Speech
-
Not All Frames Are Equal:Difference-Aware Quantization for Ultra-Low-Bit ASR
2026-10-14 06:19:47Woori Jeon, Jungmin SoAbstract
Post-training quantization (PTQ) methods such as GPTQ and AWQ compress large language models effectively, but applying them to automatic speech recognition (ASR) at ultra-low bit-widths (2-3 bits) causes severe transcription degradation. Unlike discrete text tokens, speech activations are highly correlated in steady-state and zero-padded regions yet change rapidly at phonetic boundaries; when all frames contribute equally to the Hessian, static frames dominate calibration and obscure informative transitions. We propose DiffAQ, which computes frame-to-frame activation differences to measure the rate of acoustic change and assigns Hessian importance proportionally, concentrating quantization precision on phonetically critical frames. As a training-free modification to GPTQ, DiffAQ consistently reduces WER across various Whisper sizes and standard benchmarks, with the largest gains at 2-bit precision where baseline methods frequently produce degenerate outputs.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22395
PDF
-
Learning Visual Speech Representations via Cross-Modal Distillation and Joint Face-Lip Modeling
2026-10-14 04:18:45Jing-Xuan Zhang, Genshun Wan, Jianqing Gao, Jia Pan, Yumei Zhang, Lichen ZhangAbstract
Lipreading remains challenging due to the inherent ambiguity of visual speech cues and their sensitivity to head pose and video resolution. In this work, we propose FLARE, a framework for robust visual speech representation learning via cross-modal distillation and joint face-lip modeling. FLARE leverages semantically rich Whisper representations as the acoustic teacher signal, converting them into discrete distillation targets through a random-projection quantizer and pretraining the model with a masked prediction objective. To capture complementary visual information, FLARE employs a dual-stream architecture that jointly processes lip region-of-interest (ROI) and full-face inputs, where the lip stream captures finegrained articulatory motion and the face stream encodes broader facial dynamics. During pretraining, auxiliary audio input is incorporated to facilitate cross-modal alignment, and modality dropout is applied to encourage robust visual-only representations. For downstream lipreading, FLARE serves as a visual encoder coupled with either a lightweight Transformer decoder or an LLM-based decoder. Evaluated on LRS2, LRS3, and the out-of-domain WildVSR benchmark, FLARE achieves strong lipreading performance, with word error rates of 11.7%, 13.2%, and 34.3%, respectively. A progressive design study confirms the contribution of each major component. Further analyses demonstrate that joint face-lip modeling improves robustness under degraded video resolution and large head pose variation, while yielding more phoneme-discriminative visual representations. Code and pretrained models are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.19559
PDF
-
Speaking Longer Than Learned: Training-Free Long-Form Generation for Full-Stream Text-to-Speech
Abstract
Recent full-stream text-to-speech (TTS) models enable low-latency personalized synthesis as input text arrives. However, sustaining generation beyond the lengths seen during training without additional training remains largely unexplored. We systematically analyze VoXtream2, which extends generation by periodically discarding past context while retaining the acoustic prompt. We find that this strategy does not prevent degradation: pronunciation accuracy deteriorates near the end of the training range due to the range of positions in which the model operates rather than the loss of past context, while speaker similarity gradually declines throughout generation. Based on these findings, we propose two training-free modifications that reduce the attention window and strengthen attention to the acoustic prompt. Experiments show that these modifications preserve pronunciation accuracy and speaker similarity throughout long-form generation while retaining the naturalness of the original model. Ablations further show complementary effects of the two modifications.
