Papers

Clear capture of the wearer's own voice (OV) is essential when using earbuds for mobile communication. However, OV capture remains challenging in noisy environments. Bone-conducted (BC) speech, which can be sensed as vibrations of the earbud housing, can be used to improve OV capture. However, neither bandwidth nor spatial characteristics of OV-induced earbud vibrations have been analyzed in detail, despite both characteristics being relevant, e.g., for sensor choice and placement. This study investigates both characteristics, based on measurements with two earbud models. Spectrally, results indicate that OV-induced earbud vibrations exhibit a low-pass characteristic, with a steep roll-off of -93 dB per decade above 400 Hz. Thus, sensors with comparatively low noise floors are required to sense the vibrations above \SI{1}{\kilo\hertz}. Spatially, results indicate that the earbuds mainly vibrate in and out of the ear canal entrance, with high consistency between subjects and fits. Simulations confirm that this enables capture of the high-power vibrations below 400 Hz by a single-axis sensor with less than 1.5 dB mean attenuation.

Audio LLM benchmarks measure understanding and dialogue quality, not whether speech-enabled models respond with relational warmth when a vulnerable user discloses a mental-health concern. We introduce a 7-turn scripted-disclosure probe grounded in WHO mental-health clinical guidelines, with each script run on the same model (Azure OpenAI gpt-realtime) in both audio and text-only conditions, and acoustic-prosody analysis of the generated speech. Across 532 responses we identify two audio-specific patterns transcript-only evaluation would miss: at the elicitation turn the model's voice gets shorter, faster, lower-pitched, and quieter rather than warmer (p < .001 for five of seven acoustic features), and the modality gap on relational acceptance, small in aggregate, concentrates in the highest-stakes self-harm/suicide scripts. A two-rater listener study corroborates that perceived warmth is concentrated at specific turns and on bereavement disclosures. Together these patterns indicate that auditing speech-enabled models in mental-health contexts requires evaluating the combined audio-and-text experience the user encounters, not the transcript in isolation. We release the protocol, scoring pipeline, and scripts as a starting point for evaluating speech-enabled models in mental-health contexts.

Text-to-Speech (TTS) foundation models are increasingly fine-tuned on private datasets to synthesize highly personalized voices, introducing severe privacy risks by exposing both biometric identities and sensitive speech content. Existing black-box membership inference attacks (MIAs) follow a two-stage pipeline of query generation and representation engineering, both of which face unique challenges when adapted to TTS. For query generation, dual conditioning on synthesis text and reference speech creates a large and underexplored query design space with no established criterion for identifying an effective query. For representation engineering, the multi-level speech characteristics and temporal variability of speech make low-level representations and direct comparisons inadequate for capturing membership signals. To address these challenges, we present the first black-box MIA framework explicitly tailored to TTS models at both the speaker and record levels. For query generation, we characterize the feasible query space and establish two criteria, scorable extent and memorization elicitation, for evaluating five representative queries, identifying recitation as the strongest. For representation engineering, we obtain multi-level speech representations from embedding models and temporally align the generated and target audio for fine-grained comparison. Evaluations across three state-of-the-art TTS models (CosyVoice2, F5-TTS, and XTTS-v2) fine-tuned on two benchmark datasets (VCTK and British Dialect) reveal severe privacy leakage: speaker-level AUC remains above 0.80 and approaches 1.0 in the strongest settings, while record-level AUC ranges from 0.80 to 0.90 and remains effective even in challenging scenarios where both members and non-members are of the same speakers. We further identify speech characteristics associated with disproportionate vulnerability to memorization.

Large audio language models (LALMs) can describe what is heard, but their ability to localize when queried content occurs remains less systematically evaluated. We present TAG-Bench, a benchmark for temporal audio grounding in which a model returns every time interval that matches a natural-language query. TAG-Bench contains 1,750 human-verified query-recording pairs covering 149.5 hours, with eight source-dependent subsets spanning query categories and audio durations from 7 s to 20 min; 22.1% of the queries have multiple ground-truth intervals. Across 21 evaluated systems, the best-performing model achieves 31.2 mIoU and is the only system above 20 mIoU on the two long subsets, yet even this top performer reaches only 21.5% recall at IoU >= 0.7. Moreover, 9 of 21 systems fall below 5 mIoU, and every model under-reports the number of occurrences on one-to-many queries, with none exceeding 13.2% count accuracy. Because responses are free-form, we report parsing-failure rate and MAE coverage: parsing failures remain in mIoU, Recall, gIoU, and count metrics as empty predictions but do not enter MAE. The results separate precise localization, occurrence enumeration, and output-format reliability within a benchmark whose cross-subset comparisons are descriptive rather than controlled estimates of query abstraction or duration. We will release the TAG-Bench data and evaluation code to support future research.

Open-fit hearing aids have attracted growing attention due to their superior wearing comfort. However, the open-fit design inevitably causes acoustic leakage into the ear canal, degrading the performance of existing binaural speech enhancement (BSE). To this end, we propose ABSE-NET, an active BSE framework integrating active noise control (ANC) with BSE to jointly enhance target speech and suppress acoustic leakage. The ABSE-NET pipeline cascades a binaural MVDR (BMVDR) with a lightweight neural network (LNN). The former achieves a coarse BSE, whereas the latter simultaneously cancels acoustic leakage and compensates for BMVDR-induced distortion. The LNN uses an encoder-decoder with a feature fusion module, which includes frequency-time dependency learning and convolutional attention blocks. Unlike traditional BSE+ANC solutions via adaptive filtering, ABSE-NET needs no in-ear microphone in practical deployment. Experiments validate its superiority over state-of-the-art methods. Code repository: https://github.com/Bream101/ABSE-NET.

Dominant audio classification pipelines rely either on compact handcrafted summaries or on fixed time-frequency frontends such as log-mel representations prior to deep modeling. While highly successful, these representations do not explicitly expose the physical dynamics of the underlying sound-generating event. We introduce MADS (Multi-view Acoustic Descriptor Set), a compact 19-dimensional physics-informed descriptor set de- signed to capture complementary spectral, temporal, mechanical, and stochastic structure in audio signals. Rather than treating sound only as a spectral pattern, MADS encodes properties related to excitation, damping, periodicity, impulsiveness, and structural consistency within a unified multi-view representation. We evaluate MADS using standard classical machine learning models on ESC-10, ESC-50, and MSoS, and compare it against two conventional handcrafted baselines: a compact 26D MFCC- based baseline and an expanded 38D spectral-summary baseline. Across ESC-10 and ESC-50, MADS achieves the strongest peak results overall, reaching 81.00% and 52.78%, respectively, while using roughly half the dimensionality of the 38D baseline. On MSoS, MADS again delivers the strongest top-end performance, reaching 67.48%. These results establish MADS not merely as a competitive standalone descriptor set, but as the foundational descriptor layer of a broader acoustically grounded representation program for future frame-level and deep-learning-compatible audio modeling.

Target sound extraction (TSE) aims to isolate a sound source of interest from a mixture, given a semantic query. Existing TSE systems are conditioned on fixed class representations tied to individual sound categories, limiting their ability to handle the hierarchical relationships that naturally organize environmental sounds. In this paper, we introduce ontology-based TSE, a new task formulation in which a single model extracts sounds queried at any level of a sound ontology, from fine-grained leaf classes such as cat and dog to high-level categories such as animal. We propose a learnable class embedding table defined over all nodes of an AudioSet-derived ontology, regularized with a Cophenetic Correlation Coefficient (CPCC) loss that aligns embedding distances with shortest-path distances in the ontology tree. Our experiments across different approaches show the benefit of considering the ontology structure when training TSE systems.

