145 papers
This paper proposes Style-Guided Motion Diffusion (SGMD), a novel framework that integrates a Transformer-based architecture with a Style Modulation module and spatial-temporal masking to generate realistic, music-aligned dance sequences that are both stylistically consistent and flexibly controllable for tasks like trajectory generation, in-betweening, and inpainting.
This study demonstrates that strong correlations exist between subjective perceptual ratings and objective acoustic measures in head and neck cancer patients, suggesting that a single intelligibility measure may be sufficient for clinical monitoring of speech following chemoradiation treatment.
This paper presents a quantum-inspired extension of the GenomeBits model that characterizes finite (0,1) binary sequences, such as genome data, by treating them as wavefunctions to reveal sound-wave-like features in their real and imaginary spectra.
The paper proposes ExSampling, an integrated system combining a recording application and a Deep Learning environment to enable the real-time ensemble performance of field-recorded environmental sounds through automated sound mapping to Ableton Live tracks.
This paper presents a technical tutorial demonstrating that building enterprise-grade realtime voice agents requires a cascaded streaming pipeline (STT LLM TTS) rather than native speech-to-speech models, achieving sub-second latency through the systematic integration of components like Deepgram, vLLM, and ElevenLabs.
The paper proposes MSpoof-TTS, a training-free inference framework that enhances zero-shot discrete speech synthesis by integrating multi-resolution token-based spoof detection into a hierarchical decoding strategy to prune artifacts and improve perceptual realism without retraining.
The paper proposes SLICE, a speech enhancement method that improves performance on compound real-world degradations by injecting degradation conditioning into the timestep embedding to propagate through all residual blocks, outperforming both unconditioned models and prior input-level conditioning approaches.
This paper introduces PolyBench, a new benchmark designed to evaluate compositional reasoning in polyphonic audio across five distinct tasks, revealing that current Large Audio Language Models consistently struggle with the complexity of concurrent sound events.
This paper introduces TW-Sound580K, a rigorously curated Taiwanese audio-text dataset created via a Verify-Generate-Critique protocol, which significantly enhances localized audio-language modeling performance when used to train the Tai-LALM model with dynamic arbitration strategies.
This paper proposes a training dynamics-aware multi-factor curriculum learning framework for target speaker extraction that jointly schedules multiple difficulty factors and utilizes the TSE-Datamap visualization tool to analyze training dynamics, thereby enabling data-driven progressive learning that significantly improves performance in complex multi-speaker scenarios.
This paper presents the first Environmental Sound Deepfake Detection (ESDD) challenge, detailing its task formulation, dataset, evaluation protocols, and key insights from 97 participating teams to advance robust detection methods and guide future research in this underexplored field.
This paper proposes Focus-Then-Listen (FTL), a plug-and-play audio enhancer that improves the noise robustness of Large Audio Language Models by separating speech from non-speech sounds and generating task-adaptive enhanced signals without requiring expensive model retraining.
SarcasmMiner is a reinforcement learning-based post-training framework that employs a dual-track distillation strategy with a generative reward model and group relative policy optimization to significantly enhance robust audio-visual sarcasm reasoning and reduce hallucinations in foundation models.
Latent-Mark is a novel zero-bit audio watermarking framework that achieves robustness against neural resynthesis by embedding watermarks within a codec's invariant latent space through cross-codec optimization, ensuring both semantic resilience and perceptual imperceptibility.
WavSLM is a single-stream speech language model that achieves competitive speech generation and consistency without text supervision by quantizing and distilling WavLM representations into a single codebook for autoregressive next-chunk prediction.
This paper introduces ASR-TRA, a novel test-time reinforcement learning framework that leverages audio-text semantic rewards and causal intervention to overcome confirmation bias in existing adaptation methods, thereby significantly improving ASR robustness and accuracy in noisy and accented environments without ground-truth labels.
This paper presents WhisperAlign, a solution for the DL Sprint 4.0 that combines word-boundary-aware ASR using whisper-timestamped chunking and domain-fine-tuned Pyannote diarization anchored by WhisperX to achieve high-accuracy transcription and speaker separation for long-form Bengali speech.
This paper demonstrates that applying the SAM-Audio speech enhancement model as a preprocessing step for zero-shot ASR with Whisper consistently degrades recognition accuracy despite improving perceptual audio quality, revealing a fundamental mismatch between human-perceived signal cleanliness and machine recognition robustness.
This paper addresses the underexplored role of temporal pooling in training-free anomalous sound detection by proposing and evaluating adaptive strategies, specifically Relative Deviation Pooling (RDP) and a hybrid approach, which achieve state-of-the-art performance across multiple benchmarks and outperform previously reported trained systems.
This paper introduces VoxKnesset, a large-scale open-access dataset of 2,300 hours of longitudinal Hebrew parliamentary speech spanning 2009–2025, which is used to benchmark and demonstrate the challenges of speaker verification and age prediction over time, revealing significant performance degradation in standard models as speakers age.