Julian Silva, Jaliya Kodithuwakku, Navindu Sirimanna, Shaveen Herath, Wageesha N. Manamperi, Joshua P. Kulasingham · 2026 · arXiv
DOI: 10.48550/arXiv.2610.29815 · open-access PDF
Impulsionada por avanços recentes em dispositivos de assistência auditiva, a extração de alto-falantes-alvo (TSE) em ambientes multi-talker atraiu atenção significativa. Para resolver isso, as tecnologias auditivas identificam a atenção usando sinais neurais gravados via electroencefalografia (EEG) para orientar a TSE, permitindo a descodificação de atenção auditiva neuro-direcionada. No entanto, a maioria das técnicas existentes dependem de mascaramento de frequência do tempo, que sofre de baixa fidelidade em regiões de sobreposição do espectro-tempo e é muitas vezes restrita a áudio de banda estreita. Em contraste, apresentamos o NeuroCodec, que, ao melhor de nosso conhecimento,
Machine translation (Meta M2M100); the English original follows.
Driven by recent advancements in hearing assistive devices, target speaker extraction (TSE) in multi-talker environments has drawn significant attention. To address this, hearing technologies identify attention using neural signals recorded via electroencephalography (EEG) to guide TSE, enabling neuro-steered auditory attention decoding. However, most existing techniques rely on time-frequency masking, which suffers from low fidelity in spectro-temporally overlapping regions and is often restricted to narrowband audio. In contrast, we introduce NeuroCodec, which, to the best of our knowledge,
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.29815, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange