Text-to-speech systems are commonly judged by feeding synthetic speech into an automatic speech recognizer and measuring word error rate against the input text, a procedure that inevitably mixes ASR mistakes with true synthesis errors. This paper isolates the ASR component of that verifier's floor by running the same three recognizers on the original human recordings from LibriSpeech and FLEURS, then comparing three scoring rules: the standard ASR round-trip, a single-recognizer mask that ignores words missed in human speech, and a three-recognizer adjudication. The work matters because it shows that a large share of apparent rare-word TTS error is purely recognizer failure, and it provides principled recommendations—such as reporting per-frequency ASR baselines and avoiding the single-recognizer mask—for fairer TTS evaluation.

MixJudge tackles the problem of assessing vocal mixes via natural language queries, a capability that existing audio-language systems do not separately test. The authors synthesize a curriculum of 11 mixing issues at multiple severity levels and train a contrastive audio-text critic that learns to retrieve issues, discriminate opposites, and order severity. Their menu-selection experiments further show that issue evidence transfers to ranking real processing candidates against professional mixes, offering a concrete form of explicit, comparable mixing assistance.

Joint audio-visual diffusion models repeatedly run both denoising branches and expensive cross-modal attention at every step, making inference costly. CAVC observes that audio-side drift caused by mid-stage caching can be repaired by a few terminal joint steps, whereas video-side degradation persists, and exploits this asymmetry with a training-free sandwich structure: full joint warm-up, video-only continuation with cached audio, and brief terminal recoupling. The result is a modest wall-clock speedup with improved visual dynamics, though the gains are bounded by the preserved video backbone.

Nepali–English code-switched ASR suffers from script confusion and switch-point fragility, yet human annotated conversational audio is costly. This paper curates a 15.45-hour spontaneous podcast benchmark and adapts a 1.2B-parameter multilingual encoder–decoder model using only 0.95 hours of synthetic dual-engine TTS data. The core finding is that supervised fine-tuning drives almost all cross-domain transfer, while subsequent GRPO and script-aware rewards add only marginal, hard-to-disentangle gains. The released data and the cautionary ablation make the work practically useful.

This paper tackles the underexplored problem of token sparsification in audio transformers, where self-attention cost grows quadratically with input length. The authors systematically compare pruning and merging strategies across model sizes and datasets, and propose frequency-aware heuristics—Spectral Flatness (SF) and Low-Frequency Energy (LFE)—to score token importance. Their core finding is that audio-specific spectral cues consistently outperform generic attention-only methods in post-training settings, offering a practical path to faster inference on spectrogram-based models.

Text-to-music alignment is usually tested with a single global similarity score that hides which specific musical attributes are missing or misaligned. This paper proposes MQAScore, a fine-grained evaluator that uses a large audio language model to verify each atomic concept—across genre, instrument, mood\/theme, vocal, and usage dimensions—via binary question answering. The work matters because it moves beyond opaque global scores toward interpretable, per-dimension diagnostics that can directly guide improvements in text-to-music generation systems.

Underwater vessel recognition is limited by scarce training data and small public benchmarks. This paper introduces ONCship, a 4521-hour corpus curated from Ocean Networks Canada hydrophones and Automatic Identification System vessel metadata. It evaluates domain-specific self-supervised pre-training, supplementary supervised fine-tuning, and MMSI-Level individual vessel classification, showing that scale and metadata can improve representations even though downstream gains are architecture-dependent and uneven.

Speech Emotion Recognition (SER) models and Audio LLMs often suppress vocal emotion when it contradicts transcribed text—a bias the authors label Semantic Dominance. To probe this, they introduce ASPIRE, a fully synthetic benchmark of adversarial audio-text pairs generated via EmotiVoice, and propose ACR-Net, a dual-stream Whisper-based architecture that uses a Contrastive Decoupling Loss to push conflicting acoustic and semantic representations toward orthogonality. The work claims state-of-the-art Acoustic Accuracy on both adversarial and standard congruent datasets.

Multi-party floor control is the next bottleneck for full-duplex voice agents: systems must decide not just when speech ends, but whether overlapping listeners are backchanneling or genuinely taking the floor. MultiPartyTurnBench introduces 240 synthetically generated, channel-separated conversations spanning two to five speakers and six interaction types, evaluating End-of-Turn (EOT) and Interruption (INT) detection with exact causal annotations. The results reveal a stark capability asymmetry: turn completion is largely tractable, while selective interruption handling remains near chance even for state-of-the-art commercial agents.