Abstract (translated)
URL
https://arxiv.org/abs/2610.19553
PDF
-
Revise-TTS: A Non-Masking Refinement Framework for Masked Diffusion Models in Text-to-Speech
2026-10-14 03:19:03Wanli Sun, Dan Su, Anton RagniAbstract
Text-to-speech (TTS) based on masked diffusion models (MDMs) achieves competitive zero-shot speech synthesis performance. Unlike autoregressive (AR) models, MDMs define a corruption process that maps clean speech-token sequences to masked maps and learn a reverse denoising process to recover the reference tokens. However, MDMs commit to intermediate predictions that cannot be revised in subsequent inference steps. Consequently, prediction errors accumulate and propagate, degrading synthesized speech quality. We present Revise-TTS, a single-stage framework that applies hierarchical binary quantization (HBQ) and generative refinement networks (GRN) to zero-shot speech generation. First, we replace finite scalar quantization (FSQ) with HBQ to introduce a scalable binary representation for speech tokens with an explicit coarse-to-fine structure. Second, GRN is trained to reconstruct the token sequence from a mixture of ground-truth and random tokens. During inference, iterative refinement enables self-correction by randomly discarding a small proportion of previously predicted tokens with new predictions. Experiments and ablation studies demonstrate that Revise-TTS achieves competitive zero-shot speech synthesis performance using HBQ. It can further be extended to any MDM-based TTS task as an alternative training and inference method.
Abstract (translated)
URL
https://arxiv.org/abs/2610.19499
PDF
-
Towards Efficient Simultaneous Inverse Text Normalization with Pretrained Text-to-Text Language Model and Read-Tag-Write Policy
2026-10-14 03:13:23Kiet Anh Hoang, Khanh Le, Bao Nguyen, Linh Pham, Dung Vo, Thai Tran, Mai Nguyen, Tri Nguyen, Vu LeAbstract
Streaming Inverse Text Normalization (ITN) is vital for converting spoken-form outputs from streaming Automatic Speech Recognition into formatted written text. Existing streaming ITN methods rely on hybrid systems combining neural tagging with expert-crafted finite-state transducer rules, limiting scalability across domains and languages. While end-to-end models offer superior scalability by learning directly from data, standard encoder-decoder architectures are inherently non-streaming due to global attention. In this paper, we propose an efficient streaming end-to-end ITN system, adapting a pretrained text-to-text model to leverage its robust linguistic knowledge. To enable streaming, we introduce architectural adaptations, a specialized training strategy, a Read-Tag-Write decoding policy, and inference optimizations. Experiments on Vietnamese datasets show accuracy comparable to non-streaming baselines, outperforming hybrid methods while satisfying real-time latency requirements.
Abstract (translated)
URL
https://arxiv.org/abs/2610.19492
PDF
-
ELARSpeech: A 30K-Hour Dataset Across 675 Underrepresented Languages for Long-Tail Multilingual Speech Technologies
Abstract
Massively multilingual speech modeling has made remarkable progress in recent years, yet existing training resources and benchmarks still underrepresent much of the linguistic long tail. To address this gap, we introduce ELARSpeech, a large-scale multilingual speech resource comprising 30,202 hours of speech across 675 underrepresented languages, curated from the Endangered Languages Archive. Combining human-annotated and unlabeled recordings, the corpus spans diverse recording conditions, domains, and language families. Beyond corpus construction, our experiments show how ELARSpeech supports extending ASR and TTS capabilities to diverse underrepresented languages, with further benefits from pseudo-labeling unlabeled data. At the same time, our speech representation analysis reveals remaining limitations in transferring existing multilingual models to the linguistic long tail. Together, ELARSpeech provides both a resource and a testbed for extending multilingual speech technology further into the linguistic long tail. We publicly release the dataset, all trained ASR and TTS models, and the complete data construction pipeline to facilitate research on long-tail multilingual speech technologies.
