Research

• arXiv cs.CVOct 20▲ 1

  EvaOmni: An Evidence-Grounded Benchmark for Audio-Visual Reasoning

  Xiaoxing Hu, Wenxi Yao, Chaoyuan Shi, Ziqi Ye, Xiaorong Guo +15

  Omni LLMs can naturally locate key audio and visual evidence and integrate information across modalities for audiovisual reasoning. Existing audio-visual reasoning benchmarks that mainly rely on multiple-choice questions usually score models solely based on answer correctness, making it difficult to assess whether a model truly forms a reasoning chain from evidence to the correct answer. In addition, textual or unimodal shortcuts may allow models to answer correctly without analyzing the necessary audio-visual evidence, further weakening the reliability of evaluation benchmarks. To address these issues, we introduce EvaOmni, an evidence-grounded benchmark containing 392 videos and 1,027 purely human-annotated question-answer pairs, covering 15 capabilities and three levels: retrieval and localization, basic understanding, and complex reasoning. We design a series of rigorous annotation procedures in which experts annotate audio and visual evidence and construct video-based distractors; humans review whether questions meet strict inspection criteria, and finally models filter textual and unimodal shortcuts. Beyond high-quality question-answer pairs, we require models to…

  CodePDF
• arXiv cs.CVOct 20

  PI-MLLM: Psychophysics-Inspired Multimodal Large Language Model for Oddly Satisfying Video Emotion Analysis

  Yuheng Zhang, Jie Zhang, Yuecong Min, Yunwei Zhao, Meichen Liu +2

  Oddly Satisfying Videos (OSVs) can evoke strong viewer responses through repetitive motion, visual tactility, and ASMR-like sounds despite containing few explicit semantic emotion cues. This makes OSVs a challenging setting for Video Emotion Analysis (VEA), since most existing methods focus on semantic video content and under-model the physical sensory dynamics that shape viewer responses. To support Oddly Satisfying Video Emotion Analysis (OSVEA), we construct the Oddly Satisfying Video Dataset (OSVD), comprising 12,000 annotated 5-second clips. Each clip provides viewer-emotion labels under video-only, audio-only, and audio-visual conditions, together with explanations grounded in visual and acoustic sensory evidence. Building on OSVD, we propose PI-MLLM, a psychophysics-inspired multimodal large language model that integrates Modality-Specific Dynamics Alignment (MSDA) and Coalition-Based Audio-Visual Attribution (CAVA). MSDA uses auxiliary prediction objectives to align modality representations with visual motion and acoustic energy-onset dynamics. CAVA evaluates emotion scores across modality coalitions and applies Shapley attribution to identify the dominant modality and…

  PDF
• arXiv cs.SDOct 20

  Uncovering Audio-Text Alignment in Large Audio-Language Models through Cross-Modal Concept Neurons

  Tzu-Quan Lin, Chih-Kai Yang, Yi-Cheng Lin, Hao Tang, Hung-yi Lee

  While the language model backbone is pretrained on text alone, large audio-language models (LALMs) can, to a great extent, recognize acoustic attributes, such as emotion, speaker gender, and spoken language. However, it is unclear how the audio representation is integrated, if at all, with the other text representation before the model produces text. We hypothesize that there is a shared subspace where the audio and text representations are aligned. To test this hypothesis, we identify cross-modal neurons that are responsible for representing both audio and text. We find alignment between audio and text neurons to various degrees across three LALMs and four acoustic attribute types. Causal interventions, steering and deactivating the neurons, confirm that the cross-modal neurons are not just necessary for prediction but can also be manipulated.

  PDF
• arXiv cs.SDOct 20

  Slots Are Not Speakers: Training-Free Speaker Linking for Frozen Streaming Diarizers

  Aditya Srinivas Menon, Kumarmanas Nethil, Kavya Manohar

  This paper presents a causal, training-free linker that allows a frozen streaming diarizer to track more speakers than it has output slots. Streaming end-to-end diarizers such as Streaming Sortformer emit a fixed number N of concurrent speaker slots. Above N speakers, they keep detecting speech but reuse slots across people, because N bounds how many speakers the model can express at once, not how many it will meet. The linker uses only the host's slot posteriors and the audio. It keeps the frames where one slot is active, splits each slot where the speaker changes, embeds each piece with an off-the-shelf speaker encoder, and matches it against a bank of speakers seen so far. It only relabels, so missed speech and false alarm are identical to the host's and every gain is a reduction in speaker confusion. On 1418 sessions from eight corpora, it reduces the 4-slot host's DER above its cap from 36.8% to 22.6%, and barely moves it below the cap. The same constants transfer to the host's 8-slot successor and to two streaming EEND hosts from a different model family. On courtroom hearings with up to 23 speakers it reduces cpWER from 82.7% to 24.4%.

  PDF
• arXiv cs.CVOct 20

  Edit in Sync: Unified End-to-End Audio-Visual Editing for Human-Centric Videos

  Ziye Yuan, Minghong Cai, Xu He, Ruchang Yao, Xiao Fu +6

  Human-centric audio-visual editing requires precise alignment of lip movements, gestures, and expressions with speech. Existing methods process inputs through independent video and audio pipelines, preventing cross-modal interaction between visual editing and audio dubbing. Many of these pipelines further rely on mask-based inpainting. As a result, they suffer from poor lip-audio synchronization, cumulative pipeline errors, and an inherent mask-size dilemma. We present AVE, the first unified end-to-end framework that jointly performs reference-guided person swapping, insertion, and deletion across both audio and video modalities without requiring spatial masks. To overcome data scarcity, we design a synthesis pipeline and introduce AVE-Dataset, the first audio-visual editing dataset to provide 100K pairs with appearance and voice references. By combining Synthetic-to-Real reconstruction with preliminary audio warm-up, our framework transcends synthetic pipeline limits and mitigates audio-video token imbalance. AVE outperforms modality-separate audio-visual editing pipelines in editing realism, temporal consistency, and audio-visual alignment.

  PDF
• arXiv cs.SDOct 20

  APRIL: Ambiguity-Aware Expert Routing for Respiratory Sound Domain-Incremental Learning

  Xinhong Li, Weiping Tu

  Automated respiratory sound classification enables continuous, non-invasive respiratory assessment, yet long-term deployment remains challenging due to domain shifts from evolving recording devices and acquisition periods. When privacy and governance regulations prohibit replaying historical data, sequential learning easily overwrites previously acquired knowledge. Preserving dedicated domain experts prevents parameter interference, but selecting the correct expert at inference is difficult under overlapping acoustic distributions and absent domain labels. To resolve this dilemma, we propose APRIL, an exemplar-free domain-incremental framework for RSC. Built on a shared frozen BEATs backbone, APRIL sequentially inherits and isolates low-rank experts to enable new-domain adaptation without altering earlier models. A multi-level prototype router retrieves the top-two candidate experts and dynamically selects the final model by integrating domain-routing posteriors with classification confidence, adaptively weighted by matching ambiguity. We establish standardized device- and temporal-incremental benchmarks on the ICBHI and SPRSound datasets across forward and reversed domain…

  PDF
• arXiv eess.ASOct 20

  VISH-ASR: Viterbi-Guided Selection of Hotwords for Speech-LLM Contextual ASR

  Xiaoyu Gu, Yu Xi, Chencheng Wang, Zonghan Zhou, Haoyu Li +2

  Prompt-based contextual ASR requires selecting a compact hotword subset from large dynamic inventories, yet existing pre-selection methods rely either on discrete ASR hypotheses that may discard acoustic evidence or on separately trained retrieval models. We propose Viterbi-guided Selection of Hotwords (VISH), a training-free, plug-and-play framework that directly verifies candidate-specific acoustic support over frame-level CTC posteriors. VISH formulates pre-selection as constrained posterior search; M-VISH makes large-list verification scalable through frame-synchronous shared-prefix Viterbi search with bounded top-K pruning, while Bi-MVISH exploits complementary backward evidence for robust verification. Across five benchmarks, M-VISH achieves up to 11.7% absolute improvement in Best-F1 over a strong learned-retrieval baseline and reduces candidate-search latency by 75.2% at 2,000 candidates relative to hypothesis-based filtering. These results demonstrate the effectiveness of posterior-level verification for accurate and scalable hotword pre-selection without additional model training.