Convolutional neural networks (CNNs), used widely and successfully in audio enhancement, capture long-range time-frequency dependencies only indirectly, through successive convolution and pooling. Here, we present U-PAST, a hybrid transformer-U-Net architecture that addresses this limitation through self-attention dependency-modeling in the complex spectrogram domain. U-PAST tokenizes a complex STFT representation, similarly to the magnitude spectrogram tokenization of the Audio Spectrogram Transformer (AST), applies a multi-layer transformer encoder, and reconstructs the enhanced complex spectrogram with a U-Net-style decoder. We evaluate four architectural variants with between 1.17M and 2.40M parameters on the DNS Challenge, VoiceBank-DEMAND, and LibriMix corpora under matched, acoustic mismatch, and two-dataset mismatch conditions. U-PAST attains the best SI-SDR of any evaluated model under acoustic mismatch and closely trails substantially larger convolutional and time-domain baselines by 0.26 dB to 0.63 dB SI-SDR under the remaining three conditions while achieving the strongest perceptual (DNSMOS) quality under dataset mismatch. The largest evaluated configuration, U-PAST-H (2.40M parameters), is consistently the strongest variant of the family, offering an attractive performance-to-cost trade-off at a small parameter footprint.

Codec-based text-to-speech (TTS) models make language-model post-training applicable to speech generation, but it remains unclear when learned perceptual predictors can serve as reinforcement learning rewards without losing alignment with human listeners. We study this question with Group Relative Policy Optimization (GRPO) using learned rewards for anime-like speaking style, naturalness, likability, and arousal. To prevent perceptual rewards from being optimized through transcript drift, we introduce a character error rate (CER) zone constraint and compare policy optimization with Best-of-$N$ reranking under the same reward gate. Across single-reward runs, each reward primarily improves its own target metric, showing that subjective predictors are not interchangeable quality surrogates. Multi-rater A/B tests further show uneven human transfer, while a reward-gap analysis separates average transfer from within-axis calibration: signed reward gaps significantly predict listener choices in the pooled analysis, whereas residual CER gaps do not, but per-axis calibration remains heterogeneous. Best-of-8 is a strong human-level baseline and is not clearly worse than GRPO perceptually, suggesting that GRPO should be viewed as amortizing reward-selected behavior into the policy rather than uniformly outperforming reranking. These results support analyzing subjective speech rewards as predictor-axis-base tuples and provide practical diagnostics for selecting rewards before multi-reward speech post-training.

Joint-Embedding Predictive Architecture (JEPA) has shown strong performance in learning rich representations through self-supervised prediction in latent space. However, it typically relies on teacher–student architecture with an EMA to stabilise training, and can tend to yield uninformative representations. Contrastive learning is stable to train and produces strong global representations, but remains limited on local tasks by the global nature of its objective. In this work, we combine both into CoJEPA: a single shared backbone jointly trained with a JEPA objective on masked sequence tokens and a contrastive objective on the class token. The contrastive gradient provides stability, removing the need for an EMA teacher entirely, while JEPA enriches the sequence tokens via local predictions that contrastive learning alone cannot provide. Crucially, no extra parameters are added to the backbone: the same model is guided towards richer representations purely through the design of its training signal. CoJEPA takes the best of both worlds, outperforming or matching both individual methods across global and local MIR tasks, with a particularly strong advantage on tonal and harmonic understanding, and without any task-specific architectural changes. CoJEPA shows that combining objectives with complementary inductive biases can substitute for scale, encouraging future work to invest in smarter training objectives over ever-larger models.

Generative music systems are increasingly presented as tools that democratize music creation, yet their practical suitability for musicians remains underexplored. Prior work includes openness-focused evaluation frameworks, such as MusGO (Music-Generative Open AI), as well as qualitative studies of musicians' experiences with generative systems. However, these approaches do not support systematic comparison or early-stage discovery of models for creative use. Motivated by such limitations, we introduce MusGU+, a musician-centered evaluation framework organized around three dimensions: Adaptability, Usability, and Controllability. Together, these capture whether a model can be feasibly trained or fine-tuned on personal data, integrated into real-world music workflows, and controlled in musically meaningful ways. We evaluate 10 representative generative music systems and present an interactive discovery tool that enables musicians to explore and filter models according to these criteria. While MusGO remains valuable for promoting responsible research practices, MusGU+ supports informed selection and practical adoption of generative systems by musicians.

