e.g., analysis of a particular type of sound, transcription of a given speaker, etc). To address this, we propose a source-aware codec that encodes individual sources directly from mixtures, conditioned on source type prompts. This enables user-driven selection of which source(s) to encode, including separately encoding multiple sources of the same type (e.g., multiple speech signals). Experiments show that our model achieves competitive resynthesis and separation quality relative to a cascade of source separation followed by a conventional NAC, with lower computational cost.

eess.AS↗

arXiv2025

Recent Trends in Distant Conversational Speech Recognition: A Review of CHiME-7 and 8 DASR Challenges

The CHiME-7 and 8 distant speech recognition (DASR) challenges focus on multi-channel, generalizable, joint automatic speech recognition (ASR) and diarization of conversational speech. With participation from 9 teams submitting 32 diverse systems, these challenges have contributed to state-of-the-art research in the field. This paper outlines the challenges' design, evaluation metrics, datasets, and baseline systems while analyzing key trends from participant submissions. From this analysis it emerges that: 1) Most participants use end-to-end (e2e) ASR systems, whereas hybrid systems were prevalent in previous CHiME challenges. This transition is mainly due to the availability of robust large-scale pre-trained models, which lowers the data burden for e2e-ASR. 2) Despite recent advances in neural speech separation and enhancement (SSE), all teams still heavily rely on guided source separation, suggesting that current neural SSE techniques are still unable to reliably deal with complex scenarios and different recording setups. 3) All best systems employ diarization refinement via target-speaker diarization techniques. Accurate speaker counting in the first diarization pass is thus crucial to avoid compounding errors and CHiME-8 DASR participants especially focused on this part. 4) Downstream evaluation via meeting summarization can correlate weakly with transcription quality due to the remarkable effectiveness of large-language models in handling errors. On the NOTSOFAR-1 scenario, even systems with over 50% time-constrained minimum permutation WER can perform roughly on par with the most effective ones (around 11%). 5) Despite recent progress, accurately transcribing spontaneous speech in challenging acoustic environments remains difficult, even when using computationally intensive system ensembles.

eess.AS↗

arXiv2025

FlexIO: Flexible Single- and Multi-Channel Speech Separation and Enhancement

Speech separation and enhancement (SSE) has advanced remarkably and achieved promising results in controlled settings, such as a fixed number of speakers and a fixed array configuration. Towards a universal SSE system, single-channel systems have been extended to deal with a variable number of speakers (i.e., outputs). Meanwhile, multi-channel systems accommodating various array configurations (i.e., inputs) have been developed. However, these attempts have been pursued separately. In this paper, we propose a flexible input and output SSE system, named FlexIO. It performs conditional separation using prompt vectors, one per speaker as a condition, allowing separation of an arbitrary number of speakers. Multi-channel mixtures are processed together with the prompt vectors via an array-agnostic channel communication mechanism. Our experiments demonstrate that FlexIO successfully covers diverse conditions with one to five microphones and one to three speakers. We also confirm the robustness of FlexIO on CHiME-4 real data.

cs.SD↗

arXiv2025

Spatially Aware Self-Supervised Models for Multi-Channel Neural Speaker Diarization

Self-supervised models such as WavLM have demonstrated strong performance for neural speaker diarization. However, these models are typically pre-trained on single-channel recordings, limiting their effectiveness in multi-channel scenarios. Existing diarization systems built on these models often rely on DOVER-Lap to combine outputs from individual channels. Although effective, this approach incurs substantial computational overhead and fails to fully exploit spatial information. In this work, building on DiariZen, a pipeline that combines WavLM-based local endto-end neural diarization with speaker embedding clustering, we introduce a lightweight approach to make pre-trained WavLM spatially aware by inserting channel communication modules into the early layers. Our method is agnostic to both the number of microphone channels and array topologies, ensuring broad applicability. We further propose to fuse multi-channel speaker embeddings by leveraging spatial attention weights. Evaluations on five public datasets show consistent improvements over single-channel baselines and demonstrate superior performance and efficiency compared with DOVER-Lap. Our source code is publicly available at https://github.com/BUTSpeechFIT/DiariZen.

