arXiv_SD
-
Natural Backdoor Attacks on Speech Recognition Models
2026-07-17 07:59:49Jinwen Xin, Xixiang Lyu, Jing MaAbstract
With the rapid development of deep learning, its vulnerability has gradually emerged in recent years. This work focuses on backdoor attacks on speech recognition systems. We adopt sounds that are ordinary in nature or in our daily life as triggers for natural backdoor attacks. We conduct experiments on two datasets and three models to validate the performance of natural backdoor attacks and explore the effects of poisoning rate, trigger duration and blend ratio on the performance of natural backdoor attacks. Our results show that natural backdoor attacks have a high attack success rate without compromising model performance on benign samples, even with short or low-amplitude triggers. It requires only 5% of poisoned samples to achieve a near 100% attack success rate. In addition, the backdoor will be automatically activated by the corresponding sound in nature, which is not easy to be detected and will bring severer harm.
Abstract (translated)
URL
https://arxiv.org/abs/2607.15724
PDF
-
SpeechGuard: Online Defense against Backdoor Attacks on Speech Recognition Models
2026-07-17 07:16:57Jinwen Xin, Xixiang LvAbstract
Backdoor attacks pose a critical threat to neural network models, allowing attackers to implant a backdoor during the training phase by manipulating a small portion of the training data. In security-sensitive applications such as voice interaction for autonomous driving, the presence of backdoor attacks introduces substantial security risks. This study focuses on implementing backdoor defense measures for speech recognition models in run-time, taking into account the characteristics of audio signals. We propose SpeechGuard, the first online backdoor defense pipeline designed to identify and purify poisoned audio samples. Specifically, we improve STRIP method to perform adaptive perturbation injection to detect and filter poisoned samples, named as S-STRIP. More importantly, we further consider the purification of poisoned samples. We utilize time-frequency (T-F) masking to suppress the expression of trigger signals and autonomously generate masks based on an autoencoder. The two-stage processing prevents the backdoor in the model from being triggered, and even input speech carrying triggers can be accurately predicted. Extensive experimental demonstrate that SpeechGuard can accurately filter out poisoned samples. Through purification, it can significantly mitigate the backdoor threat while maintaining a certain prediction accuracy.
Abstract (translated)
URL
https://arxiv.org/abs/2607.15697
PDF
-
A Geometry-Limited Identification Floor and Its Consequences for Voice-Clone Attribution in Professional Voice Actors
Abstract
A voice actor's voice is their asset, and AI cloning directly threatens it. The natural defense flags the enrolled actor whose embedding similarity to a suspect recording crosses a threshold. We show it fails where it is most needed: trained voices crowd the embedding space, and each actor performs many styles. On 1,168 Japanese voice actors (56,568 segments, ~63 h), a misidentification floor survives calibration, score normalization, and discriminative re-ranking (linear and nonlinear, including PLDA): the residual is a limit of the embedding geometry, not of the back-ends we evaluate. The best ensemble still leaves ~2.6% closed-set misidentification, several-fold above matched controls; session-disjoint, re-ranking lowers the floor only to 13.0%. The same crowding drives false attribution: on a generic English encoder, roughly half the clones of non-enrolled people falsely accuse an enrolled actor, while -- by a separate real-vs-synthetic shift -- 32% of Seed-VC clones of enrolled targets are missed at the same threshold; one operating point couples the two, and none escapes both. A domain-matched, voice-actor-trained encoder mitigates substantially (a four-fold gender gap vanishes; wrongful misattribution falls to 1.5-10%), but does not remove the floor. Controls (codec, channel, vocoder, content) support reading the miss rate as a real-versus-synthetic covariate shift, not missing speaker information. Fixed-threshold clone attribution is thus unreliable here, and on a generic encoder unfair. Robust attribution must extend spoofing-aware speaker verification to open-set 1:N (anti-spoofing gate, domain-matched encoder, per-speaker calibration, abstain option), and even then supports detection, not autonomous enforcement.