  PDF
• arXiv cs.SDOct 20

  SLM-SS: Token-Based Speech Separation with Speech Language Models

  Chenda Li, Tianhua Li, Yiming Chen, Wei Wang, Jiahe Wang +2

  Speech separation (SS) has witnessed substantial progress in recent years with the advent of neural network-based methods, achieving notable improvements on signal-level evaluation metrics. Existing speech separation systems are mostly optimized with signal-level objectives, and often yield outputs that are acceptable in waveform metrics but suboptimal for intelligibility-sensitive downstream tasks. To address this gap, we propose SLM-SS, a token-based generative speech separation framework that models multi-talker mixtures with speech language models. We first discretize clean speech into multi-codebook token sequences with neural codecs and serialize multi-speaker targets via Serialized Output Training (SOT). An encoder-decoder autoregressive speech language model predicts the zero-order sequence to establish speaker ordering and coarse linguistic content, and a non-autoregressive module then refines higher-order residual codebooks for efficient reconstruction. We further introduce a per-talker non-autoregressive strategy that simplifies high-order modeling and improves the stability. On Libri2Mix, SLM-SS with per-talker NAR achieves $6.92\%$ WER, approaching codec-only…

  PDF
• arXiv cs.SDOct 20

  PhonoBridge: Error-Aware Phoneme-Mediated EMG-to-Text Reconstruction

  Wen Qiu, Jiacheng Zhang, Xuanda Chen, Siqi Cai, Haizhou Li

  Electromyography (EMG) provides a non-invasive means of decoding silently articulated speech into text, but accurate decoding remains challenging due to limited availability of paired EMG-text data. We introduce PhonoBridge, a two-stage framework comprising a channel-aware EMG-to-phoneme frontend and a large language model (LLM) backend for text reconstruction. The frontend is trained on paired EMG-text data that consists of channel-wise feature extraction, cross-channel fusion, and electrode embeddings. With phonemes as the intermediate representation, we expand the backend's training data by converting LibriSpeech transcripts into phoneme-text pairs without additional EMG recordings. To adapt the LLM to frontend noise, we introduce Error-Profile-Guided Augmentation (EPGA), which perturbs transcript-derived phoneme sequences according to error patterns estimated from frontend predictions, generating additional training pairs for the LLM. On the Open Vocabulary silent-speech dataset, PhonoBridge achieves 24.77% WER, outperforming the previously reported best of 28.27% on the same test split.

  PDF
• arXiv cs.AIOct 20

  Reusing Multimodal Agents: Efficient Evaluation of Sound Designs in Games

  Thai Nguyen Van, Ibrahim Khan, Mury Fajar Dewantoro, Pratch Suntichaikul, Hai Van Pham +1

  This paper introduces a novel framework for efficiently evaluating in-game sound designs using multimodal learning and reinforcement learning. Sound design significantly influences gameplay and accessibility; however, objective evaluation methods, defined here as automated assessments based on agent performance rather than human ratings, often require retraining agents from scratch for each sound design. Our approach first pre-trains a multimodal encoder that encodes visual and auditory information into a shared latent space. A reinforcement learning agent is then trained using this latent representation. We fine-tune the multimodal encoder for each sound design while keeping the trained policy fixed, allowing us to isolate the effects of sound changes on agent behavior. To evaluate the proposed method, we conducted experiments on games from multiple genres, comparing the performance of blind agents (agents using only sound input) under various sound designs. Experimental results suggest that this approach can detect differences in agent performance caused by degraded or altered sound design. Moreover, we significantly reduce the computational cost compared to retraining the…

  PDF
• arXiv cs.CLOct 20

  Corpus Quality Improves, Retrieval Utility Does Not: An Ablation of Preprocessing and Refinement in a Speech-to-QA Pipeline

  Wonsup Shin, Jingu Kim

  Practitioners building training corpora with a pipeline of language models keep a preprocessing or refinement (post-process) stage when switching it on raises the corpus quality. We ablate a production pipeline that turns conference speech into question-answer pairs. The preprocessing stage rewrites the transcript, and the refinement stage filters the generated pairs. Switching each on and off gives four corpora from the same 40 Korean medical and finance sessions. On the corpus itself, quality rises as the stages switch on. Four LLM judges and six human domain experts rank the four corpora the same way, and the fully refined corpus leads by +0.18 and +0.22 on a 1-5 scale. We then ask whether that gain carries downstream. We supply each corpus to six models at inference and measure retrieval accuracy. The ranking does not hold. Enabling the transcript rewrite lowers retrieval accuracy by 0.061, the only stage effect that survives correction for multiple comparisons. That stage also reads the whole session, so it almost doubles the cost of one. With both stages on, accuracy does not change. An equivalence test we declared in advance confirms this. The corpus itself is clearly…

