arXiv_SD
-
Unifying Score and Performance for Fine-Grained Music Understanding in Audio-Language Models
2026-09-09 15:46:40Milan Liessens Dujardin, Song-Ze Yu, Kevin MiaoAbstract
Large audio language models (LALMs) have shown promising progress in broad music-understanding tasks such as tagging, retrieval, and captioning. Music understanding that requires finer hearing over both the content and how it is realized within a performance through dynamics, phrasing, articulation, time, and other performance techniques, however, remains at an earlier stage. Existing audio-language model (ALM) training pipelines typically rely on coarse, weakly grounded captions and therefore provide little support for learning these subtle nuances in music, limiting their ability to serve real-world applications in education or artistic practice. We therefore introduce MuNo-SP (Music Notation unifying Score and Performance), a text-based representation that jointly encodes score content and performance information. Building on MuNo-SP, we develop an automatic training-data generation pipeline that uses aligned scores and performances to produce long-form auditory analyses and musically informed question-answer pairs. We use this pipeline to construct MAESTROCaps, a classical piano dataset comprising 148 long-form performance analyses and 31,080 question-answer pairs derived from 148 aligned score-performance pairs. In a human evaluation, MuNo-SP analyses were preferred by majority vote over MIDI-only analyses for eight of nine excerpts. MuNo-SP also performed strongly on a benchmark of score-performance understanding, suggesting that integrating score and performance information enables more reliable and musically informative LALM supervision than a MIDI-only baseline.
Abstract (translated)
URL
https://arxiv.org/abs/2609.10351
PDF
-
TimeCues Studio: A Workspace for Music Annotation and Algorithm Prototyping
Abstract
Multimedia applications require precise music annotation-labeled positions, segments, or loops-placed by hand or algorithmically. Machine-learning algorithms are scalable and effective but need annotated training data, scarce for many tasks. TimeCues Studio is an open-source workspace where algorithm-development teams annotate a music corpus, compare detection algorithms against those annotations, and prototype new ones. Unlike existing tools built for a single track at a time, TimeCues targets teams annotating whole collections, tightly integrated with algorithm development. Annotators place several marker types-each supporting ambiguity-aware labeling-on a grid-locked timeline that visualizes many music features, including separated audio stems. The same timeline drives an algorithm-comparison engine with bundled baselines, a Python sandbox for prototyping new models, and an ambiguity-aware evaluator that honors the structured fields. The same visualization suits solo annotators on music-sync projects. TimeCues is MIT-licensed and deploys via one Docker Compose command.
Abstract (translated)
URL
https://arxiv.org/abs/2609.10338
PDF
-
Pushing the Boundaries of Streaming Multi-Speaker ASR: A Systematic Study of Architectural Trade-offs
2026-09-09 14:53:20Taejin Park, Ivan Medennikov, Kunal Dhawan, Weiqing Wang, Jagadeesh Balam, Boris GinsburgAbstract
Streaming multi-speaker ASR is a challenging task that must balance accuracy, latency, and efficiency while handling overlapping speech and maintaining coherent long-context modeling over extended conversations in an online fashion. We present a unified framework that categorizes streaming multi-speaker ASR into four architectural strategies based on how diarization and ASR are integrated. Using a shared pair of open-source streaming ASR and diarization models as a common foundation, we derive four multi-speaker ASR systems that differ in whether they employ multiple model instances, fine-tuning, or both. We evaluate these systems across multi-speaker accuracy, single-speaker accuracy degradation, memory footprint, and training complexity. Through this systematic architectural analysis, we clarify the design space for streaming multi-speaker ASR and provide practical guidance for selecting the most suitable approach under diverse deployment constraints.