Abstract (translated)
URL
https://arxiv.org/abs/2607.15694
PDF
-
StemFX: Learning Mixing Style Representations via Autoregressive FX Chain Prediction on Source-Separated Stems
2026-07-17 05:21:42Yuan-Chiao Cheng, Jui-Te Wu, Brian Chen, Yen-Tung Yeh, Yu-Hua Chen, Yi-Hsuan YangAbstract
Audio mixing style encompasses the artistic and technical decisions a mix engineer makes, including level balancing, spatialization, and the choice, ordering, and parameterization of audio effects (FX) on each stem. FX chains are a key determinant of this style, yet existing approaches to modeling them remain limited. Some operate on stereo mixtures without explicit per-stem FX chain modeling, others fix the number or type of effects per track, and many require differentiable effect implementations or scarce multitrack datasets. We present StemFX, a framework that learns mixing style representations by autoregressively predicting variable-length FX chains on source-separated stems. A Transformer decoder predicts tokenized FX chains autoregressively, while a band-split multi-band CNN encoder with FiLM conditioning captures per-stem spectral structure. To enable large-scale paired training, we extract pseudo-stems from about 105K songs via source separation and augment them using MultiAFx, a toolkit unifying 85 audio effects from 7 Python libraries. Evaluated on mixing style retrieval, StemFX outperforms all baseline models across all tested chain lengths. On paired mixing style transfer, StemFX achieves the best spectral fidelity and the highest listener preference, over 4000 times faster than iterative optimization.
Abstract (translated)
URL
https://arxiv.org/abs/2607.15634
PDF
-
A Study of Parallelizable Alternatives to Dynamic Time Warping for Aligning Long Sequences
Abstract
This article investigates several parallelizable alternatives to DTW for estimating the alignment between two long sequences. Whereas most previous work has focused on reducing the total computation and/or memory costs of DTW, our focus is instead on reducing wall clock time by utilizing common hardware like GPUs that are optimized for parallel processing. We propose and study four different parallelizable alignment algorithms: the first three algorithms compute approximations of DTW by breaking the pairwise cost matrix into rectangular regions and processing the regions in parallel, and the fourth algorithm computes an exact DTW alignment by processing the cost matrix along diagonals rather than rows or columns. We characterize the performance of our proposed alignment algorithms on an audio-audio alignment task, and we develop GPU-based implementations for the two best-performing algorithms, which we call weakly-ordered Segmental DTW (WSDTW) and Parallelized Diagonal DTW (ParDTW). Our experiments indicate that ParDTW is the most practical and useful of the four algorithms: it computes an exact DTW alignment and reduces runtime by 1.5 to 2 orders of magnitude on long sequences compared to current alternatives. We present a comprehensive evaluation and study of the alignment accuracy, runtime, and practical limitations of the proposed alignment algorithms.
Abstract (translated)
URL
https://arxiv.org/abs/2607.15478
PDF
-
Segmental DTW: A Parallelizable Alternative to Dynamic Time Warping
Abstract
In this work we explore parallelizable alternatives to DTW for globally aligning two feature sequences. One of the main practical limitations of DTW is its quadratic computation and memory cost. Previous works have sought to reduce the computational cost in various ways, such as imposing bands in the cost matrix or using a multiresolution approach. In this work, we utilize the fact that computation is an abundant resource and focus instead on exploring alternatives that approximate the inherently sequential DTW algorithm with one that is parallelizable. We describe two variations of an algorithm called Segmental DTW, in which the global cost matrix is broken into smaller sub-matrices, subsequence DTW is performed on each sub-matrix, and the results are used to solve a segment-level dynamic programming problem that specifies a globally optimal alignment path. We evaluate the proposed alignment algorithms on an audio-audio alignment task using the Chopin Mazurka dataset, and we show that they closely match the performance of regular DTW. We further demonstrate that almost all of the computations in Segmental DTW are parallelizable, and that one of the variants is unilaterally better than the other for both empirical and theoretical reasons.