The vocal music of each language carries a distinctive sonic identity, even without instrumental accompaniment. We ask whether these differences are measurable and traceable to specific phonemes. To tackle this question, we introduce phoneme-conditional analysis, which isolates the acoustic effect of typologically distinctive phonemes by comparing marker syllables against matched non-marker controls within the same song, holding singer, melody, and genre constant. Across nine typologically diverse languages and thousands of songs, we measure effects along five acoustic dimensions. Song-level profiles built from these effects identify the language of an unaccompanied vocal at 85.5% balanced accuracy in a nine-way classification with folds grouped by artist; whether the separability arises by accumulation of the phoneme-local effects themselves is left open. Our findings suggest that phonological structure leaves systematic and measurable traces in how each language is sung.

Obtaining data from neuromorphic sensors and processing it with Spiking Neural Networks is a promising solution to lower the energy cost of artificial intelligence. The current rarity of natively neuromorphic datasets promotes the development of software tools to translate input sensory data into spikes. However, highly bio-mimetic simulators can be challenging to implement on digital hardware. In this work, we evaluate the neuromorphic encoding and subsequent classification of audio into spikes using a non-learnable, high-level, programmable encoder targeting hardware implementation on FPGA. We quantify the pipeline's efficiency with hardware-agnostic metrics based on the quantitative spiking activity. Our study focuses on the simultaneous optimisation of encoder and classifier: the first provides efficient and informative data so that the latter achieves a better performance with an overall lower energy cost at learning and inference. This work introduces the first end-to-end neuromorphic spike-encoding and evaluation of the TIMIT dataset. Our simple feedforward network reaches a classification accuracy of 99.77% on a spike-encoded Heidelberg Digits, overcoming the neuromorphic state of the art on this benchmark dataset.

Large language model (LLM)-based automatic speech recognition (ASR) systems achieve strong performance on conventional speech data by leveraging powerful linguistic priors and multilingual capabilities. However, under challenging conditions, these priors can override acoustic evidence, resulting in unintended translation, instruction execution, repetition, or catastrophic deletion. We propose Likelihood-Constrained Acoustic Reranking (LCAR), a training-free decoding method that improves acoustic grounding while preserving support from the base model. At each decoding step, LCAR first retains tokens whose base-model likelihood falls within a margin of the greedy token, then reranks them using an acoustic compatibility score computed from attention-pooled audio embeddings and the existing LM head. By restricting acoustic intervention to plausible, model-supported alternatives, LCAR requires no additional training, external detector, reference transcript, or auxiliary model at inference. We evaluate LCAR on four LLM-based ASR systems using human-audited TTS and open-source speech challenge suites. At $\delta=0.60$, LCAR removes 38.8–57.1% of detector-identified hallucination failures while largely maintaining WER/CER on standard open-source test sets.

This paper proposes two spectrally weighted STFT loss functions for lightweight streaming speech enhancement, addressing the magnitude over-attenuation in mid-to-high frequency regions caused by the magnitude-phase compensation effect. The proposed sigmoid-weighted loss applies a smooth frequency-dependent modulation to the phase-aware contribution, while the signal-dependent spectrally adaptive loss further conditions the modulation on the ground-truth log-magnitude spectrogram. To evaluate the proposed objectives, we additionally design HyST-Net, a lightweight and competitive backbone with hybrid MHA-GRU spectral-temporal modelling for low-latency streaming scenarios. Experimental results exhibit consistent improvements in high-frequency spectral reconstruction for both losses. The spectrally adaptive loss further enhances the mid-frequency region, resulting in a more balanced spectral reconstruction across the full frequency range.