Abstract (translated)
URL
https://arxiv.org/abs/2609.10265
PDF
-
Sparse Weight and Edge Circuit Discovery in Transformer-based Acoustic Models
2026-09-09 13:03:49Jiankun Wei, Ewan Dunbar, Gerald PennAbstract
Transformer-based foundation models are powerful but opaque, motivating Mechanistic Interpretation methods to uncover the black-box by identifying small computation subgraphs responsible for a task. DiscoGP is a joint weight-and-edge circuit discovery framework originally developed for text decoders. We extend DiscoGP to speech encoders and present, to our knowledge, the first circuit discovery study for modern speech foundation models. Across HuBERT and Wav2Vec 2.0 on several speech classification tasks, we find that the discovered circuits are extremely compact, yet often match or even exceed the performance of the full pretrained encoder with the same downstream head. Through ablations, we show that these circuits reflect pretrained computation rather than random structure or task-head artifacts. We also introduce a memory-efficient DiscoGP variant that reduces the GPU memory cost of edge-circuit discovery at runtime from quartic to cubic. Overall, our results broaden Mechanistic Interpretation beyond text decoders and show that circuit-level analysis can reveal both explanatory structure and unexpected functional behavior in speech encoders.
Abstract (translated)
URL
https://arxiv.org/abs/2609.10645
PDF
-
Orukeet: Multilingual ASR with Frozen Gabor Kernels
2026-09-09 11:30:03Nathan Roll (Oruk AI, Stanford University), Irene Yi (Oruk AI, Stanford University), B\"u\c{s}ra Mar\c{s}an (Oruk AI, Stanford University), Vianney Grenez (Oruk AI), Gabriel Stein (OpenWhispr), Momcilo Mrkaic (Hoid), Pavle Padjin (Hoid), Vladimir Zeljkovic (Hoid), Calbert Graham (Oruk AI, University of Cambridge)Abstract
Orukeet replaces half of an adapted Parakeet encoder's temporal filters with 12,288 fitted Gabor kernels, freezes these replacements, and trains the remaining parameters on multilingual and multi-accent data. Final adaptation and checkpoint selection use LibriSpeech test-other. Across 20,146 FLEURS recordings in 25 languages, pooled word error rate (WER) falls from Parakeet's 11.01% to Orukeet's 9.85%, a 10.6% relative reduction. Orukeet has lower WER on 23 of the 25 languages. Orukeet outperforms Parakeet on 61 out of 74 tested splits, including LibriSpeech test-clean (1.46% vs. 1.53% WER), test-other (2.86% vs. 3.14%), and FLEURS English (3.82% vs. 4.28%). All comparisons decode the same audio with matched NeMo settings. The fitted kernels are stored as ordinary convolution weights, retaining Parakeet's architecture and inference operators.
Abstract (translated)
URL
https://arxiv.org/abs/2609.10054
PDF
-
Zero-Shot Temporal Localisation of Audio Deepfakes in Multi-Speaker Conversations
2026-09-09 11:27:26Soumyadeep RoyAbstract
Voice-cloning fraud increasingly relies on surgical injection: a genuine conversation in which only one or two sentences are replaced by synthetic speech. Utterance-level deepfake detectors emit a single real/fake label per clip and cannot report where the synthetic speech lies. We formalise this as Temporal Deepfake Localisation in Multi-Speaker Conversations (TDLMC), show that equal error rate and min-DCF are ill-posed once a file contains both classes, and propose temporal metrics for this regime. Our contribution is a training-free five-stage pipeline that wraps a frozen binary detector and adds segment-level output with no retraining, using a two-threshold hysteresis finitestate-machine decoder to turn noisy window scores into coherent intervals. On 180 constructed multi-speaker conversations from ASVspoof 5, the system attains temporal intersection-over-union 0.90, temporal detection rate 0.95, and MS-DCF 0.26 with a strong backbone, and its false-alarm rate on genuine speech is below 6%, falling under 2% on genuine real multi-speaker dialogue (AMI). Under an identical pipeline, a trained localiser improves temporal IoU by only about 0.04, bounding the cost of forgoing supervision. Evaluated across three frozen detectors under one decoder whose constants are selected on a held-out calibration split, and with a controlled analysis attributing the residual false-alarm rate to a backbone domain gap rather than to the decoder, this provides the first zero-shot baseline and a reusable benchmark for TDLMC.