Abstract (translated)
URL
https://arxiv.org/abs/2607.15475
PDF
-
Estimating the Reliability of Dynamic Time Warping Alignments Using Circumstantial Evidence
2026-07-16 20:29:28Aanya Pratapneni, Alice Yuan, TJ TsaiAbstract
Recent works have explored ways to handle uncertainty in dynamic time warping (DTW) alignment paths through the use of differentiable variants of DTW like Soft-DTW. In this paper, we approach the issue of uncertainty in DTW alignment paths in a different way. Given a DTW alignment path, we propose a metric that indicates how reliable a local segment of the alignment path is. The intuition for our metric is based on the idea of circumstantial evidence. If DTW has found a very prominent path, then if we re-run the alignment with relaxed boundary conditions, it will still pick the same path. If, on the other hand, DTW has found a "weak" path, then re-running the alignment with relaxed boundary conditions will likely yield a different path. Accordingly, our reliability metric is computed by picking a local section of the DTW alignment path, re-estimating the alignment with FlexDTW (which allows flexibility in the boundary conditions), and then measuring how well the DTW and FlexDTW paths agree. We assess the proposed reliability metric on DTW alignment paths containing both matching and non-matching regions across a range of scenarios on an audio-audio alignment task. We find that the reliability metric correctly identifies reliable regions of the alignment path with an aggregate AUROC of 0.97. This approach provides an unsupervised method for estimating the reliability of a DTW alignment path.
Abstract (translated)
URL
https://arxiv.org/abs/2607.15443
PDF
-
What does the model actually see? Evaluation protocols and input availability in data-driven prediction of room acoustic parameters
Abstract
Machine-learnt models are increasingly used to predict ISO 3382-1 room acoustic parameters from sparse measurements, with reported coefficients of determination frequently above 0.85. This paper shows that such figures are often determined by the evaluation protocol rather than by the model. Using a multi-condition measurement campaign in a 264-seat conference hall and a 180-seat concert hall, three model families were evaluated under a factorial protocol ablation: validation splits either row-based or grouped by receiver position, and input features either including measured-at-test quantities or restricted to source-receiver geometry and environmental state. Row-based splits with measured-at-test inputs reproduce the high reported accuracies (mean $R^2$ 0.81 for the core parameters); grouping the splits by position and restricting inputs to information available at an unmeasured position reduces these to 0.09-0.57, reordering the apparent difficulty of parameter classes. A hybrid CNN evaluated with the target's own impulse response as input is shown to exploit it as a position fingerprint rather than as transferable acoustic information; training-only signal access yields no gain for any parameter tested, including reverberation time. Under the deployment-consistent protocol, the spread between Random Forest, the hybrid CNN, and inverse-distance weighting is an order of magnitude smaller than the spread between protocols for a fixed model; the learnt models retain a genuine advantage for sound strength and reverberation time, and the high accuracy of the original pipelines re-emerges as condition interpolation at measured positions (band means 0.80-0.88), a distinct and operationally useful task.
Abstract (translated)
URL
https://arxiv.org/abs/2607.15243
PDF
-
SLT 2026 REAL-TSE Challenge: Real-world Target Speaker Extraction from Conversational Recordings
2026-07-16 16:57:05Shuai Wang, Zihan Qian, Ke Zhang, Jiangyu Han, Zikai Liu, Xiaoyang Yu, Haoyu Li, Marc Delcroix, Kai Yu, Lei Xie, Ming Li, Haizhou LiAbstract
We introduce the REAL-TSE Challenge, an IEEE SLT 2026 satellite challenge on target speaker extraction~(TSE) from real conversational recordings. Given a multi-speaker mixture and one or more enrollment utterances from a target speaker, participating systems must recover only the target speech. Unlike simulated read-speech benchmarks, REAL-TSE evaluates Mandarin and English recordings that contain natural overlap, reverberation, noise, channel mismatch, and conversational dynamics. The challenge defines two complementary tracks: an Online track for low-latency streaming extraction and an Offline track for full-context processing. Systems are evaluated with Token Error Rate (TER), Speaker Similarity (SpkSim), DNSMOS, and target-speaker activity F1. This overview paper describes the task definition, datasets, baselines, evaluation protocol, submitted systems, condition-wise findings, and lessons for future real-world TSE benchmarks.
