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…

The paper uses sparse autoencoders to identify specific latent features within LLM-based TTS models, enabling interpretable and fine-grained control over emotional expression by intervening in small s…

MindVoice is a neuro-to-speech framework that uses pretrained priors to disentangle and reconstruct intelligible speech from noisy, non-invasive neural signals, significantly outperforming existing me…

LoSATok proposes a low-dimensional semantic-acoustic tokenizer that efficiently compresses high-dimensional audio features into a compact latent space, significantly improving the performance and effi…

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…