arXiv_SD
-
AircraftWitness: How Often Aircraft Can Locate Recordings
Abstract
Aircraft overhead can reveal where an outdoor recording was made. Propellers and rotors leave Doppler curves in audio, and public ADS-B archives log equipped aircraft. We measure how often, blind and against chance. Our main test was registered and timestamped before any audio, and its two amendments came before any answer was read. It covers 24 new places, with the recorders' own clocks, a 300 s slack and a 20 km square. The best of three locators places clear-pass clips within 1 km at 4 places, where a uniform guess predicts 0.57 (p = 0.0065 after correcting for the pick). With the wrong time or swapped audio it places none. The other two hit 1 and 2. On 360 clips from 7 places of a GPS-timed network, two locators place 6% and 8% within 1 km. By place, a unit chosen after that run, they hit 4 and 5 of 7 where a uniform guess predicts 2.3. On 1,600 random public recordings, picked and cut without the truth in a time-bounded run, the three locators answer at most 20 times and place at most 2. We release AircraftWitness, a benchmark, and pass labels for 11.7 million recordings.
Abstract (translated)
URL
https://arxiv.org/abs/2611.08791
PDF
-
FoleyForge: Free-form, Controllable, Rectified-flow Editing of Sound Effects
2026-11-05 20:52:06Giovana Morais, Hugo Flores Garc\'ia, Prem Seetharaman, Johannes Imort, Justin Salamon, Magdalena Fuentes, Oriol NietoAbstract
We present FoleyForge, a generative model for instruction-based editing of sound effects. Given an input clip and a free-form instruction describing the desired change, it applies the edit while preserving the input's identity. A single model handles semantic, stylistic, and DSP-like changes. We introduce a data pipeline that guides an audio language model to author both DSP-based acoustic edits and similarity-preserving semantic edits, thus addressing the lack of publicly available audio editing data. Such data is then used to fine-tune a rectified-flow audio generation model, which we extend to expose attribute controls for loudness change, edit strength, and an input-derived contour envelope, each tunable via classifier-free guidance, yielding a more expressive editing model. FoleyForge achieves state-of-the-art instruction adherence at competitive audio quality and source faithfulness.
Abstract (translated)
URL
https://arxiv.org/abs/2611.08695
PDF
-
VoxCanvas-41M: A Large-Scale Bilingual Dataset for Instruction-Based Speech Editing and Its Learning Dynamics
2026-11-05 16:28:02Zhikang Niu, Wenming Tu, Yalin Li, Yanru Huo, Junxi Liu, Tianrui Wang, Ruiqi Yan, Junxuan Liang, Ziyang Ma, Zilong Zheng, Xie ChenAbstract
Recent advances in speech generation have spurred the development of speech editing techniques. However, achieving high-quality speech editing remains challenging due to two key limitations. First, the major hurdle is the lack of large-scale, high-quality speech editing datasets. Constructing such datasets is costly, while open-source, scalable data pipelines remain limited. Second, the learning dynamics of speech editing models remain poorly understood. In particular, how models acquire editing capabilities and the relationship between generation and editing remain unclear. To address these challenges, we introduce VoxCanvas-41M, a large-scale bilingual dataset comprising approximately 41 million speech editing pairs. VoxCanvas-41M covers two major categories: content editing, including single-span, multi-span, and location-reference editing, and paralinguistic editing, covering the insertion and deletion of 39 classes of nonverbal events such as laughter, sighs, and coughs. Building on VoxCanvas-41M, we train VoxCanvas-Edit, an instruction-based speech editing model, demonstrating the effectiveness of our dataset in improving editing performance. Furthermore, we systematically investigate the learning dynamics of speech editing, examining how models learn different editing operations and how data scale, task interactions, and training strategies affect editing performance. The dataset, pipeline, and demos are publicly available.
Abstract (translated)
URL
https://arxiv.org/abs/2611.08251
PDF
-
SubRoformer: Subband Time-Domain Representation for Music Source Separation
2026-11-05 14:58:56Chunyat Wu, Chuang Ding, Paris Smaragdis, Qiuqiang KongAbstract
Music source separation extracts vocals and instruments from a mixed recording, enabling remixing, content production, and music analysis. Existing systems commonly operate on waveforms or full-band spectrograms. Waveform inputs contain many samples even in short segments, whereas a single spectrogram resolution imposes a shared time-frequency resolution trade-off across frequency ranges. We propose SubRoFormer, a Transformer-based system comprising a subband module and a residual RoFormer module. The subband module decomposes the mixture into frequency-localized, lower-rate signals for separation. It then reconstructs the target waveforms from the estimated subbands. The residual RoFormer module models temporal and cross-band relationships on temporally compressed features. It combines this context with fine-rate features through gated residual fusion to estimate source-specific complex masks. On the MUSDB18-HQ test set, training only on MUSDB18-HQ yields an average signal-to-distortion ratio (SDR) of 10.63 dB across four stems using target-specific models, achieving state-of-the-art performance among the compared systems without extra training data. With 500 additional training songs, a single model jointly separating all four stems achieves an average SDR of 11.59 dB, establishing state-of-the-art performance among the compared single-model multi-stem systems trained with extra data. Code and checkpoints are released at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2611.08130
PDF
-
Route-DMD: Distribution Matching Distillation with Task-Routed Mechanism for Speech Foundation Models
2026-11-05 13:35:01Yanru Huo, Zhikang Niu, Wenming Tu, Junxi Liu, Tian Tan, Shan Yang, Yipeng Kang, Ziyang Ma, Xie Chen, Zilong ZhengAbstract
Speech foundation models built on flow matching handle generation, editing, and processing in one system, but every request costs 20-50 iterative steps, and classifier-free guidance (CFG) doubles each of them. Distribution matching distillation (DMD) trains a student that approaches the teacher's quality in a few steps, yet existing speech distillation work applies it to generation alone. We show that a distribution-matching objective does not serve every task: in separation, the noised states of erroneous student outputs deviate far from the teacher's training distribution, where its prediction is unreliable. Route-DMD therefore makes the objective task-dependent, routing the affected tasks to a regression loss and keeping decoupled distribution matching elsewhere. The student is initialized by consistency distillation, and teacher rollouts use adaptive projected guidance (APG) instead of CFG. Without CFG, the 4-step student matches the 32-step teacher on generation, editing, and processing tasks at a 4.5$\times$ end-to-end speedup.
Abstract (translated)
URL
https://arxiv.org/abs/2611.08011
PDF
-
ProCraft: Instruction-Driven Music Production from Free-Form Text
2026-11-05 04:18:46Yuan-Chiao Cheng, Yi-Hsuan Yang, Vincent K. M. CheungAbstract
Music production typically involves multiple editing operations that each require specialized tools and expertise. Existing text-guided music editing systems support few operations or instruments, operate on short clips, or handle only one operation per instruction, unlike real workflows where several changes are requested at once. Here, we present ProCraft, a lightweight 0.5B-parameter autoregressive codec language model that edits 30s music excerpts end-to-end from free-form instructions, including compound requests. ProCraft supports seven operations across eight instruments, from tasks with a unique target (e.g., track removal) to creative ones (e.g., accompaniment generation). We align intermediate representations with pretrained music embeddings and pitch and instrument targets to preserve content outside the edit, and gated cross-attention in every decoder layer to keep generation tied to the instruction. To train on compound requests, we introduce On-the-fly Editing-pair Synthesis, which generates paired instructions and audio combining track-level operations with effect changes. ProCraft performs competitively against task-specific systems on single-task editing, and outperforms four free-text editors on compound instructions for track removal, extraction and denoising on real (MoisesDB) and synthetic (Slakh) recordings. In a user study (16 listeners), ProCraft was rated highest on removal and denoising and on-par with a 16-times larger model on extraction and instrument transfer. Ablations further show that representation alignment and cross-attention reduce leakage from unwanted tracks and raise editing success rates, especially on out-of-domain data.
Abstract (translated)
URL
https://arxiv.org/abs/2611.07423
PDF
-
Adaptive and High-Fidelity Matching Algorithm for Retrieval-Based Accent Conversion
2026-11-05 04:16:24Xinran Wang, Ning Chen, Yixin Luo, Hongqing Zhu, Li TianAbstract
Accent conversion (AC) aims to transform accent-related acoustic characteristics of the source speech to a target accent while preserving linguistic content and speaker identity. Unlike conventional generative AC models, the retrieval-based ones, which employ k-nearest neighbors (kNN) to directly retrieve acoustic features from target-accent speech and so do not need source-accent speech during training, are more effective. However, existing retrieval-based AC frameworks face three issues: limited intelligibility due to incomplete phoneme coverage from sequential matching pool construction, limited adaptability to source speech variations, and low spectral continuity from coarse-grained style modulation. To address these limitations, we propose Anisotropy-Aware Adaptive k-Nearest Neighbor Accent Conversion (AA-kNN-AC), an enhanced retrieval-based AC model. First, we design a phoneme coverage-based matching pool construction strategy, employing greedy selection with diversity-aware scoring to achieve balanced and near-complete phonetic representation under limited target accent data. Second, we propose an anisotropy-aware adaptive kNN retrieval mechanism that dynamically determines the neighborhood size according to the singular value decomposition (SVD)-based anisotropy analysis, enhancing adaptability to source speech variations. Third, we present a progressive Adaptive Instance Normalization (AdaIN)-based fine-grained decoder by integrating temporal up-sampling within AdaIN blocks, enhancing spectral continuity of the converted speech. Experimental results on the L2-ARCTIC and VCTK datasets demonstrate that the proposed method outperforms existing retrieval-based and generative baselines in both objective and subjective evaluations, achieving high intelligibility, speaker similarity, and naturalness. Demo page is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2611.07420
PDF
-
Design of a Speech Enhancement-Based Deep Semantic Autoencoder for Wireless Communications
2026-11-05 02:56:11Xiaoling Han, Bin Lin, Nan Wu, Tony Q. S. QuekAbstract
Speech communication plays a crucial role in the Internet of Things and autonomous networks. However, traditional communication systems suffer from insufficient semantic extraction and limited noise suppression capability. To address these issues, we propose a Speech enhancement-based Deep Semantic Autoencoder (S-DSA) communication system for wireless communications. It consists of a dual-branch semantic encoder, a channel encoder, a channel decoder, and two semantic decoders, enabling joint source-channel coding for robust transmission. A key novelty lies in an adaptive semantic noise decoupling mechanism that disentangles target speech semantics from noise representations through an interaction module, thus maintaining semantic consistency under low SNR conditions. Furthermore, a joint training strategy optimizes speech reconstruction and noise estimation, while a lightweight testing strategy reduces complexity by disabling the noise-decoding path. The proposed S-DSA enables more effective separation between speech and noise, and yields higher robustness as well as better reconstruction quality. These findings highlight the potential of the proposed S-DSA as a practical solution for next-generation intelligent wireless communications.
Abstract (translated)
URL
https://arxiv.org/abs/2611.07361
PDF
-
Latent Terrain: Adapting Neural Audio Autoencoders as Design Materials in NIME
2026-11-04 22:58:06Shuoyang Jasper Zheng, Keigo Yoshida, Nico Garc\'ia-Peguinho, Jiatong Liu, Dan Hearn, Anna Xamb\'o Sed\'o, Nick Bryan-KinnsAbstract
Neural audio autoencoders, a deep learning method for sound synthesis, are increasingly popular in AI-enhanced NIMEs. It is timely to explore as a community how this technological opportunity has opened a domain of design in NIME. This paper focuses on one compelling technique of using autoencoders for sound synthesis: navigating their latent space as a generative sound space. We introduce Latent Terrain, a Max/MSP tool package designed to tailor latent spaces into corpus-based sound spaces for NIMEs. We describe the rationale and development process of Latent Terrain to offer insights into the use of autoencoders in a material-oriented crafting space of musical interface design. We deliver an annotated portfolio resulting from a collaborative artistic exploration of Latent Terrain with four NIME makers, to showcase the design possibilities opened by autoencoders. We reflect on our practice-based account to discuss the challenges and opportunities of enabling neural audio autoencoders as design materials for AI-enhanced NIMEs.
Abstract (translated)
URL
https://arxiv.org/abs/2611.07210
PDF
-
Drowning in Noise: On Signal Saliency in Self-Supervised Learning for Ocean Acoustics
2026-11-04 16:14:04Shikhar Bharadwaj, Samuele Cornell, Shinji Watanabe, Malcolm SlaneyAbstract
Self-supervised learning (SSL) for audio typically benefits from larger pre-training corpora, but this relationship assumes that training data carries meaningful learning signal. In ocean acoustics, this assumption is often violated: passive recordings are dominated by waves, wind, and silence, with biological vocalizations occupying a small fraction of the total duration. We show that this overrepresentation of noise causes SSL models to allocate representational capacity to acoustically trivial structure, degrading downstream performance. Using BEATs as a testbed, we demonstrate that pre-training on 30 hours of salient recordings (segments containing animal vocalizations) outperforms 1,240 hours of unfiltered data on a 31-class marine mammal classification benchmark. Under linear probing, the manually curated salient set achieves markedly better accuracy than the full corpus, despite using 41 times less data. Automatic saliency-based filtering improves over unfiltered pre-training, but still falls well short of the manually curated salient set. Our findings suggest that, in domains where informative content is temporally sparse, data curation matters more than data scale for SSL pre-training.
Abstract (translated)
URL
https://arxiv.org/abs/2611.06725
PDF
-
Decode Before You Hear: Speculative Listening for Chunk-Interleaved Full-Duplex Speech Language Models
2026-11-04 15:16:15Yutong Bian, Yanglin Zhang, Yuxiang Wang, Luoyuan Zhang, Rongshen He, Zihao Wang, Junwen Qiu, Jiaqi Li, Zhizheng WuAbstract
Chunk-interleaved full-duplex speech language models listen and speak in fixed time chunks, and each chunk must be processed before the next one arrives. Their workload is asymmetric across chunks: listen chunks leave compute idle while awaiting audio, and speak and tool-call chunks require serial generation, which delays responses and tool calls. Using the idle compute for the next chunk requires decoding it before its audio arrives, under an assumed input. Taking silence as the assumed input and comparing the output with the output under real audio on four models, we observe two properties. First, the next audio chunk does not change the output in 95.3% of chunks. Second, 88% of changes begin at the first output token. Building on these properties, we propose Speculative Listening, a training-free, lossless framework for input-time self-speculative decoding. During idle time, the model drafts the next chunk under silence and, for changes at the first token, a second branch from the runner-up first token. It keeps all drafts in a cross-chunk hypothesis pool and verifies them when the audio arrives. On our eight-task benchmark TickTock-Bench, Speculative Listening speeds up speak chunks by 2.6-2.8x and tool-call chunks by up to 23.4x. On average, it reduces the decoding delay before a response starts by 73%, to 74-241 ms, close to the 200 ms gap between human turns, and the maximum lag behind real time by 94.4%.
Abstract (translated)
URL
https://arxiv.org/abs/2611.06982
PDF
-
MuLaCover: Flexible Cover Song Generation via Symbolic Tonal Control
2026-11-04 10:37:01Lynn Yi, Zihan Xiong, Junjie Cao, Xiaolong Weng, Yingzhe Ma, Gus Xia, Jinliang Liu, Yuxin Xie, Xianwei Zhuang, Yuguo Yin, Qiao Jin, Gongxi Zhu, Jiayu Wang, Junjie Liang, Qin Yue, Ziyu Wang, Dading Chong, Meng Cao, Jiahuan Zhou, Dongchao YangAbstract
A cover song re-renders an existing piece, most commonly by preserving its tonal content -- melody and chord progression -- while reshaping other musical attributes. This suggests a natural formulation for generative cover synthesis with pretrained music language models: explicitly control tonal content, while specifying lyrics and style through text. Existing approaches condition on frame-level features, tightly coupling generation to the reference's timing and structure, and limiting flexibility such as tempo variation, structural rearrangement, or partial conditioning. To this end, we present MuLaCover, a cover generation model that conditions a pretrained text-to-song foundation model on an editable symbolic lead sheet. Our design enables alignment-free control: generated outputs preserve the tonal signature of the source without frame-level alignment, allowing flexible timing, structure, and segment-level generation. We further introduce a training curriculum with partially mismatched audio-symbolic pairs, improving diversity and robustness. We evaluate MuLaCover with objective metrics, standard subjective ratings, and in-depth expert interviews that provide fine-grained diagnostic insights. Experiments show that MuLaCover achieves state-of-the-art performance among open-source systems and is competitive with leading commercial models such as Suno-v5.5. Audio samples and code are available at our project page: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2610.26684