Abstract (translated)
URL
https://arxiv.org/abs/2607.15198
PDF
-
MIDI-RAE-JEPA: Hierarchical Representation Learning and Generation for Symbolic Music
2026-07-16 03:42:35Scott H. HawleyAbstract
Rich internal representations of musical structure are essential for music understanding tasks such as machine-assisted music co-writing, yet self-supervised approaches for symbolic music representation remain underexplored, particularly those that encode the hierarchical multiscale nature of musical structures. We present MIDI-RAE-JEPA, combining a pitch- and time-shift equivariance objective with LeJEPA and a Swin Transformer V2 encoder to learn such hierarchical representations of symbolic music encoded as piano roll images. The time-shift equivariance objective encourages the model to internalize temporal musical relationships. The encoder is trained purely on self-supervised objectives -- including a masked embedding predictor (MEP) -- with collapse prevented via SIGReg. A separate decoder trained on the frozen encoder embeddings achieves reconstruction F1 of 0.995, and a flow matching generative model conditioned on those embeddings produces generations that closely match the pitch register and rhythmic density of the conditioning excerpt, while mismatched conditioning yields unrelated but musically plausible output. Learned representations outperform a Haar scattering transform baseline on a downstream emotion classification task, and embedding distances increase monotonically with pitch and time shift magnitude, confirming measurable equivariance. These results suggest that equivariance-based SSL objectives, combined with sufficient fine-level encoder capacity, provide a viable path toward semantically rich, generatively useful representations of symbolic music.
Abstract (translated)
URL
https://arxiv.org/abs/2607.14537
PDF
-
MetaPerch: Learning from metadata for bioacoustics foundation models
2026-07-15 17:42:41Mustafa Chasmai, Vincent Dumoulin, Jenny HamerAbstract
Bioacoustic foundation models rely on large-scale citizen science platforms like Xeno-Canto for geographically and ecologically diverse data. Recent work has shown that supervision alone can produce SotA species detection models when trained on this large-scale data -- however, there remains unutilized potential in the form of recording metadata readily available within these community-driven data hubs. In this work, we explore the use of metadata -- such as location and time -- as auxiliary supervision signals, allowing the model to leverage species-metadata correlations in its learned representation. Auxiliary metadata losses provide additional information beyond vocalizations alone that can encourage a richer, more robust representation that generalizes better to species distribution and acoustic domain shifts -- important challenges for deployment in real-world passive acoustic monitoring (PAM) settings. We introduce MetaPerch, a new foundation model that achieves strong species identification performance across multiple challenging domains and present an extensive empirical study of the effects of 9 diverse metadata sources on 17 bioacoustic datasets.
Abstract (translated)
URL
https://arxiv.org/abs/2607.14072
PDF
-
Genre Bias or Aesthetic Perception? Identifying and Mitigating Shortcut Learning in Music Evaluation
2026-07-15 14:44:50Yizhou Zhang, Wangjin Zhou, Yi Zhao, Wei Tan, Keisuke Imoto, Zhi GongAbstract
Music aesthetics scoring plays a critical role in applications such as dataset curation, generative model evaluation, and reward modeling for music generation. Recent approaches rely on deep neural networks trained on human-annotated ratings, but these models may exploit spurious correlations rather than capturing perceptually meaningful aesthetics. In this work, we identify a previously underexplored failure mode in music evaluation models: genre-induced shortcut learning. Through a systematic analysis of SongEval, we show that biases in training data lead to strong correlations between genre-related features and predicted scores, causing the model to use them as a proxy for aesthetics. This results in systematic overestimation of pop music and undervaluation of high-quality samples from other genres, leading to predictions that are inconsistent with human preferences. To address this issue, we propose a training objective that jointly reweights hard samples and regularizes group-level performance, encouraging the model to learn genre-invariant representations of musicality. Experimental results demonstrate that our method reduces genre-dependent bias and improves alignment with human preferences, as reflected by gains in both cross-genre and within-genre preference alignment.