Multilingual speech technologies still fail to reach most of the world's languages because existing corpora are limited to a few hundred well-resourced languages and narrow domains like parliamentary proceedings or Bible readings. ELARSpeech addresses this gap by curating 30,202 hours of speech across 675 underrepresented languages from the Endangered Languages Archive, yielding both labeled and unlabeled subsets with rich acoustic and communicative diversity. It matters because it provides a large-scale, publicly available testbed that reveals existing self-supervised speech models struggle on the true linguistic long tail despite massive pretraining.

Sound classification with transformers usually demands stacking many layers, which inflates parameters and compute. LAST asks whether the same blocks can be reused to refine only a single class token while keeping audio features fixed, trading depth for recurrence. Their looped Audio Spectrogram Transformer matches or exceeds deeper sequential baselines on AudioSet at roughly half the parameter count, suggesting that how tokens are updated matters as much as how many layers exist.

Speech-based Alzheimer's assessment increasingly relies on self-supervised learning models, but their vulnerability to nuisance acoustic factors remains unclear. This paper asks whether noise and reverberation are merely encoded in SSL representations or actively drive diagnostic predictions. Using controlled input- and representation-space interventions on the ADReSSo dataset, the authors show that acoustic manipulations systematically shift classifier outputs even when no baseline group difference exists, challenging the assumption that predictive accuracy implies robustness.

Deep learning audio research hides a massive energy footprint behind the final training run. This paper develops a methodology to estimate the full development-phase cost of audio DL projects by mining job logs from the Grid5000 shared computing platform. By tracing thousands of individual jobs across four representative projects, the authors show that prototyping, debugging, and hyper-parameter search can consume $3 imes$ to $256 imes$ more energy than training the reported best models, calling for systematic lifecycle reporting.

AURAL tackles the tension between reasoning quality and low latency in speech language models by replacing explicit chain-of-thought with adaptive latent reasoning. Instead of generating slow text intermediates, the model predicts chunks of continuous latent states drawn from a Gaussian mixture, cutting time to the first token by more than 11x while largely matching explicit CoT accuracy across two backbones. The work also constructs AuralReason-683K, a bilingual corpus of 683K utterances with concise reasoning traces used to initialize latent training.

This paper tackles video-to-speech (V2S) synthesis, where the central challenge is a one-to-many mapping: visually identical lip movements can correspond to different phonemes. The proposed Watch Your Speech (WYS) framework injects explicit textual conditioning—ground-truth text during training and lip-reader predictions at inference—into a conditional flow matching model via an attention-based fusion module. The key question is whether training-time textual guidance can outperform inference-only classifier guidance while preserving naturalness.

Cross-lingual dysarthria detection in Parkinson's disease is hampered by language-dependent structure in self-supervised speech representations that confounds pathology classification. This paper proposes a centroid-based 'language shift' (LS) that aligns source-language embeddings toward target-language distributions using only healthy control speech, enabling zero-shot transfer without model retraining. The approach addresses the critical data scarcity in clinical speech applications while aiming to disentangle linguistic variation from motor impairment markers.

This paper tackles the problem of speaker traits entangling with synthesis source information in speech deepfake source verification. The authors propose a Speaker-Disentangled Metric Learning (SDML) framework that combines Chebyshev polynomial approximations for gradient stability with Riemannian geometry (hyperbolic space) to separate speaker identity from source generator artifacts. Evaluated on four new cross-protocols using the MLAAD benchmark, the method aims to prevent models from relying on speaker shortcuts when verifying synthetic speech origins.

AnimalCLAP addresses zero-shot species recognition from vocalizations—a critical challenge for biodiversity monitoring when training data is scarce for rare species. The core idea is to inject hierarchical taxonomic knowledge (class, order, family, genus, species) into audio-text contrastive learning via multiple prompt templates, paired with a large dataset of 4,225 hours covering 6,823 species annotated with 22 ecological traits. This matters because it enables automated monitoring in visually occluded habitats like dense forests while inferring biological traits directly from sound.

This paper proposes SqueezeComposer, a long-form music generation framework that tackles computational constraints by applying temporal speed-up (e.g., 2×, 4×, 8×) to compress audio sequences before generation. The core idea is to generate music in an accelerated domain using diffusion models, then restore it to normal speed, theoretically enabling models to produce 10+ minute compositions with fixed memory budgets. The approach is tested on continuation, completion, and singing accompaniment tasks.

This paper studies the coupling between three design axes in audio representation learning: input frontend (raw waveform vs. spectrogram), backbone architecture (Mamba vs. attention), and sequence length. The authors introduce HELIX, a minimal hybrid architecture with five bidirectional Mamba layers and one attention bottleneck at matched 8.3M parameter capacity. The key finding is that these choices are not independent: raw waveforms help with Mamba but not attention, attention hurts on short environmental sounds but becomes critical at 30,000 tokens (5 minutes), where pure attention fails with OOM errors and HELIX closes an 11.5-point gap over pure Mamba on speaker identification.