The paper introduces Target Speaker Tagging (TST), a task that combines speaker diarization, verification, and identification into a single workflow for multi-speaker conversations. It presents TST-Be…

Echo is a joint-embedding predictive architecture that uses a single, pretrained ViT encoder to simultaneously perform speaker diarization, speech recognition, and dynamic source separation in a share…

A Wave-U-Net model is trained to extract a fundamental waveform from input speech signals for accurate and robust instantaneous pitch estimation.

The paper proposes a novel workflow to extract fine-grained regional accent features in Brazilian Portuguese using only acoustic labels and a phoneme-based forced aligner, showing that localized featu…

The paper proposes Domain-Aware Sharpness Minimization (DASM), a novel optimizer that enhances the robustness and generalization of voice stream steganalysis models across varying data distributions.

The paper introduces BEA-Dialogue+, an expanded 200-hour corpus for Hungarian conversational ASR, demonstrating that while larger data is challenging, specialized fine-tuning techniques significantly…

The paper introduces a novel Clean-Referenced Feature-Vocoder Attack, a black-box adversarial attack that perturbs high-level SSL feature representations instead of raw audio waveforms, achieving supe…

MelShield is a robust, in-generation audio watermarking framework that embeds identifiable signals into AI-generated speech in the Mel-spectrogram domain for reliable copyright protection and attribut…

This paper introduces 'implicit identity' as a unifying framework to survey and categorize LLM fingerprinting and watermarking techniques for verifying ownership and provenance across datasets, models…

The paper introduces GRIDS, a framework using Local Intrinsic Dimensionality (LID) to detect anomalies in self-supervised speech model representations, showing that LID elevation correlates with ASR d…

The paper introduces three new Korean speech benchmarks (KVoiceBench, KOpenAudioBench, and KMMAU) to evaluate SpeechLMs, demonstrating that English-centric evaluation fails to capture performance gaps…

PolySpeech-100 introduces a massive, multi-lingual benchmark covering 110 linguistic variants to rigorously test Speech-LLMs, demonstrating that open-source models struggle with low-resource languages…