PDF
-
Speaker-Consistent Grounding for Confusion-Resilient LLM-Based Target Speech Extraction
2026-11-04 10:32:20Hanyu Meng, Hao Shi, Zhanhong He, Qiquan Zhang, Yang Xiao, Sungwoo Cho, Haowei Lou, Haizhou LiAbstract
Deterministic target-speaker extraction (TSE) tends to preserve observed linguistic content but may extract the interfering speaker. In contrast, autoregressive generative TSE improves perceptual quality, but is prone to content hallucination and speaker identity drift, which can be mitigated by model grounding with the evidence from the deterministic TSE. However, grounding such a generative TSE model with speaker-confused evidence may therefore reinforce the error. To address this gap, we proposed a repair-before-grounding framework with a training-free evidence-repair stage. Conditioning-diverse candidate selection (CDCS) selects target speaker-consistent evidence from complementary frozen TSE outputs. The selected waveform can then be used by code-space grounding (CSG) to constrain LLM-based TSE decoding. On Libri2Mix, CDCS reduces wrong-speaker extraction errors from 6.87% to 0.75% on clean mixtures and from 18.95% to 10.46% under noise. With the LLM-based TSE checkpoint unchanged, CSG further reduces noisy content- and acoustic-switch rates from 12.79% and 1.68% to 9.10% and 0.51%, respectively. Despite this stronger grounding, generative TSE retains its predicted perceptual-quality advantage over direct deterministic extraction. These results show that repairing evidence identity before grounding improves the reliability of generative TSE. Audio demos and code are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2611.06297
PDF
-
SonoDyno: A Sonic Dynamometer for Engine Speed and Load Estimation from Audio
Abstract
Controllable engine sound synthesis, Active Sound Design and engine order analysis all build on the relationship between the sound of an engine and its momentary operating state: its speed and its load. Recordings of engine sound are abundant in archives, sample packs and online video, yet they rarely carry time-aligned annotations of that state, which limits their applicability to controllable engine sound generation. We present SonoDyno, which estimates the engine speed, the cylinder count and an engine-normalized load intensity from a microphone signal alone, with no tachometer, no bus access and no prior knowledge of the engine configuration. A convolutional scorer of 124,302 parameters reads the harmonic order energy of each frame at three time-frequency resolutions to jointly score cylinder count and speed, and a decoder imposes the rotational dynamics of the engine on the speed trajectory. A second head estimates the load intensity, the position of the torque between the engine's drag floor at 0 and its full-load ceiling at 1, from the order levels at the decoded speed. On recordings of engines it has never heard, with microphone position, engine type and cylinder count unknown, SonoDyno places 93 to 97% of the frames within 2% of the true speed, identifies the cylinder count with 80% accuracy and confuses the octave on fewer than 2% of the frames. On an unseen engine of a known type, the load intensity has a mean absolute error of 0.12, and the sign of the torque, driving or braking, is right on 91% of the frames. General pitch trackers fall behind even when the harmonic order of each engine is supplied: on our validation recordings and at a tolerance of 5%, the best of them places 62% of the frames within the tolerance, against 96% for SonoDyno.
Abstract (translated)
URL
https://arxiv.org/abs/2611.06262
PDF
-
GraphSeal: Graph-Augmented Speech Deepfake Detection via Temporal-Spectral Artifact Propagation
2026-11-04 08:52:12Lee Seung-woo, Bowen Qi, Kim Min-jun, Jang Won-youngAbstract
Current speech deepfake detectors treat each utterance as a flat sequence of frames, limiting their ability to capture long-range spectral inconsistencies that span non-adjacent regions of an audio signal. We propose \textbf{GraphSeal}, which constructs a temporal-spectral graph over short speech segments and propagates artifact cues through graph attention layers before a global readout produces the bonafide-vs-spoof decision. Each node in the graph corresponds to a fixed-length segment; edges encode temporal adjacency and spectral similarity, letting the network attend to distant frames that share suspicious spectral patterns. A multi-head graph attention mechanism weights neighboring nodes according to both learned features and edge attributes, and a hierarchical readout aggregates node representations into a single utterance-level embedding for binary classification. GraphSeal is front-end agnostic: it operates on top of any self-supervised or handcrafted feature extractor. On ASVspoof 2019~LA, ASVspoof 2021~LA, ASVspoof~5, and the In-the-Wild dataset, GraphSeal achieves equal error rates of 0.52\%, 2.41\%, 8.17\%, and 5.24\%, respectively, matching or outperforming prior methods that rely on fixed-topology graph networks or purely sequential architectures.