Abstract (translated)
URL
https://arxiv.org/abs/2610.19388
PDF
-
Kandinsky S2V 1.0: Audio-Driven Avatar Video Generation
2026-10-13 23:11:39Nikolay Semenov, Artem Riabinin, Sergey Bassenko, Anna Averchenkova, Julia Agafonova, Anastasia Aliaskina, Kirill Kozlov, Lev Novitskiy, Nikita Samsonov, Nikolai Gerasimenko, Denis DimitrovAbstract
We present Kandinsky S2V 1.0, an open family of speech-to-video models for controllable audio-driven human animation, comprising Kandinsky S2V 1.0 Lite (2B parameters) and Kandinsky S2V 1.0 Pro (21B parameters). From a single reference image, a speech waveform, and a text prompt, the models generate long-form 25 FPS video in which lip motion, expression, pose, and gesture follow the speech. The architecture draws text and audio conditioning from one Qwen2.5-Omni model and adds a reference-aware three-scale visual memory. Training starts from the Kandinsky 5.0 Video foundation models [1] and combines mixed reference-memory layouts with an area-adaptive face loss. The training corpus contains 1.17M single-speaker clips selected by active-speaker detection, with captions generated directly in English and Russian. A side-by-side human evaluation against the strongest open-source baseline and two proprietary commercial models shows that Kandinsky S2V 1.0 Pro performs comparably to or better than these models on average and is also preferred for lip synchronization. On common speech to video benchmarks, Kandinsky S2V 1.0 Lite and Kandinsky S2V 1.0 Pro rank among the top performing models according to mean rank over five reported metrics. Beyond the base models, we provide {\pi}-Flow distilled variants of both Kandinsky S2V 1.0 Lite and Kandinsky S2V 1.0 Pro. The distilled Kandinsky S2V 1.0 Pro model generates video in 16 sampling steps without classifier-free guidance, achieving a 5.4 times end-to-end speedup over the base model, while matching or exceeding it on nearly all reported benchmark metrics. To accelerate open research and deployment in speech-to-video generation, we release the code, model checkpoints, and diffusers integration under the MIT license.
Abstract (translated)
URL
https://arxiv.org/abs/2610.19290
PDF
-
From Detection To Anticipation: Continuous Onset Forecasting For Stuttered Speech
2026-10-13 21:52:59Tampu Ravi Kumar, Ayoub Daliri, Vivek GuptaAbstract
Automatic stuttering systems primarily detect dysfluencies after they have occurred, limiting their use for anticipatory intervention. We address this gap by formulating stuttering prediction as continuous causal time-to-event forecasting, where a model estimates the risk of an upcoming stuttering onset every 100 ms using only preceding speech. To support this task, we augment FluencyBank Timestamped for 36 speakers with manually reviewed repetitions, prolongations, and blocks, yielding 2,872 forecasting events. We then model the temporal evolution of frozen Whisper-large-v3 speech representations using a compact causal Conformer with 3.67M trainable parameters. The proposed approach achieves an AUROC of 0.63. Temporal analysis further shows that explicitly modeling preceding speech states outperforms simply increasing the static acoustic window, while a discrete-time survival formulation provides coherent forecasts from 300 ms to 1.5 s using a single model. These results provide initial evidence that stuttering onset is preceded by measurable temporal information in speech and establish a framework for future anticipatory stuttering systems.
Abstract (translated)
URL
https://arxiv.org/abs/2610.19235
PDF
-
CAFE: Confining Feature Distillation to Language-Routed Adapters for Compact Multilingual Automatic Speech Recognition
2026-10-13 20:04:19Tianchi Liu, Nicholas Moratelli, Khurram Azeem Hashmi, Mohammadreza Zolfaghari, Rishabh Jain, Louis Lu, Changdae Park, Amril NazirAbstract
Feature distillation is usually expected to add to logit distillation. We find that this expectation does not hold for two common feature losses in compact multilingual automatic speech recognition (ASR), and analyze why through their gradients. The gradient of a projection-based loss is orthogonal to the task gradient, while that of Centered Kernel Alignment (CKA), a similarity-based loss, is weakly aligned with it. CKA lowers the word error rate (WER) on non-English languages, but at the expense of data-rich English. Three loss-level remedies (one trained, two probed) all fall short, and the CKA gradient overlaps with the subspace English uses in the shared encoder by 97.5% to 99.5% (about 81% by chance). Guided by this diagnosis, we propose CAFE (Confined-Adapter Feature distillation), which confines the CKA gradient to adapters that English bypasses, addressing the trade-off in the parameters rather than in the loss. On the Open ASR Leaderboard, CAFE lowers the average WER from 8.55% to 8.02%, beats an adapter-only capacity control at 8.51%, and makes English more stable across checkpoints. At 254M parameters, it trails the 0.6B teacher by 2 WER points and is competitive with much larger models across 48 test sets in 24 languages. We use 564k hours of training data and state-of-the-art models to keep the findings relevant to practice.