Abstract (translated)
URL
https://arxiv.org/abs/2609.10051
PDF
-
Over-Tightening-Aware Pseudo-Labeling for Tight-Boundary Speaker Diarization
2026-09-09 09:52:27Shota Horiguchi, Takanori Ashihara, Marc Delcroix, Naohiro Tawara, Alexis PlaquetAbstract
Training speaker diarization models on loose labels, such as speech segments with padded boundaries or filled pauses, often results in similarly loose model outputs. To obtain tighter boundaries, pseudo-labeling based on the averaged outputs of causal and anticausal models has been proposed. However, since the pseudo-labels are estimation-based, they can suffer from over-tightening, which increases missed detections that can propagate as unrecoverable errors to downstream tasks. This paper carefully analyzes the causes of over-tightening and proposes three approaches to address them: (i) removing pause filling rather than padding, (ii) introducing a burn-in phase to mitigate missed detections near the beginning of causal and anticausal predictions, and (iii) making pseudo-label-based co-training aware of the non-causal model used for final inference. Experimental results show that the proposed method reduces missed detections caused by over-tightening and improves both diarization accuracy and downstream multi-talker ASR performance.
Abstract (translated)
URL
https://arxiv.org/abs/2609.09965
PDF
-
Robust Rank Aggregation for Multimodal Speech-Based Alzheimer's Disease Detection
Abstract
Speech-based Alzheimer's disease (AD) detection has recently benefited from multimodal foundation-model representations that integrate complementary acoustic and linguistic information. However, conventional probability averaging over these complementary classifiers is unreliable, because their posterior probabilities exhibit mismatched scales: identical values may reflect different confidence levels across models. We propose a robust rank aggregation framework that aggregates normalized prediction ranks instead of posterior probabilities. Each subject is scored by its percentile within a fixed training-cohort distribution of out-of-fold predictions; since rank ordering is invariant to monotonic transformations, this avoids probability-scale mismatch while preserving classifier confidence ordering. A confidence-gated Random Forest further corrects residual errors using clinically interpretable linguistic features, overriding the rank prediction only when the two disagree and the RF is highly confident, without additional deep model training or explicit posterior-probability calibration. On ADReSS2020 and ADReSSo2021, the method achieves accuracies of 95.83% and 90.14%, respectively, comparing favorably with previously reported results.
Abstract (translated)
URL
https://arxiv.org/abs/2609.09948
PDF
-
SpeechAnnotator: A Context-Aware Multi-Agent Framework and Benchmark for Multidimensional Speech Annotation
2026-09-09 09:37:29Qirui Zhan, Shuiyuan Wang, Jingbin Hu, Haoyu Zhang, Xiaming Ren, Jinrui Liang, Chaoren Yu, Bengu Wu, Yunxiang Chen, Houdun Liu, Su Feng, Liumeng Xue, Lei XieAbstract
Recent controllable speech generation requires training data with fine-grained annotations of speaker traits, prosody, emotion, paralinguistic cues, acoustic scenes, and context. Existing workflows often rely on manual correction, paid hosted multimodal services, or fixed processing chains, which limits large-scale data processing through annotation cost, external-service dependence, or weak cross-stage recovery. We introduce SpeechAnnotator, a locally deployable, context-aware multi-agent framework built entirely from open-source models and tools. Supporting frontend modules first obtain speaker-aware segments and final segment transcripts, while prior evidence extractors attach heterogeneous segment-level cues. Three specialist agents then collaborate through shared state: the Planning Agent converts local audio evidence, speaker history, neighboring segments, and recording-level context into field-specific contracts; the Labeling Agent performs contract-guided multimodal prediction for directly observable attributes; and the Review Agent runs a bounded review loop that checks evidence support and cross-segment consistency, triggering relabeling only for unsupported or inconsistent fields. To address the fragmentation of existing evaluation resources across isolated tasks and narrow-domain test sets, we introduce SpeechAnnotator-Bench (SA-Bench), containing 8.87 hours of human-annotated audio across nine source formats, together with SpeechAnnotator-Eval (SA-Eval), which separates Timeline-Eval for speaker-aware timeline recovery, Closed-Eval for finite-set attributes, and Open-Eval for open-ended attributes. Experiments and ablations show that SpeechAnnotator provides a locally deployable alternative to commercial audio-capable systems, while the bounded review loop improves multidimensional annotation through evidence- and context-aware field-level recovery.