Abstract (translated)
URL
https://arxiv.org/abs/2607.13903
PDF
-
Rethinking Speech Foundation Model Fine-tuning: Better SFT or Better Match?
2026-07-15 14:07:58Wangjin Zhou, Yizhou Zhang, Yichi Wang, Tatsuya KawaharaAbstract
Supervised fine-tuning (SFT) is widely used to adapt self-supervised speech representations to downstream classification tasks. Small gains observed under a single pretrained checkpoint are often interpreted as method-level improvements, i.e., a higher attainable performance ceiling. We show that such conclusions are not always reliable because SFT outcomes depend strongly on the specific pretrained instance. We conduct a systematic study on 3 SUPERB classification tasks, evaluating 8 SFT variants across 9 pretrained checkpoints from wav2vec~2.0, HuBERT, and WavLM, with multi-seed repetitions on representative base-scale models. We find that the identity of the statistically indistinguishable top-group SFT recipe is often checkpoint-dependent, with limited transferability across pretrained instances. These findings suggest that many reported downstream gains reflect instance and seed dependent elicitation match, rather than universally improving the attainable performance ceiling.
Abstract (translated)
URL
https://arxiv.org/abs/2607.13864
PDF
-
From Continuous Deployment to Queryable Dataset: Terabyte-Scale AIS-Aligned Passive Acoustic Labelling
2026-07-15 13:47:56Wayne Renaud, Priyanka Aravindan, Gabriel SpadonAbstract
Long-duration passive acoustic deployments produce large archives of recordings that are not linked to vessel tracks or encounter structure, leaving range and contact conditions unavailable as variables and requiring manual selection for analysis. To address this limitation, we propose a database-native workflow that aligns hydrophone recordings with Automatic Identification System (AIS) position reports to produce distance-resolved data. Fixed-duration recording windows and AIS messages are stored as persistent geospatial tables and associated through an indexed spatiotemporal join, replacing in-memory nested iteration with a single scalable set-based database process capable of handling continuous, multi-year, million-window archival deployments without exhausting available memory. In this study, the approach processes approximately 9.5x10e5 recording windows and 6.9x10e6 AIS position reports, producing a structured table that separates no-contact, single-contact, and two-contact windows, with the closest point of approach computed directly where applicable and background conditions characterized via deterministic spectral ranking. This formulation enables a GeoAI framework in which spatially indexed, queryable data become directly usable for machine learning. The resulting data product reveals predominantly noise-dominated conditions, with vessel contributions emerging mainly at shorter ranges, indicating that the task lies in extracting structure under background-limited regimes. Spectrogram and quantitative analyses show weak tonal signatures embedded in noise and a consistent decay of signal-to-noise ratio with distance, supporting the use of this representation for scalable machine learning, similarity analysis, and predictive acoustic modelling in real maritime environments.