Abstract (translated)
URL
https://arxiv.org/abs/2610.19134
PDF
-
GeoMER: A Joint Euclidean-Hyperbolic Geometry Framework for Multimodal Emotion Recognition
2026-10-13 15:48:40Ting Zhu, Huizhi Liang, Boguslaw Obara, Shufei Duan, Varun OjhaAbstract
Multimodal Emotion Recognition (MER) aims to understand human emotions by integrating information from multiple modalities such as speech and text. Psychological studies suggest that emotions exhibit latent hierarchical structured relationships in their semantic representations. However, most MER approaches rely on Euclidean representations, which capture fine-grained cross-modal interactions but do not explicitly provide a geometric prior for organizing hierarchical emotional structures. To mitigate this gap, we propose GeoMER, a joint Euclidean-Hyperbolic modeling framework that introduces hyperbolic emotion-core routing to capture higher-level, abstract emotional representations for MER. The proposed framework jointly models token-level cross-modal semantic interactions and latent emotion representations in two complementary geometric spaces. Specifically, GeoMER consists of a Euclidean Multimodal Fusion Module (EuclFusion) for multimodal representation fusion and a Hyperbolic Geometric Core Routing (HypGeoRoute) module that performs geometry-aware core assignment and aggregation in a hyperbolic manifold to capture more abstract feature representations. The HypGeoRoute module complements the Euclidean token-level modeling. We experiment on the IEMOCAP multimodal MER benchmark and demonstrate that the proposed method achieves the best performance, with 83.54% weighted accuracy and 83.35% unweighted accuracy, outperforming Euclidean baselines, including MemoCMT.
Abstract (translated)
URL
https://arxiv.org/abs/2610.18587
PDF
-
TontaubeV1: Streaming Text-to-Speech with Hierarchical Codec Modeling and Bounded Context
2026-10-13 15:24:21Fritz Cremer, Jonathan CremerAbstract
Text-to-speech systems often face a trade-off between natural prosody and efficient inference: higher perceptual quality usually comes at increased computational cost and latency. We present TontaubeV1, a model that preserves natural prosody while enabling streaming from a single consumer GPU. Speech is encoded by the hierarchical DualCodec representation at 12.5 Hz, which separates a semantic stream from successive acoustic refinements. Our design assumes that prosodic structure is largely established when the semantic stream is generated, and allocates capacity accordingly: a Qwen3-1.7B-derived transformer predicts that stream and thereby the utterance duration, while three progressively smaller Qwen3-0.6B-derived transformers each add one acoustic refinement. Text is tokenized per character rather than by subword. Paired text and audio markers at shared positions support long-form generation with bounded context, and overlapping DualCodec reconstructions are mapped into the VibeVoice acoustic latent space and decoded causally, enabling streaming despite DualCodec's noncausal decoder. The model accepts up to one minute of reference audio for voice conditioning and is designed primarily for English and German, with additional multilingual support. The four predictors total 2.9B parameters; on a single RTX 5090 the streaming path reaches about 200 ms to first audio. In separate non-streaming measurements, the end-to-end real-time factor (RTF) is 0.08 for one input and the aggregate RTF is 0.02 across eight concurrent inputs. In a blinded study, 40 listeners preferred TontaubeV1's prosody over Fish Audio S2 Pro in 70.25% of 400 comparisons (95% CI: 64.2-75.7%). On an LLM-as-a-judge benchmark, it matches ElevenLabs Flash v2.5 and outperforms the April 2026 Gradium API and Cartesia Sonic 3 on prosody. The weights are released on Hugging Face under the Tontaube Community Model License 1.0.