Abstract (translated)
URL
https://arxiv.org/abs/2609.09947
PDF
-
NVV-Locator: From Transcript Tags to Acoustic Boundaries for Fine-Grained Nonverbal Vocalization Grounding
2026-09-09 09:30:48Yuang Cao, Bingshen Mu, Zhennan Lin, Guojian Li, Haoyue Zhan, Jie Liu, Chuan Xie, Qiang Zhang, Liumeng Xue, Lei XieAbstract
Human speech includes nonverbal vocalizations (NVVs), such as laughter, sighs, breaths, and coughs, which convey affective and interactional information. Existing approaches typically represent NVVs as transcript-level tags, providing limited supervision for their waveform-time boundaries. We present NVV-Locator for fine-grained NVV temporal grounding. We first unify 26 NVV categories across public resources and construct large-scale timestamp-supervised training data through dual-LLM verification, transcript-guided forced alignment, and energy-based boundary refinement. We further introduce NVV-TimeBench, an expert-refined benchmark with 667 utterances and 1,094 events. NVV-Locator uses a non-autoregressive slot-filling architecture to jointly predict lexical timestamps, NVV categories, and event boundaries. On NVV-TimeBench, it achieves 71.0% Micro F1, 70.2% Macro F1, 80.4% Macro mIoU, and 59.6 ms Macro mMAE, outperforming the evaluated large audio model counterparts. Evaluation on an external corpus further demonstrates the cross-corpus generalization of NVV-Locator.
Abstract (translated)
URL
https://arxiv.org/abs/2609.09940
PDF
-
Source-Adaptive Data Curation for Bilingual NVV-Aware ASR
2026-09-09 09:19:15Yuang Cao, Qirui Zhan, Jingbin Hu, Ziyu Zhang, Yunxiang Chen, Houdun Liu, Shuo Feng, Bengu Wu, Lei Xie, Liumeng XueAbstract
Nonverbal vocalizations (NVVs), such as laughter, sighs, breaths, and coughs, convey affective and interactional information that conventional automatic speech recognition (ASR) systems often discard. We present a bilingual Mandarin-English system for Track 1 of the NVVSpeech Challenge at ISCSLP 2026, which requires joint transcription of lexical content and 16 NVV categories at their transcript-relative positions. Our NVV-Aware Whisper adapts Whisper-medium through checkpoint-compatible vocabulary remapping, enabling lexical tokens and inline NVV tags to be decoded within a unified autoregressive sequence without expanding the vocabulary. To provide reliable and diverse supervision, we further introduce a source-adaptive data curation strategy that refines public NVV corpora through acoustic augmentation and multimodal LLM filtering, while mining spontaneous NVVs from in-the-wild media through automated preprocessing and annotation. Under the official bilingual evaluation protocol, the proposed system improves final score from 33.32 to 53.61, with ablations confirming the complementary benefits of the proposed data-curation components.