This paper develops an optically movable Rydberg atomic quantum receiver (RAQR), in which the probe and coupling beams are steered within each vapor cell to dynamically reconfigure the effective radio-frequency (RF) sensing position without mechanical actuation. A closed-form equivalent baseband model is derived by separating the atomic transduction coefficient, optical steering phase, and cell-center array response into distinct factors and the accuracy of the resulting model is validated against numerical solutions of the Lindblad master equation. Based on the derived model, we reveal two complementary channel-shaping mechanisms, including intrinsic beam-pattern shaping through RF-to-optical transduction and per-cell phase control enabled by optical displacement. To further exploit these capabilities, a non-convex sum-rate maximization problem is formulated over the optical positions and local oscillator design and solved via an alternating optimization framework with analytical gradients. Simulation results validate the derived model and demonstrate substantial performance gains enabled by optical movability, highlighting its potential as a programmable receiver architecture for future wireless networks.

Deepfake voice detection suffers from poor generalization across unseen domains. While Audio Large Language Models (ALLMs) show promise, the modality gap between continuous audio embeddings which capture the subtle acoustic details necessary for deepfake detection and the semantic space of LLMs remains a critical, underexplored bottleneck. We address this by benchmarking diverse audio encoders integrated with Qwen LLMs (0.5B to 7B parameters). First, we demonstrate that fine-tuning the LLM alone risks out-of-domain overfitting, making a frozen LLM a stronger, resource-efficient baseline. Second, to explicitly bridge the modality gap, we introduce a cross-modal prompting strategy that injects linguistic-knowledge-driven acoustic features (via openSMILE) as structured text tokens. This explicit textual grounding not only enhances the frozen baseline but also makes LLM fine-tuning more effective. Ultimately, our approach demonstrates state-of-the-art resilience on the out-of-domain ITW and MLAAD benchmarks, yielding over 16.2% absolute improvement in Macro-F1 over existing ALLM baselines while maintaining competitive in-domain performance. All models reported in this work are \href{https://huggingface.co/01Yassine/AudioLLM-Deepfake-Detection}{publicly available}.

Speech enhancement (SE) is commonly applied as a preprocessing step in spoken AI pipelines under the assumption that better audio quality improves downstream task performance. Whether SE-induced distortions propagate to downstream LLM task performance remains an open question. We introduce Output Divergence Rate (ODR), which measures how often SE changes an LLM's intent classification relative to clean speech, and benchmark five conditions on 2,974 SLURP clips using Whisper large-v3 and wav2vec2-large cascades. Every condition produces ODR significantly above zero ($p < 0.001$, binomial test). MetricGAN{+} more than doubles ODR versus unenhanced noisy speech (0.318 vs. 0.135) despite improving PESQ, and unmitigated echo reaches an ODR of 0.836 through speaker substitution, a failure WER cannot capture. Audio quality metrics range from near-zero to moderate correlation with ODR (SQUIM-MOS $\rho=-0.068$, PESQ $\rho=-0.467$). The MetricGAN{+} and echo results replicate across ASR architectures, indicating that standard audio quality metrics are insufficient for LLM pipeline quality.

Tabla Stroke Transcription (TST) is central to the analysis of rhythmic structure in Hindustani music, yet it remains challenging due to complex and dynamic rhythmic organization and the scarcity of strongly annotated data. Existing approaches largely rely on fully supervised learning with onset-level annotations, which are costly and impractical at scale. This work addresses TST in a weakly supervised setting, using only symbolic stroke sequences without temporal alignment of onsets. We propose a framework that combines a Connectionist Temporal Classification (CTC)-based acoustic model with a sequence-level rhythmic language model for rescoring, similar to that used in automatic speech recognition. The acoustic model produces a decoding lattice, which is refined using an Adaptive Dynamic Rhythm Language Model (ADRM) that combines $t\bar{a}la$-conditioned symbolic rhythmic regularities with local stroke dynamics. Moreover, we release a new performance-recorded tabla dataset, named Tabla Improvisation Dataset, along with a complementary synthetic dataset for sequence-level weakly supervised TST. Experiments demonstrate consistent and substantial reductions in stroke error rates with ADRM compared to those with acoustic-only decoding, confirming the benefit of incorporating symbolic rhythmic regularities during lattice rescoring for accurate transcription.