Abstract (translated)
URL
https://arxiv.org/abs/2609.08703
PDF
-
An Initial Study of Physiological Markers for Deepfake Speech Detection
2026-10-13 11:41:04Vojt\v{e}ch Stan\v{e}k, Michal Fri\v{c}, Kamil Malinka, Anton FircAbstract
Conventional deepfake speech detectors primarily target synthesis artifacts and often degrade under unseen attacks or recording conditions. Human speech, however, contains physiological markers associated with respiration, phonation, and temporal coordination arising from the speech-production system that synthesizers may not reproduce faithfully. This motivates the hypothesis that deepfake speech can be detected by identifying inconsistencies in these patterns, which we test using 36 handcrafted physiological markers organized into respiratory, vocal, and temporal categories. We evaluate the marker vectors with logistic regression and SVM classifiers on pooled English recordings. The best in-domain system achieves a 21.40% equal error rate (EER), while logistic regression achieves 32.77% on the out-of-domain dataset pair. Since the markers describe specific speech-production properties, the logistic-regression coefficients indicate whether higher marker values push the classifier toward bona fide or deepfake speech. These results provide initial evidence that physiological markers offer a useful, interpretable signal for deepfake speech detection.
Abstract (translated)
URL
https://arxiv.org/abs/2610.18934
PDF
-
Collapse, Repair, and Drift: Dissecting Fine Tuning Dynamics in Speech Language Models
2026-10-13 11:29:49Yichi Wang, Wangjin Zhou, Yizhou Zhang, Xin Gu, Wei Tan, Yi Zhao, Gong ZhiAbstract
Supervised fine tuning (SFT) is commonly monitored through training and evaluation loss, but loss does not fully characterize how model functionality evolves along the same trajectory. We study this gap through dialect adaptation of Qwen3-ASR, MiMo-Audio, and FireRed-LLM across learning rates from $10^{-5}$ to $10^{-3}$. Character error rate (CER) reveals pronounced transient collapse and recovery whose severity and temporal structure are only weakly reflected by loss. Bidirectional layer patching reveals strong cross checkpoint functional incompatibility during recoverable collapse, with model dependent depth profiles that reorganize during recovery. Pairwise gradient similarity alone does not reliably indicate optimization stability, whereas raw gradient spectral analysis provides a clearer structural distinction between stable and unstable optimization: successfully converged runs approach a broad and temporally stable spectral energy distribution, while failed runs remain spectrally concentrated or exhibit persistent fluctuations. Finally, AdamW update transfer bypasses pronounced early collapse, yet substantial Mandarin degradation still emerges later in training. These results motivate three separable SFT dynamics: collapse, repair, and drift, and show that transient collapse is not necessary for persistent source domain degradation.
Abstract (translated)
URL
https://arxiv.org/abs/2610.18192
PDF
-
Fish Audio Drama 3 Technical Report
2026-10-13 09:06:28Dawei Han, Shidong Li, Shijia Liao, Jiahua Liu, Songting Liu, Qingzheng Wang, Yuxuan Wang, Xin Chen, Yifan Cheng, Tianyu Li, Gangin Park, Xuehao Yang, Chang Zeng, Haoyang Zhang, Ruoyi Zhang, Xiangyu ZhangAbstract
We introduce Fish Audio Drama 3, an open-source speech generation model that turns text into directed performances, built on a 35B-parameter mixture-of-experts backbone that activates 3B parameters per token. It clones voices from multiple references, follows natural-language direction, revises a take when the next turn gives a note, voices multi-character scenes, edits existing speech by infilling, and synthesizes long-form and streaming audio. Multi-turn revision, scene dubbing, editing by infilling, and streaming text input are new in Drama 3, all in one model. Drama 3 pairs the hybrid linear-attention backbone with a new codebook multi-token-prediction audio decoder that predicts the acoustic codebooks of each frame in dedicated layers that attend over the entire sequence. The model is trained with a three-stage pre-training recipe, instruction fine-tuning, and large-batch reinforcement learning whose only reward is a single learned model of human preference. Its inference engine decodes a single stream at 271 frames per second on one H200, against 177 for Fish Audio S2, although Drama 3 has more than seven times as many parameters. The model weights are available on GitHub (this https URL) and Hugging Face (this https URL), and inference is available through SGLang-Omni (this https URL). We highly encourage readers to visit this https URL to direct their own performances.