Abstract (translated)
URL
https://arxiv.org/abs/2609.09929
PDF
-
Beyond Accuracy: ARIA-Rubrics for Evaluating Audio Reasoning in Large Audio Language Models
2026-09-09 03:56:05Yupei Li, Qiyang Sun, Mohamed Mady, Chenxi Wang, Zhengwei Gong, Berrak Sisman, Bj\"orn SchllerAbstract
Large Audio Language Models (LALMs) have shown strong performance on audio reasoning benchmarks, but accuracy alone cannot distinguish true reasoning from superficial pattern matching, often overestimating reasoning ability since high scores may result from guessing rather than genuine audio understanding. Evaluating the reasoning process itself is essential for improving LALMs' reasoning ability, yet remains challenging. Existing methods either rely on costly human annotation or opaque LLM-as-judge approaches, making them impractical, biased, and lacking transparency. Moreover, audio reasoning introduces unique challenges absent in text-based settings, perceptual hallucination and cross-modal alignment between audio understanding and textual inference, hence text-based evaluation frameworks cannot be directly applied. Therefore, we propose ARIA-Rubrics (Audio Reasoning Integrity Assessment), a lightweight, annotation-free gold reasoning chains, automatic and transparent framework comprising six complementary metrics that evaluate audio reasoning quality across perceptual grounding, reasoning coherence, and answer consistency. We use Chain-of-Thought prompting as an externalization mechanism to make the reasoning process observable. Experiments on 9 models across 2 benchmarks identify three reasoning modes of current LALMs with actionable directions for future development, with ARIA-Rubrics achieving high correlation with human judgments. The code is available at the Github Repository.
Abstract (translated)
URL
https://arxiv.org/abs/2609.09681
PDF
-
Population Ecology of Tunes
Abstract
How cultural repertoires maintain diversity under selection is a fundamental question in cultural evolution. We address this using thirteen years of weekly popularity data for approximately 20,000 Irish traditional tunes, fitting ecological birth-process models under neutral, frequency-dependent, and per-tune selection hypotheses. We find strong evidence that tunes differ in intrinsic fitness - some are systematically more likely to be learned than others. We find that 29% of the variance in fitness can be explained by a mixture of social and melodic features. Some tunes appear to be carried along via linkage due to the tradition of playing tunes in sets, analogous to selective sweeps in genetics. By measuring changes in fitness over time and comparing this with recordings we precisely identify the mechanism by which a long-dormant tune can become fit through a popular recording. Despite the directional selection, repertoire diversity increases, driven by the continual arrival of new compositions. These results demonstrate that selection and diversity can coexist in a cultural ecosystem, and establish Irish traditional music as a quantitatively tractable system for studying the evolution of cultural variants and understanding what makes a tune stand out.
Abstract (translated)
URL
https://arxiv.org/abs/2609.09501
PDF
-
Audio Deepfake Detection Using Temporal Coherence Analysis
2026-09-08 22:08:30Justin D. Norman, Sarah BarringtonAbstract
The proliferation of AI-generated audio (so-called "deepfake" audio) poses significant threats to information integrity, from voice cloning fraud to synthetic music copyright disputes. We present a temporal coherence analysis framework built upon Contrastive Language-Audio Pretraining (CLAP) embeddings that spans speech, instrumental music, and music with vocals. By computing pairwise cosine similarities between audio segment embeddings and extracting statistical features from the resulting distributions, we train lightweight ensemble classifiers that reliably distinguish authentic from synthetic audio. Our work provides an interpretable, computationally efficient alternative to common deep learning methods while still achieving competitive performance across speech and music domains. Further, we reveal two notable empirical findings about audio deepfakes: (1) a feature-label inversion phenomenon in which 21 of 29 statistical features reverse their discriminative direction between training and in-the-wild deployment, and (2) a speech--music direction reversal in which entropy discriminates in opposite directions for speech and music deepfakes.