Recent generative music models offer increasingly fine-grained control through text and audio conditioning, yet how faithfully they follow intended emotional cues remains an open question. We address this gap with a unified evaluation pipeline for emotion-following in generated music. Using all 1000 tracks in GTZAN, we extract semantic audio descriptions with DashengLM, an audio captioning model, and estimate source-track valence and arousal with Music2Emotion, a music emotion recognition model. We construct affect-aware text prompts by combining descriptions with top-ranked emotion tags and generate 30-second outputs with three systems, Stable Audio Open, MusicGen, and InspireMusic, evaluating both text- and audio-conditioned generation. To measure emotion-following, we compute valence and arousal on generated audio and compare them with the source tracks using absolute error and Euclidean distance in valence-arousal space. Text-conditioned generation consistently outperforms audio conditioning, with MusicGen (text) and InspireMusic (text) achieving the best performance, while audio-conditioned variants prove less stable. We further find that valence is preserved more reliably than arousal and that emotion-following varies substantially across genres. These findings underscore the importance of evaluating affective controllability directly rather than relying solely on general quality or prompt-relevance metrics.

Low-resource ASR remains difficult because scarce transcripts provide limited supervised evidence for target-side generation. To address this gap, we propose SAMA-ASR, a lightweight adapter mechanism that augments the decoder with semantic anchors from auxiliary translations and an acoustic anchor from speech; in principle, the mechanism can be applied to similar encoder–decoder multitask speech models. Through cross-modal adaptation, SAMA-ASR conditions decoder states on translation-derived semantic embeddings and a speech embedding, combining utterance-level meaning with speech-grounded evidence before token prediction. At evaluation time, these semantic anchors can be generated automatically by an upstream speech-to-text translator rather than supplied as oracle translations. Experiments on two 30-hour datasets covering the low-resource Sinitic varieties Taiwanese Hokkien and Hakka show that SAMA-ASR improves over acoustic, prior prompt-based, and semantic-only translation-guided baselines and remains effective in practical automatic semantic-anchor settings; translator-capacity analyses show that useful semantic anchors can be produced by a compact ST model.

Deep learning has a powerful capability of feature extraction. However, the lack of fairness and interpretability in deep neural networks poses limitations to their adoption in the medical domain. This paper proposes a disentangled representation learning (DisenRL) framework, named the Attributes-based Gaussian Estimation for Disentangled Representation (AGEDR), which incorporates Attribute Mapping Embedding (AME) modules designed to map attributes into vectors and align them with a subset of the latent vectors in a Variational AutoEncoder (VAE). This part of the latent vector will be disentangled from the remaining latent vectors by minimizing mutual information. A classifier is then trained using the mean parameters of the latent vectors from the VAE. Extensive experiments demonstrate that AGEDR outperforms both conventional classification models and existing disentangled representation learning methods. The ablation experiments also indicate the disentangling capability and fairness of AGEDR. The source code is publicly available at https://github.com/ZhaoKe1024/DisentangledRepr.

Unified all-type audio deepfake detection aims to determine whether an input clip is real or fake when its audio type may be speech, environmental sound, singing voice, or music. Existing speech-centric or type-dependent solutions are insufficient for this setting because the test-time audio type is unknown, while the required output is still a single binary decision. To address these issues, this paper proposes a dual-domain SSL fusion method that maps heterogeneous audio into a shared binary authenticity space. EAT-large and wav2vec 2.0 XLS-R-300M are used as complementary SSL feature sources, providing broad acoustic and event-level representations as well as waveform-level, vocal, and speech-sensitive representations. Layer-wise weighted fusion integrates multi-level artifacts from different transformer depths, while token-level fusion forms a unified feature pool without enforcing frame-level alignment between the two SSL streams. The fused tokens are summarized by multi-head attentive statistics pooling and classified with a binary MLP head. With conservative speech refinement applied on top of this unified core detector, the submitted system achieves 95.58% Macro-F1 on the AT-ADD Track 2 evaluation set and ranks second in the challenge.

As air traffic volumes in the National Airspace System continue to expand, in particular at low altitude, the need for scalable decision support tools used by air traffic controllers will also require more development. This article introduces Voice-to-Trajectory for Air Traffic Control, a joint voice communication-flight trajectory data embedding framework, that can be a component of situational awareness in congested airspaces, and assist the development of tools for ATC as they reason in real-time over Automatic Dependent Surveillance-Broadcast trajectories, or the intent expressed by pilots in natural language. We show that these data modalities are not independent and represent a common physical referent: an aircraft flying through the airspace. V2TATC maps a voice instruction and the trajectory of the addressed aircraft to nearby points in a single latent space that can be queried in both directions. It combines a self-supervised trajectory encoder, a frozen speech encoder, a contrastive joint embedding, and a bijective lifting via normalizing flows. We demonstrate V2TATC's effectiveness on the San Francisco Bay Area, for its concentration of major airports, and its mix of commercial and general aviation traffic. Lastly, we release a novel paired voice-trajectory dataset, and report experiments on cross-modal retrieval, ablations, and latent-space analysis.

Affective cues across modalities may be incongruous (e.g., sarcasm or mocking praise), potentially leading to misinterpretation when relying on a single modality. Large Audio-Language Models (LALMs) have recently gained popularity and been applied to multimodal emotion recognition, but their ability to disentangle acoustic and semantic cues, especially in incongruent cases, remains underexplored. To address this gap, we introduce CREMA-ASIS, a dataset specifically created to investigate incongruence between acoustic emotion and semantic sentiment cues. It pairs acoustic emotion labels with semantic sentiment polarities. Using this dataset, we evaluate LALM biases within a multitask framework and conduct a layer-wise analysis to identify modality dominance across layers. Our findings reveal that LALMs struggle with semantic-acoustic incongruent cases, rarely predicting incongruity, and that LALMs are predominantly influenced by semantic information. However, supervised fine-tuning significantly improves LALM performance on our CREMA-ASIS test set while preserving transcription accuracy and joint emotion recognition. Results demonstrate potential for enhancing both acoustic and semantic understanding on out-of-domain data.

An avatar that holds a conversation should decide what to say and to move while saying it, yet these abilities live in separate model families: spoken dialogue models produce speech without motion, and co-speech motion models produce motion only from audio handed to them. The standard remedy is a cascade that first generates the spoken response and then runs a motion model over the finished audio, which requires a second full inference pass and precludes any joint optimisation between the two. We present Motion-Omni, an end-to-end framework in which a spoken dialogue model natively outputs explicit facial expression together with hand, upper-body and lower-body motion, generated directly from the hidden states that produce the speech. Joint training is not optional here: with the speech pathway frozen, motion remains misaligned with the audio, and co-adapting the LLM, Speech Generator and Motion Generator under both objectives is what recovers alignment while retaining spoken-dialogue ability. Supervision comes from a scalable, model-agnostic pipeline that pseudo-labels consistent-voice speech responses with a replaceable motion teacher, yielding 422,856 quality-ranked pairs (1,402 hours). We further release SwDA-500 and, to our knowledge, the first public evaluation protocol for stochastic open-ended full-body spoken dialogue, matching audio across motion systems while unifying rendering, automatic metrics, human evaluation, and latency measurement. Instantiated with a Qwen2.5-7B-Instruct backbone, Motion-Omni-Q7 matches the same-audio teacher cascade to within 2% on reference-free motion metrics while responding 5.4 x faster (RTF=0.78, faster than real time), surpasses all non-teacher cascades on beat correlation and diversity, and reaches a 2.62% word error rate, the lowest among the omni-modal systems compared.