  PDF
• arXiv cs.CLOct 20

  A Two-Way Street: Surveying the Interplay between Code-Mixing and Native Languages in Text and Speech

  Debajyoti Mazumder, Akash Anil

  Systems for code-mixed (CM) text and speech rarely start from scratch. CM data is scarce, so most work borrows from the languages being mixed, which we call native languages. This transfer can also run in reverse, when CM data is used to improve models for the native languages. Existing surveys focus on processing CM itself, and none brings the two directions together. This paper fills that gap with a systematic survey of transfer in both directions, across text and speech. We organise the surveyed work in a taxonomy of transfer direction, route and modality. Through this taxonomy, we find that most transfer runs from native languages into the CM setting. The reverse direction is younger, and in it code-switching mainly helps by aligning the two languages. Text and speech work share methods but rarely cite each other. On a shared speech benchmark, native data helps more than new architectures. These findings point to open challenges, such as how much native and CM data to mix in training, and how to evaluate CM text written in different scripts.

  PDF
• arXiv cs.AIOct 20

  DuplexLedger: Benchmarking Transactional Memory in Full-Duplex Speech Agents

  Yuxuan Li, Xiangchen Guan, Kunrong Li, Jin Wang, Kaiwen Luo +5

  Full-duplex speech agents must update persistent memory while listening and speaking, yet it remains unclear which events should be stored, revised, or excluded. Existing benchmarks isolate interaction timing from memory outcomes, obscuring the state transitions behind a correct answer. We introduce DuplexLedger, a bilingual benchmark of 1,094 persistent sessions aligning four full-duplex scenarios with event-level Write/Update/Ignore/Retain supervision, explicit pre/post memory states, and 6,564 same-session questions and checks. Evaluating five full-duplex models reveals an interaction-memory gap: no system combines strong boundary control with coherent final-state memory, and the best final-state fact coverage is 2.01%. We propose ACT-Mem, an 8.92M-parameter sidecar comprising an event controller, a versioned transactional ledger, and a typed retriever coupled with a frozen MiniCPM-o 4.5 backbone. On 219 held-out sessions, ACT-Mem increases latest-value accuracy from 4.11% to 8.68% while reducing stale assertions and distractor adoption. It improves interaction boundaries but slows interruption stopping. These results motivate selective, auditable full-duplex memory rather…

  PDF
• arXiv cs.CLOct 20

  AudiPsy: Evidence-Grounded Multimodal Reasoning over Spoken Counseling Conversations for Depression Assessment

  Chuanbo Zhu, Run Luo, Weibo Zhao, Yue Li, Kun Qian +4

  Depression assessment from counseling speech requires integrating textual and acoustic psychological evidence across turns, yet existing end-to-end classification approaches lack explicit multimodal evidence interpretation and context-aware reasoning. We propose AudiPsy, an evidence-grounded omni-LLM for depression assessment over spoken counseling conversations. AudiPsy employs an Observation-Assessment-Summary (OAS) paradigm to integrate dialogue transcripts, textual and acoustic emotions, and textual-acoustic emotion incongruence into structured reasoning. OAS incrementally organizes multimodal observations, performs contextualized assessment, and maintains an evolving dialogue summary for subsequent turns. To support this framework, we construct AudiPsy-Counsel, a synthetic spoken counseling conversation corpus with multimodal context augmentation, and develop a unified three-stage curriculum for depression-oriented reasoning. Experiments on DAIC-WOZ demonstrate superior depression assessment performance over specialized depression detection methods and general-purpose speech/omni-LLMs, along with improved reasoning quality, while supplementary evaluation on EATD-Corpus…

  PDF
• arXiv cs.SDOct 20

  MiCLA: Mixture-to-Constituent Latent Alignment for Polyphonic Audio Representation Learning