Abstract (translated)
URL
https://arxiv.org/abs/2609.09489
PDF
-
DuplexJail: Safety Alignment Breaks Under Spoken Interruption in Full-Duplex Models
2026-09-08 20:19:24Jaechul Roh, Deepak Chandran, Amir Houmansadr, Andrea FanelliAbstract
Full-duplex speech models accept user speech while generating responses, creating an underexplored attack surface. We introduce DuplexJail, which delivers fixed, request-independent spoken prompts through the user audio channel. We compare fixed-delay interruption after the harmful request ends with refusal-triggered interruption following a cue in the model's streaming text. Across four open-source models and 720 harmful requests from AdvBench and HarmBench, fixed-delay interruption raises whole-response attack success rates on AdvBench to 40.3% for PersonaPlex and 48.7% for PersonaPlex-RL, increases of +33.8 and +39.3 percentage points. The refusal-triggered policy reaches 35.6% and 48.6%, respectively, with all trials scored regardless of whether an interruption occurs. Selected conditions also increase FLM-Audio's harmful-response rate, while BayLing-Duplex shows decreases. These findings identify spoken interruption as a jailbreak attack vector and motivate evaluating safety throughout ongoing full-duplex interaction.
Abstract (translated)
URL
https://arxiv.org/abs/2609.09420
PDF
-
Voice or Stereotype? Disentangling Acoustic and Content-Based Gender in Speech-to-Speech Models
2026-09-08 17:58:11Xiaoqun Liu, Tanu Mitra, Harshit Rajgarhia, Abhishek MukherjiAbstract
Speech-to-speech (S2S) models now run inside dubbing, translation, and voice agents. Unlike text models, they hear the speaker's voice, which carries the speaker's gender. A faithful system should treat a speaker as who they sound like, not as whoever usually says what they said. Testing this is harder than it looks, since most S2S models answer in a single, fixed output voice, hard-coded so it cannot drift toward a stereotype. Checking the output voice comes back clean even when the model is biased. We therefore ask two questions. When a model re-speaks the input, does the stereotype in the words shift the perceived gender of the output voice (voice rendering)? And when the model states the speaker's gender, does it follow the voice or the content (gender attribution)? We answer both with one controlled experiment crossing male and female voices with masculine-, neutral-, and feminine-stereotyped passages, on five open- and closed-source models in English, Spanish, and Mandarin. The rendered voice shows no stereotype drift. But every model decides the speaker's gender from the content, not the voice. Making the content one step more feminine (masculine -> neutral -> feminine) multiplies the odds of a "female" judgment by 1.7-24. When the content clashes with the voice, the worst model misgenders the speaker in 90% of cases. When they agree, it misgenders in only 2%. The bias thus hides in gender attribution, where fixed-voice evaluation cannot see, and where audits must look as S2S systems increasingly speak for real people.
Abstract (translated)
URL
https://arxiv.org/abs/2609.09263
PDF
-
A General Approach to Enharmonicism
Abstract
We propose a general approach to enharmonicism within syntactic music theory; that is, we formalize several abstract structures of enharmonicism without any acoustic considerations. The structures of concern to this paper are constructed from diatonics, chromatics, and enharmonics, and we seek to present a general enharmonic theory that builds upon Hook's enharmonic theory published in "Enharmonic Systems: A Theory of Key Signatures, Enharmonic Equivalence and Diatonicism" (2007). We also propose that the two criteria of reflection and maximal evenness can be used to determine whether an arbitrary enharmonic system is musically practical. Moreover, we argue that preferential treatment of the standard enharmonic system (SES) can be motivated from an abstract mathematical perspective divorced from pitch consideration and conventional acoustic constructions of SES.