Abstract (translated)
URL
https://arxiv.org/abs/2611.06171
PDF
-
LiveFoley: Dynamic Real-Time Video-to-Audio Generation for Immersive Interactive Worlds
2026-11-04 05:35:42Yusheng Dai, Vladimir Iashin, Kangdi Wang, Yuxuan Jiang, Ilpo Viertola, Weiqiang Wang, Qiuhong Ke, Min Zhao, Jianfei CaiAbstract
Streaming video-to-audio (V2A) generation is essential for immersive interactive applications. However, real-time constraints leave existing streaming V2A methods far behind offline models: (1) visual frontends shrink their receptive fields to cut look-ahead latency, severely degrading audio-visual alignment; (2) causal autoregressive diffusion backends denoise each audio patch in isolation, impairing audio quality. To this end, we present LiveFoley, a streaming causal autoregressive diffusion architecture that addresses both bottlenecks with imperceptible latency. For the visual frontend, we introduce a Trailing Sliding Window that converts non-causal segment-level encoders into streaming modules without retraining. By simply realigning the window, it preserves precise audio-visual alignment, while a configurable hop size reduces the frontend look-ahead well below the human perceptual threshold. Building on this tunable hop size, we propose the Unified Varhop Framework to accommodate scenarios with diverse latency and computation budgets. For the audio backend, we explore widening the denoising window of the local diffusion transformer (LocDiT) head in two temporal directions. History LocDiT adds past context to improve quality at no latency cost and serves as our default. Alternatively, Future-Warmup LocDiT breaks the autoregressive deadlock with an approximate future condition, further improving generation quality at the cost of an acceptable backend look-ahead. Extensive experiments demonstrate that LiveFoley matches offline models in temporal alignment and leads streaming systems in generation quality. Project page: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2611.05988
PDF
-
A General Theoretical Framework for Transformed Geometric Pattern Matching in Music
Abstract
In this paper, we present a framework of concepts, terminology and notation for geometric pattern matching, centred around the idea of a {\em transformation class}. After formally defining the concept of a transformation class, we provide detailed definitions of a number of specific transformation classes that are particularly relevant to pattern matching and pattern discovery in music, which is the primary application domain within which the framework has been developed. We then provide formal definitions of the notions of {\em match}, {\em occurrence}, {\em maximal match\/} and {\em maximal occurrence\/} and prove some results relating to these concepts. We then define and explore in detail the idea of an {\em occurrence set\/} and the more general notion of a {\em heterogeneous occurrence set}. Finally, we explore in detail the concept of {\em transformational equivalence}, including a consideration of {\em transformation groups}, along with the group-theoretic and transformational equivalence properties of selected transformation classes.
