Suchergebnisse - "Short sequence encoder–decoder framework"

Efficient time-domain speech separation using short encoded sequence network

Autoren: Debang Liu Tianqi Zhang Mads Græsbøll Christensen et al.

Quelle: Liu, D, Zhang, T, Christensen, M G, Ma, B & Deng, P 2025, 'Efficient time-domain speech separation using short encoded sequence network', Speech Communication, vol. 166, 103150. https://doi.org/10.1016/j.specom.2024.103150

Schlagwörter: Computational complexity, Short sequence encoder–decoder framework, Multi-temporal resolution Transformer, Speech separation

Zugangs-URL: http://www.scopus.com/inward/record.url?scp=85211171172&partnerID=8YFLogxK
https://doi.org/10.1016/j.specom.2024.103150
https://vbn.aau.dk/da/publications/c8112047-4149-46d3-a4c7-c60c94965fca

Speech Separation Using Advanced Deep Neural Network Methods: A Recent Survey.

Autoren: Wang, Zeng Luo, Zhongqiang

Quelle: Big Data & Cognitive Computing; Nov2025, Vol. 9 Issue 11, p289, 37p

Schlagwörter: ARTIFICIAL neural networks, SIGNAL separation, LOSS functions (Statistics), TECHNOLOGICAL innovations, ACOUSTIC signal processing, SOFTWARE architecture, SCIENTIFIC method

Efficient time-domain speech separation using short encoded sequence network.

Autoren: Liu, Debang Zhang, Tianqi Christensen, Mads Græsbøll et al.

Quelle: Speech Communication; Jan2025, Vol. 166, pN.PAG-N.PAG, 1p

Schlagwörter: TRANSFORMER models, COMPUTATIONAL complexity, SPEECH, SPEED, ENCODING