  Kohei Yamamoto, Kosuke Okusa

  Real-world audio typically contains concurrent sound events, yet standard self-supervised methods treat each clip as an isolated training unit without explicitly modeling mixture--constituent relationships. We propose Mixture-to-Constituent Latent Alignment (MiCLA), a two-stage self-supervised pre-training framework that uses synthetic log-mel mixing to align mixture representations with their constituent clips. Stage 1 structures single-clip representations via masked self-distillation and contrastive regularization. Stage 2 introduces bidirectional alignment: for a synthetic mixture, MiCLA suppresses the component aligned with one constituent and aligns the residual with the other, using projective residualization on patch tokens and sample-adaptive soft residualization on the global class token. In downstream evaluations, MiCLA achieves 43.2% mean average precision (mAP) on AS-20K and 50.3% mAP on AS-2M under fine-tuning, and achieves the highest mAP among evaluated models on both AudioSet settings under frozen Convex Gated Probing (CGP). Furthermore, a Joint Semantic Retrieval diagnostic shows that MiCLA improves simultaneous retrieval of both constituent classes over…

  PDF
• arXiv cs.SDOct 19

  Steering intonational tunes in text-to-speech synthesis

  Juan Pablo Vigneaux, Jennifer Cole

  Text-to-speech systems built on residual vector quantization often generate audio in two stages: a transformer backbone emits the first level of each frame's token stack, and a smaller depth model generates the rest autoregressively. We ask which components of such a model are responsible for prosodic intonation, more precisely for generating the English nuclear tune (for instance, the falling pitch melody that distinguishes an assertion from a question's rising melody), and whether interventions on those components can be used to control intonation. Prompt-based control mostly fails; only a final question mark is a reliable lever. Interchange interventions in CSM and S2 locate the tune: the backbone's hidden state carries it to the waveform through the depth model, and the first level of the stack carries little or none of it. Steering the backbone state with a difference-of-means vector computed on new material generated with a final period or question mark moves the tune, but the push toward an assertion degrades the voice. Steering vectors computed instead from the backbone states associated with human imitations of theoretically-specified tunes, whose text carries no…

  PDF
• arXiv cs.CVOct 19

  Generalizing Multimodal Foundational Models in Context-Driven Class Incremental Learning

  Avi Gupta, Nilotpal Sinha, Vishnu Raj, Sambuddha Saha, Pratik Joshi +2

  Class-Incremental Learning (CIL) aims to learn new classes continuously without forgetting the previously learned ones. Recent works in CIL have significantly advanced across various modalities; however, at the intersection of audio-visual modality, this problem remains underexplored. While representations from multimodal foundational models (MFMs) encapsulate rich static priors, our preliminary analysis shows that these representations struggle in incremental settings. Motivated by this, we propose a framework that generalizes frozen MFMs to audio-visual CIL. Specifically, we leverage their dense audio and visual representations and employ an attention-based contextual guidance module, in which the audio representations serve as task-stable contextual guidance for the visual representations, enabling effective class recognition in the incremental setting. To further mitigate catastrophic forgetting and preserve stability across tasks, we employ feature- and logit-level distillation, which are primarily responsible for the reduced forgetting. Extensive evaluations across various audio-visual CIL benchmarks demonstrate that our approach consistently outperforms state-of-the-art…

  PDF
• arXiv cs.LGOct 19

  You Are the Trigger: Speaker-Activated Backdoors

  Nataša Krčo, Euodia Dodd, Peter Romov, Yves-Alexandre de Montjoye

  Speech models are increasingly used as an interface to AI systems, from transcription tools to voice agents. Existing audio backdoors require an attacker to introduce triggers at inference time. We study a different threat model in which the attacker compromises the model during fine-tuning but has no access to the victim's inference-time inputs. We introduce the Speaker-Activated Backdoor (SAB) setting, in which a target speaker's natural voice serves as the trigger. We develop a two-phase fine-tuning method that first makes speaker identity more accessible and then binds the target speaker to an attacker-chosen payload. Compared with a one-phase baseline with the same training budget, the two-phase method substantially improves selectivity and clean performance, and is especially important for content-dependent attacks. SAB achieves 90.2% and 97.0% backdoor success on Whisper-medium and Parakeet, with false-positive rates of 1.7% and 0%, respectively using as little as two minutes of real audio from the target speaker. We further demonstrate content-dependent semantic rewriting and downstream tool-use attacks, where malicious instructions are inserted into 96.9% of…