Abstract (translated)
URL
https://arxiv.org/abs/2607.13840
PDF
-
From Prediction to Collaboration: Interactive Symbolic Music Analysis
2026-07-15 08:28:43Emmanouil Karystinaios, Johannes Hentschel, Markus Neuwirth, Gerhard WidmerAbstract
Automatic symbolic music analysis has made substantial progress, yet existing systems are typically designed for a single mode of use, such as full-score prediction, and therefore do not match the broader range of operations that arise in analysis workflows, including partial completion, local correction, and iterative refinement. As a result, there remains a gap between strong benchmark models and systems that can support interactive analytical use. We present a unified framework for symbolic Roman-numeral (RN) analysis that narrows this gap by combining strong predictive performance with direct support for constrained completion and revision. The method is designed to provide a practical trade-off between accuracy and interactive responsiveness by computing expensive pretrained representations once and reusing them during iterative refinement, making powerful pretrained models more amenable to interactive settings. It supports complete score analysis, targeted revision of existing labels, and inference of missing annotations from partial context through a shared modeling framework. Experiments on Dilemmadata, the largest and most heterogeneous benchmark of its kind, show that the proposed approach is a strong RN-analysis baseline while also supporting masked completion from partial labels. Together with a prototype interface for multi-level candidate inspection and editing, these results position automatic RN analysis not only as a prediction problem, but also as a foundation for future interactive tools for music analysis.
Abstract (translated)
URL
https://arxiv.org/abs/2607.13587
PDF
-
Cover First, Disagree Softly: Rethinking Mismatch-First Active Learning for Frame-Level Audio Classification
Abstract
Sound event detection relies on frame-level strong labels whose annotation is expensive. Active learning addresses this problem by selecting the audio segments whose labels help the classifier most. One of the prevailing acquisition strategies for this task, mismatch-first farthest-traversal (MFFT), combines the disagreement between two classifiers and the diversity of the selected segments through hard sequential decisions. It selects whole groups of high-disagreement segments first and spreads only the remaining budget by farthest traversal. On two multi-label datasets we show that this design is blind to the similarity among the selected segments and fails under low budgets, with every mismatch-first variant ending below the plain geometric strategy it builds on. We propose mismatch-weighted facility location (MW-FL), which spends the entire budget through a disagreement-weighted coverage objective that penalizes similarity among the selected segments. The disagreement signal from MFFT is used to obtain the nonnegative weights of this facility-location objective, without introducing hyperparameters. Experiments across two geometric mechanisms with three ways of using disagreement show that coverage of the selected segments is the dominant factor, hard disagreement gating of selection is harmful on both mechanisms, and soft disagreement weighting helps on top of coverage. MW-FL attains the best area under the learning curve on both datasets.
Abstract (translated)
URL
https://arxiv.org/abs/2607.13571
PDF
-
Greedy Volume Maximization of Gradient Embeddings for Long-Tailed Frame-Level Bioacoustic Active Learning
2026-07-15 07:59:54Shiqi Zhang, Marius Fai{\ss}, Ariana Strandburg-Peshkin, Tuomas VirtanenAbstract
Bioacoustic call-type classification relies on costly expert annotation. Active learning can reduce this burden by selecting a small batch of segments for expert annotation and using the labeled segments for training the classifier. The setting is hard: the target calls are extremely sparse and the call-type distribution is long-tailed, so a tight budget must be spent on the few rare, informative segments. We propose BADGE-Greedy-DPP, a deterministic batch selector that greedily adds the segment whose BADGE gradient embedding most enlarges the volume spanned by the batch; because this log-volume objective is submodular, the greedy rule guarantees a batch value at least a (1-1/e) fraction of the optimum of this objective, a guarantee not provided by BADGE's existing k-means++ and MCMC DPP sampling heuristics. There is also a temporal granularity mismatch in the task. The acquisition function scores whole segments, yet the informative frames inside them are few. Uniform averaging therefore washes them out. We show that the BADGE construction naturally addresses this mismatch when applied frame-wise, as prediction residuals weight the aggregated pseudo-gradient, so confidently predicted no-call frames contribute little while a single uncertain rare-call frame can still set the segment's direction. Across 10 runs on a sparse, imbalanced hyena call-type dataset, BADGE-Greedy-DPP achieves the best overall and rare-call-type performance among all compared query strategies, including MFFT, the strongest non-BADGE baseline, and the two vanilla BADGE traversals.
Abstract (translated)
URL
https://arxiv.org/abs/2607.13555
PDF
-
Auditing Protocol-Level Shortcuts in Large Audio Language Model Judges for Speech Evaluation
2026-07-15 06:10:53Joonyong Park, David M. Chan, Yuki Saito, Hiroshi SaruwatariAbstract
Large audio-language models (LALMs) are increasingly used as automatic judges for speech evaluation. However, high agreement with human ratings does not guarantee that their verdicts are grounded in the audio. A judge may instead rely on specialist labels or reference data supplied by the evaluation protocol itself, taking a shortcut in place of listening to the audio. In this paper, we audit such protocol-level ``shortcuts'' in LALM judges across three common deployment protocols: feature-blueprint judging, where the audio is replaced by a structured text description of acoustic features, reference-conditioned judging, and pairwise A/B comparison. Across six judges and four attributes, we find that several LALMs rely on protocol-level shortcuts. For example, in feature-blueprint judging, incorrect specialist labels reduce five judges' emotion accuracy to 0.10 or below, and in concatenated A/B comparisons, Qwen3-Omni-Thinking often picks the same slot regardless of order swaps. These results indicate that aggregate agreement can overstate the validity of LALM judges unless the model and the evaluation protocol are assessed jointly, and that each model-protocol pair should be evaluated with a matched shortcut probe.
Abstract (translated)
URL
https://arxiv.org/abs/2607.13477
PDF
-
Improving Text-to-Audio Instruction Following via Fine-Grained Feedback from Audio-Aware Large Language Models
2026-07-15 03:13:06Chun-Yi Kuan, Siwon Kim, Byeonggeun Kim, Suyoun Kim, Bo-Ru Lu, Qinming Tang, Ankur Gandhe, Hung-yi Lee, Chieh-Chi Kao, Chao WangAbstract
Recent text-to-audio models generate high-quality audio, but often fail to follow instructions involving multiple sound events and temporal order. This gap arises because existing evaluation and training signals mainly emphasize global similarity or perceptual quality, with limited supervision on instruction-level correctness. We propose an instruction-level framework that uses audio-aware large language models (ALLMs) as fine-grained judges to verify target event presence and temporal relations in generated audio. After validating ALLM judgments on benchmarks and through human verification, we use their feedback to construct preference pairs for direct preference optimization. We further introduce S3Bench, a narrative benchmark for evaluating multi-event temporal instruction following. Experiments show that our method improves event completeness, temporal ordering, and joint instruction-following accuracy across existing benchmarks and S3Bench, while maintaining audio quality.
Abstract (translated)
URL
https://arxiv.org/abs/2607.13408
PDF
-
Adapting a Diffusion-Based Music Synthesis Model to Human Voice Conversion
2026-07-14 21:29:17Ben Maman, Frank Zalkow, Hans-Ulrich Berendes, Paolo Sani, Christian Dittmar, Meinard M\"ullerAbstract
Recent diffusion-based generative models have achieved strong results in domain-specific audio generation tasks such as speech, singing, and instrumental music synthesis. However, these models are typically specialized and do not generalize well to mixed or intermediate audio types. In this work, we adapt a diffusion-based model originally designed for multi-instrument music synthesis to voice conversion, covering both speech and singing within a unified framework. Specifically, we extend musical note-based conditioning to include phonetic posteriorgrams (PPGs) and pitch contours, and reinterpret timbre conditioning as speaker or singer identity via feature-wise linear modulation. Experiments show that the adapted model matches or surpasses a dedicated voice conversion system in terms of naturalness and performer similarity, while maintaining accurate pitch control across speech and singing. At the same time, we observe limitations in phonetic fidelity and a degradation in vocal quality when incorporating instrumental training data. Furthermore, we demonstrate that off-the-shelf feature extractors provide effective conditioning signals, enabling large-scale self-supervised training without manual annotations. These results highlight the potential of cross-domain model transfer towards unified audio generation systems capable of handling speech, singing, and music. Qualitative samples can be found on our project page: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2607.13278
PDF