We describe our submission to Task A of the 1st DAFx parameter estimation challenge. The task is to recover the six physical parameters of a simulated metal-plate reverberator – its dimensions and material properties – from a single impulse response (IR). We treat this as a black-box optimization: candidate parameter sets are fed to the simulator and scored by a loss against the target IR. The method has two stages. The first uses CMA-ES, an evolutionary optimizer, to recover five of the six parameters, comparing IRs under an amplitude-normalized loss. Amplitude normalization makes the search robust but discards the cue to the sixth parameter, the plate's surface density; a second stage therefore estimates it alone, with a ternary search on the un-normalized loss. As the choice of loss strongly affects the search, we select it beforehand, and analyze why compression in the common multi-scale spectral loss degrades recovery. Finally, we test our method on a validation set of 50 IRs, discuss a pathological failure mode, and ablate to justify having two different stages instead of a unified CMA-ES search.

Cochlear implants (CI) restore hearing for individuals with severe to profound hearing loss. However, CI users often struggle to understand speech in noisy environments. Deep neural networks (DNN) have shown promise in enhancing speech for CI users, yet their high energy demands make them non-ideal for low-power CI processors. Spiking neural networks (SNN), on the other hand, offer comparable performance with significantly lower energy consumption. Hence, we propose a novel SNN inspired by the Deep ACE architecture that simultaneously performs speech enhancement and CI coding. Our model achieves competitive vocoded short-time objective intelligibility (VSTOI) and signal-to-noise ratio improvement (SNRi) scores compared to Deep ACE, while achieving more than a sixfold reduction in energy consumption.

Deep neural networks (DNNs) based on state-space models (SSMs) are increasingly applied to speech processing, but typically operate on pulse-code-modulated (PCM) audio. This constrains deployment on low-power, always-on edge devices, which commonly use single-bit pulse-density-modulated (PDM) micro-electromechanical (MEMS) microphones for their noise robustness, low cost, and variable sampling rates that enable low-power operation. In fact, converting PDM to PCM requires low-pass filtering and decimation, imposing costly overhead on resource-constrained hardware. While prior works have attempted to process PDM signals directly, they require long training times and generalize poorly across sampling rates. In this paper, we show that the SSM has two key properties that remediate these issues: its continuous-time parametrization allows it to produce a consistent representation of the input audio signal, regardless of the modulation strategy and sampling rate, and its long-term memory enables this representation to be aggressively downsampled without needing any anti-aliasing operations. We then propose a novel end-to-end PDM speech processing architecture that uses an SSM to encode the input audio signal into a modulation- and sampling-rate-invariant latent representation. We show that our proposed architecture achieves robust speech classification and enhancement gains at low-power sampling-rates (512 kHz) and similar performance to state-of-the-art algorithms operating on PCM data when tested on standard PDM sampling-rates of 2 MHz. Moreover, we show that the SSM's output can be downsampled by more than 65,000 times, thus significantly reducing the number of processing timesteps in downstream layers.

Separating individual musical instruments within a complex mixture of sounds poses a persistent challenge for listeners with hearing loss. Although spatial separation of sources improves speech recognition in this population, the potential benefits of spatial cue enhancement for music perception remain largely unexplored. This paper introduces a method to increase spatial cue salience through the augmentation of individual head-related transfer functions (HRTFs). Auditory model analyses indicate that augmented HRTFs may enhance the separability of musical instruments relative to individual HRTFs. Predicted benefits persist when moderate sensorineural hearing loss is modelled, though they are substantially reduced. Simulated hearing aid processing does not restore these benefits to normal-hearing levels.