  PDF
• arXiv cs.CLOct 19

  Preference-Aware Pareto Steering for Multi-Task Speech LLMs

  Liuyuan Jiang, Vishal Sunder, Samuel Thomas, Brian Kingsbury, Jeff Kuo +2

  Speech large language models (LLMs) perform multiple tasks, including automatic speech recognition (ASR), timestamp prediction (TS), and speech translation (ST). Joint training of speech LLMs creates task trade-offs, yet standard training with fixed loss weights does not generally control the resulting trade-off according to deployment preferences. To address this, we propose Endpoint-Anchored Preference-Aware Sampling Uniformly along the Pareto Front (EA-SURF), an a priori method that adapts scalarization weights so that the resulting task trade-off reflects the desired preference. EA-SURF retains the standard weighted-loss training pipeline, tracking the current model's performance relative to each task-specific reference and adapting the scalarization weights as training proceeds. We theoretically show that EA-SURF can match a desired preference, with the update becoming stationary at the target under checkable regularity conditions. Across six three-objective speech LLM requests, EA-SURF empirically converges toward the requested targets and increases endpoint-inclusive normalized hypervolume by 17.8% over fixed loss weighting.

  PDF
• arXiv cs.SDOct 19

  Beyond Two Tracks: Speaker-Anchored Full-Duplex Dialogue Recovery

  Yuxuan Chen, Yang Xiao, Jack Sun, Chak Sun, Brick Li +1

  Spoken interaction is moving from alternating turns to full-duplex conversation, where an agent listens while speaking. Learning this coordination requires natural dialogue with persistent speaker-resolved tracks, a data requirement that remains difficult to satisfy at scale. Generative recovery offers a route from ordinary recordings, but recovering two voices is not enough: their track assignments can drift as the conversation unfolds. We address this missing link with speaker-anchored routing before diffusion: a 1.84M-parameter module matches the separator's coarse streams to fixed enrollment identities and orders them before a frozen generator reconstructs the speech, without retraining the generator or altering the reconstructed audio. On 25-minute remote conversations, routing cuts wrong-track time from 43.9% to 4.1%, below the 6.2% of matched-enrollment waveform re-identification, with its largest advantage when one participant holds the floor (17.8% versus 28.6%), and raises fixed-track activity F1 from 0.46 to 0.84 while per-chunk reconstruction quality is unchanged. The same router transfers to unseen face-to-face and telephone recordings, and a margin-gated…

  PDF

• Spatial audio alignment in joint video-audio generation3 papers raise it · 3 address it

  Immersive applications like AR/VR require stereo audio that dynamically matches visual source motion, which current models often lack.

  • Hear the World in Stereo: Learning Dynamic Spatial Correspondence for Immersive Joint Video-Audio Generationraises · addresses
  • WorldSonus: Bringing Sound to Worldsraises · addresses
  • HelixWorld: A Real-time Interactive Audio-Visual World Modelraises · addresses
• Real-time joint audio-video generation2 papers raise it · 2 address it

  Interactive applications need low-latency synthesis to keep pace with user input and camera motion.

  • WorldSonus: Bringing Sound to Worldsraises · addresses
  • HelixWorld: A Real-time Interactive Audio-Visual World Modelraises · addresses
• Multi-stem audio separation in generation1 paper raises it · 1 addresses it

  Accessing individual sound sources is necessary for dynamic scene rendering and editing, but most models output only mixed audio.

  • SepGen: Multi-Stem Audio-Video Separation and Generation in a Single Modelraises · addresses
• Evaluation of complex audio-video consistency1 paper raises it · 1 addresses it

  Current metrics fail to assess multi-event, multi-layer, or asymmetric cross-modal scenes, limiting progress in advanced generation.

  • AVC-Reward: Event-Centric Audio-Video Consistency Evaluationraises · addresses
• Accent leakage in cross-lingual voice cloning1 paper raises it · 1 addresses it

  Reference accents often contaminate target speech, reducing naturalness and speaker similarity in multilingual synthesis.

  • Accent Analogy Guidance: More Speaker Similarity at Equal Accent in Cross-Lingual Voice Cloningraises · addresses

Named by an AI from these papers' abstracts.