Abstract (translated)
URL
https://arxiv.org/abs/2610.18010
PDF
-
Mixture of Phonetic Experts Based Low-Rank Adaptation of Conformer Models for Accented English Speech Recognition
2026-10-13 08:35:54Santosh Dahal, Anmol Guragain, Tianchi Liu, Luis Fernando D'Haro, Kiran Chandra DahalAbstract
We present Mixture of Phonetic Experts based Low-Rank Adaptation (MoPE-LoRA), a parameter-efficient adaptation framework for accented English speech recognition. Recent mixture-of-experts approaches typically allocate experts per accent, implicitly treating accent identity as the primary axis of variation. In contrast, we organize adaptation along phonetic categories, motivated by the observation that accent differences are often expressed as systematic distortions of phoneme realization. MoPE-LoRA introduces a fixed set of six low-rank experts aligned with manner-of-articulation classes and performs frame-level routing through a hybrid mechanism that combines phoneme supervision with learned acoustic gating. Because the expert set is shared across accents, the model does not require accent-specific modules and naturally extends to previously unseen accents. Experiments on L2-ARCTIC show that MoPE-LoRA consistently improves over single LoRA and full fine-tuning. In zero-shot evaluation where one accent is held out during training, the proposed method yields a 12.3% relative improvement over single LoRA. These results indicate that phonetic-category-based decomposition offers a scalable and transferable alternative to accent-level adaptation.
Abstract (translated)
URL
https://arxiv.org/abs/2610.26888
PDF
-
Beyond Fixed Targets: On-Policy One-Shot Speaker Personalization for Autoregressive Text-To-Speech Models
2026-10-13 06:58:21Sangkwon Park, Che Hyun Lee, Heeseung Kim, Sungroh YoonAbstract
One-shot personalization of autoregressive (AR) text-to-speech (TTS) models remains challenging because supervised fine-tuning (SFT) on a single reference pair rapidly degrades generation quality. We identify fixed, off-policy supervision as a key cause of failure in one-shot SFT for AR TTS, leading to blank or near-empty outputs at inference. Diversifying the training data with zero-shot pseudo-pairs eliminates this failure but yields little improvement in speaker similarity and increases word error rate because the targets remain fixed and teacher-forced. We therefore propose two on-policy approaches for one-shot speaker personalization: Group Relative Policy Optimization (GRPO) with a speaker-similarity reward and On-Policy Self-Distillation (OPSD) with soft supervision from a reference-conditioned teacher. Both on-policy methods improve speaker similarity while preserving intelligibility, with different trade-offs: GRPO achieves the strongest overall performance, whereas OPSD enables substantially faster adaptation without external reward evaluation. Further analysis confirms that these gains stem from on-policy supervision rather than target diversity, establishing on-policy training as an effective framework for one-shot AR TTS personalization.
Abstract (translated)
URL
https://arxiv.org/abs/2610.17838
PDF
-
SSEmb: Training a Generalizable Speech Retrieval Model Using Only Automatic Speech Recognition Data
2026-10-13 06:39:50Sangkwon Park, Dongwook Lee, Youngho Cho, Donghun Kang, Heeseung Kim, Sungroh YoonAbstract
End-to-end speech-to-text retrieval is becoming an important capability for voice agents, allowing spoken queries to retrieve relevant documents without intermediate transcription. Training these retrievers typically depends on large collections of spoken query-document pairs that are costly to acquire and difficult to extend across domains and languages. We introduce \ours, which replaces such task-specific supervision with speech-transcript pairs from standard ASR corpora. A lightweight adapter projects the output of a frozen speech encoder into the retrieval space of a frozen pretrained text embedding model. \ours is competitive with cascaded ASR-then-retrieve systems while reducing inference latency, and outperforms existing publicly available speech embedding models. It also transfers to text-to-speech and speech-to-speech retrieval without additional training. Controlled analyses validate the speech-transcript alignment paradigm, demonstrating robustness to reduced training data and consistent gains from larger corpora. Further ablations of loss functions and trainable modules establish practical guidelines for the framework. Model weights and codes are to be released.