Abstract (translated)
URL
https://arxiv.org/abs/2610.42095
PDF
-
A richness-sensitive Acoustic Biodiversity Index from species-level detections: classifier benchmarking, false-positive control and validation against standard soundscape indices in an African savanna and an urban zoo
2026-10-30 17:05:52Muhammad Saeed, Dmitry Mikhaylov, Mohamed H. Alhosani, Yasser F. Al Wahedi, Rory Pilossof, Ahmed Arabi, Walid ShaabaAbstract
Acoustic indices are widely used as rapid proxies for biodiversity, but they summarise the distribution of sound energy rather than the species producing it and often track richness poorly. We revise and test an Acoustic Biodiversity Index (ABI) built from species-level detections. Its primary form, ABI_E, is Shannon diversity of detections normalised by the regional species pool expected at the site and season (H / ln S_ref); temporal stability T is reported as a separate component. We first benchmarked four classifiers on a strongly labelled tropical dataset (1,216 calls, 24 classes) with recording-grouped cross-validation. BirdNET embeddings + logistic regression performed best (macro-F1 0.750 +/- 0.029), and random frame-level splits inflated accuracy from 0.41 to 0.70. We then applied BirdNET v2.4 with a location and season filter to recordings from a riverine savanna in the Zambezi Valley, Zimbabwe, and from three habitats at Emirates Park Zoo and Resort, Abu Dhabi, United Arab Emirates. A stricter post-hoc location filter removed 517 high-confidence detections of 9 implausible species, all at the zoo. After diel-matched rarefaction to equal effort (6 h), the savanna site held 21 species (Hill number 1D = 9.83; ABI_E = 0.38) against 1.3-13 species (ABI_E = 0.03-0.21) at the zoo sites. Across 149 recorded hours, ABI_E correlated strongly with richness (Spearman rho = 0.93), whereas six standard indices did not (best: ACI, rho = 0.48). The stability term was lower at the savanna site (0.39) than at the zoo (0.65-0.67), showing that it penalises the natural diel cycle of bird activity. Species-level indices with explicit false-positive control, a declared regional reference pool and effort standardisation provide a more interpretable biodiversity indicator than energy-based acoustic indices.
Abstract (translated)
URL
https://arxiv.org/abs/2610.42042
PDF
-
Self-Supervised Object-Centric Representation for Multi-Task Audio Analysis
2026-10-30 15:20:22Parthasaarathy Sudarsanam, Tuomas VirtanenAbstract
This paper studies the capability of an object-centric audio representation to support multiple downstream tasks within a unified framework. The object-centric model is trained in a self-supervised setup using slot attention by reconstructing Audio Spectrogram Transformer (AST) patch embeddings from a set of latent slots. It is trained on synthetic audio mixtures, which provides controlled multi-source audio scenes. These slot representations are evaluated for the classification, detection, and separation of sound events by training task specific output layers. On the classification task, the model achieves an F1-score of 0.8, comparable to clip-level AST embeddings which achieve 0.7. For sound event detection, it reaches a macro F1-score of 0.7, outperforming clip-level AST embeddings at 0.4 and matching AST patch embeddings at 0.7, which encode finer time-frequency information. In source separation, it achieves an SI-SDR improvement (SI-SDRi) of 18.4 dB. Furthermore, in a zero-shot source separation setting, the model achieves an SI-SDRi of 14.5 dB. These results demonstrate that slot-based representations capture transferable and compositional structure in audio scenes, enabling generalization across tasks and datasets.
Abstract (translated)
URL
https://arxiv.org/abs/2610.41870
PDF
-
MFlowAudio: Efficient Text-to-Audio Synthesis via Mamba-based Stateful Flow Matching
2026-10-30 15:08:03Hao Dai, Panyu Chen, Jagmohan ChauhanAbstract
Recent advancements in audio generation have been largely driven by Transformer-based diffusion models. However, these models suffer from quadratic complexity of self-attention, severely bottlenecking the long-form audio synthesis. To overcome this limitation, we propose MFlowAudio, a novel latent audio generation framework that synergizes the continuous-time dynamics of Flow Matching with a custom-designed TCMamba backbone. TCMamba uses an innovative dual-scan mechanism: a TimeMamba module to capture long-range causal dependencies with linear complexity, and a ChannelMamba module to model cross-channel correlations such as harmonic structures. Exploiting this structural foundation, we formulate the Stateful Flow Matching (SFM) paradigm. This framework inherently enables chunk-wise training and streaming generation, maintaining an $\mathcal{O}(1)$ caching complexity without incurring extra computational overhead. To enable fine-grained controllable synthesis, we devise a novel guidance mechanism that neutralizes vector field collisions precipitated by on-the-fly semantic transitions of prompts. Comprehensive empirical evaluations confirm that MFlowAudio yields generative fidelity on par with state-of-the-art baselines while establishing significant computational efficiency, achieving above $14.5$% acceleration in generation and facilitating perceptually seamless streaming synthesis with a constant latency of $1.8$ seconds. Demo: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2610.41852
PDF