Abstract (translated)
URL
https://arxiv.org/abs/2609.10603
PDF
-
From Masking to Merging: Rethinking SpecAugment for Efficient Audio Spectrogram Transformer
2026-09-06 15:21:19Minhee Park, Hyowon Ahn, Chanwoo KimAbstract
This paper proposes SpecAugment-Patch Merging, a simple yet effective method to accelerate Audio Spectrogram Transformer (AST) training. We first apply SpecAugment to mask input spectrograms at the patch level, and after positional embeddings are added, the method selects r pairs of masked patches and merges them, reducing the number of tokens processed by the Transformer. Increasing the number of merged pairs r from 0 to 100 keeps mAP on AudioSet nearly unchanged (34.07 to 34.08) while throughput increases from 43.3 to 49.3 samples/sec, which is a relatively 13.9% improvement. Similar patterns appear on ESC-50 and Speech Commands V2, where throughput steadily improves with only minor accuracy changes, demonstrating that this merging approach provides faster training with minimal performance loss.
Abstract (translated)
URL
https://arxiv.org/abs/2609.13260
PDF
-
KanAdapter: A Kolmogorov-Arnold Network-based Plug-and-Play Module for Efficient Fine-tuning of Foundation Speech Models
2026-09-04 15:33:54Phuong Tuan Dat, Phuong Khai Minh, Tran Huy DatAbstract
Fully fine-tuning self-supervised learning (SSL) speech models for downstream tasks is computationally prohibitive, and existing parameter-efficient fine-tuning approaches predominantly rely on MLP-based adapters whose fixed activation functions limit their representational expressiveness under tight parameter budgets. We propose \textbf{KanAdapter}, a lightweight adapter framework that replaces conventional MLP bottlenecks with Group-Rational Kolmogorov-Arnold Network (GR-KAN) modules for more expressive and parameter-efficient adaptation. Following a parallel bottleneck design, KanAdapter inserts trainable GR-KAN branches alongside frozen Transformer encoder blocks and leverages weight transfer from pre-trained MLP layers for stable initialization. Across speaker verification, speech emotion recognition, and deepfake detection, KanAdapter achieves up to 97.5\% reduction in trainable parameters relative to full fine-tuning while remaining highly competitive, and consistently outperforms AdaptFormer under comparable parameter budgets. In continual learning, it yields up to 83.6\% error reduction over full fine-tuning and MLP-based adapters, which we attribute to the localized nature of GR-KAN's rational activations that mitigates catastrophic forgetting. To our knowledge, this is the first work to explore KAN-based modules for parameter-efficient fine-tuning of speech foundation models.
Abstract (translated)
URL
https://arxiv.org/abs/2609.05281
PDF
-
SwanWeave:One-Stage Multi-Task Instruction-Guided 3D Spatial Audio Editing
2026-09-04 10:27:52Ke Lei, Chenyuhao Wen, Yu Zhang, Wenxiang Guo, Changhao Pan, Sashuai Zhou, Yongshi Li, Ruiqi Li, Ruofan Hu, Haorui Xu, Xiang Yin, Zhou ZhaoAbstract
Spatial audio editing modifies an existing soundfield according to a user's instruction while preserving the rest of the scene. Unlike conventional audio editing, it must reason jointly about audio events, spatial information, dynamic changes, and environmental information in first-order Ambisonic (FOA) waveforms. Existing language-guided editors mainly target conventional audio or rely on sequential operations, and therefore do not directly support one-stage editing for complex 3D spatial instructions. We present SwanWeave, the first one-stage multi-task framework for instruction-guided 3D FOA spatial audio editing. We build paired FOA supervision from open-source speech and sound-effect corpora using controllable room simulation, covering more than ten single-operation and compound tasks across the four editing axes. To handle this heterogeneous edit space, SwanWeave uses Spatial Edit Mixture-of-Experts (SE-MoE) with dual-level routing, selecting task-aware expert combinations for compound instructions and frame-level routed/null experts for local edit decisions. We further introduce Spatial Preference Optimization (SPO), a Direct Preference Optimization (DPO)-based alignment objective with edit-specific negative targets, and adopt staged training to improve natural-language grounding. Experiments show that SwanWeave achieves better editing quality than existing general audio editors and spatial audio baselines across all tasks. Spatial audio editing demos can be found at this https URL, code can be found at: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.04975
PDF