Abstract (translated)
URL
https://arxiv.org/abs/2610.17813
PDF
-
Multimodal Contrastive Representation Learning Based Voice Conversion for Electrolaryngeal Speech Enhancement
2026-10-13 04:47:07Ding Ma, Jinyi Mi, Jiajun He, Kazuhiro Kobayashi, Naoki Nishio, Tomoki TodaAbstract
Electrolaryngeal (EL) speech suffers from severe acoustic mismatches with normal speech, resulting in degraded naturalness and intelligibility. These mismatches also make sequence-to-sequence voice conversion struggle to learn robust intermediate representations, hindering EL-speech-to-normal-speech conversion (EL2SP) performance. To address this, we propose a novel multimodal contrastive representation learning framework to 1) achieve richer multimodal-representation learning, and 2) facilitate the transferability of multimodal representations to speech-only EL2SP. First, EL speech and text representations are fused to learn multimodal representations for target speech generation, during which cross-modal contrastive learning is employed to encourage a semantically consistent speech--text representation space. Next, the fused representations are treated as a fixed target to guide speech-only representation learning through cross-stage contrastive learning, enabling multimodal knowledge to be transferred to the EL2SP task while preserving architectural and inference simplicity. Experimental results demonstrate that the proposed method consistently outperforms both the speech-only and multimodal-based baselines.
Abstract (translated)
URL
https://arxiv.org/abs/2610.17716
PDF
-
What Do Deepfake Audio Detectors Hear? From Self-Supervised Models to Audio LLMs
2026-10-13 02:40:30Wanying Ge, Xin Wang, Junichi YamagishiAbstract
Real-world audio recordings for deepfake detection rarely consist solely of speech; they often are mixtures of speech and background events that themselves may also be synthetic. When processing these mixtures, it remains unclear whether detectors attend to the speech or the background event, and where their spectral evidence lies. We study this on the CompSpoof V2 database, whose mixtures pair independently real-or-fake speech and event components. Our results show that all systems detect fake events more accurately than fake speech. However, this performance gap is largely driven by poor generalization to an unseen fake speech domain, rather than a true difference in difficulty. Furthermore, sub-band probing reveals that the front-end encoder dictates where a countermeasure focuses its frequency evidence. To enable reliable deployment in real-world scenarios, future countermeasures should address out-of-domain generalization failures and carefully select front-end encoders aligned with their target acoustic evidence. Our source code and checkpoints are released at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.17617
PDF
-
SonicWorld: Source-Centric Latent Dynamics for Spatial Audio Reasoning
2026-10-12 17:19:19Chenlong Wei, Hanling Wang, Mingjin Lou, Yufan Shi, Yandong Sun, Sheldon Yu, Xiaohui Zhu, Xiaobo Jin, Yiwei WangAbstract
Dynamic spatial audio reasoning requires a model to associate changing acoustic observations with the correct source and recover its spatial state at a queried time or interval, a challenge intensified by overlapping speech and source motion. To study this problem, we introduce Sonic-Bench, comprising 2.8K first-order Ambisonics clips and 28.8K target-specific question-answer pairs across 480 simulated indoor scenes. The benchmark covers localization, distance estimation, and motion reasoning in single- and dual-source settings. We further propose SonicWorld, which integrates physical, learned acoustic, and semantic features into persistent source states through learned transitions and recurrent updates, and projects them into an Omni LLM for spatial reasoning. Compared with Spatial-Omni on the Sonic-Bench test split, SonicWorld improves direction accuracy from 31.98% to 34.69% and reduces azimuth error from 57.22° to 48.01°. In zero-shot transfer to Spatial LibriSpeech, SonicWorld retains strong localization performance, achieving 73.98% direction accuracy and 19.29° azimuth error, compared with 27.14% and 70.74° for Spatial-Omni.
Abstract (translated)
URL
https://arxiv.org/abs/2610.17131
PDF