eess.AS↗

arXiv2025

Exploring Disentangled Neural Speech Codecs from Self-Supervised Representations

Neural audio codecs (NACs), which use neural networks to generate compact audio representations, have garnered interest for their applicability to many downstream tasks -- especially quantized codecs due to their compatibility with large language models. However, unlike text, speech conveys not only linguistic content but also rich paralinguistic features. Encoding these elements in an entangled fashion may be suboptimal, as it limits flexibility. For instance, voice conversion (VC) aims to convert speaker characteristics while preserving the original linguistic content, which requires a disentangled representation. Inspired by VC methods utilizing $k$-means quantization with self-supervised features to disentangle phonetic information, we develop a discrete NAC capable of structured disentanglement. Experimental evaluations show that our approach achieves reconstruction performance on par with conventional NACs that do not explicitly perform disentanglement, while also matching the effectiveness of conventional VC techniques.

eess.AS↗

arXiv2025

FasTUSS: Faster Task-Aware Unified Source Separation

Time-Frequency (TF) dual-path models are currently among the best performing audio source separation network architectures, achieving state-of-the-art performance in speech enhancement, music source separation, and cinematic audio source separation. While they are characterized by a relatively low parameter count, they still require a considerable number of operations, implying a higher execution time. This problem is exacerbated by the trend towards bigger models trained on large amounts of data to solve more general tasks, such as the recently introduced task-aware unified source separation (TUSS) model. TUSS, which aims to solve audio source separation tasks using a single, conditional model, is built upon TF-Locoformer, a TF dual-path model combining convolution and attention layers. The task definition comes in the form of a sequence of prompts that specify the number and type of sources to be extracted. In this paper, we analyze the design choices of TUSS with the goal of optimizing its performance-complexity trade-off. We derive two more efficient models, FasTUSS-8.3G and FasTUSS-11.7G that reduce the original model's operations by 81\% and 73\% with minor performance drops of 1.2~dB and 0.4~dB averaged over all benchmarks, respectively. Additionally, we investigate the impact of prompt conditioning to derive a causal TUSS model.

cs.SD↗

arXiv2025

Physics-Informed Direction-Aware Neural Acoustic Fields

This paper presents a physics-informed neural network (PINN) for modeling first-order Ambisonic (FOA) room impulse responses (RIRs). PINNs have demonstrated promising performance in sound field interpolation by combining the powerful modeling capability of neural networks and the physical principles of sound propagation. In room acoustics, PINNs have typically been trained to represent the sound pressure measured by omnidirectional microphones where the wave equation or its frequency-domain counterpart, i.e., the Helmholtz equation, is leveraged. Meanwhile, FOA RIRs additionally provide spatial characteristics and are useful for immersive audio generation with a wide range of applications. In this paper, we extend the PINN framework to model FOA RIRs. We derive two physics-informed priors for FOA RIRs based on the correspondence between the particle velocity and the (X, Y, Z)-channels of FOA. These priors associate the predicted W-channel and other channels through their partial derivatives and impose the physically feasible relationship on the four channels. Our experiments confirm the effectiveness of the proposed method compared with a neural network without the physics-informed prior.

cs.SD↗

arXiv2025

Factorized RVQ-GAN For Disentangled Speech Tokenization

We propose Hierarchical Audio Codec (HAC), a unified neural speech codec that factorizes its bottleneck into three linguistic levels-acoustic, phonetic, and lexical-within a single model. HAC leverages two knowledge distillation objectives: one from a pre-trained speech encoder (HuBERT) for phoneme-level structure, and another from a text-based encoder (LaBSE) for lexical cues. Experiments on English and multilingual data show that HAC's factorized bottleneck yields disentangled token sets: one aligns with phonemes, while another captures word-level semantics. Quantitative evaluations confirm that HAC tokens preserve naturalness and provide interpretable linguistic information, outperforming single-level baselines in both disentanglement and reconstruction quality. These findings underscore HAC's potential as a unified discrete speech representation, bridging acoustic detail and lexical meaning for downstream speech generation and understanding tasks.

eess.AS↗

arXiv2025

Direction-Aware Neural Acoustic Fields for Few-Shot Interpolation of Ambisonic Impulse Responses

The characteristics of a sound field are intrinsically linked to the geometric and spatial properties of the environment surrounding a sound source and a listener. The physics of sound propagation is captured in a time-domain signal known as a room impulse response (RIR). Prior work using neural fields (NFs) has allowed learning spatially-continuous representations of RIRs from finite RIR measurements. However, previous NF-based methods have focused on monaural omnidirectional or at most binaural listeners, which does not precisely capture the directional characteristics of a real sound field at a single point. We propose a direction-aware neural field (DANF) that more explicitly incorporates the directional information by Ambisonic-format RIRs. While DANF inherently captures spatial relations between sources and listeners, we further propose a direction-aware loss. In addition, we investigate the ability of DANF to adapt to new rooms in various ways including low-rank adaptation.

eess.AS↗