One Model, Many Latencies: Universal Speech Enhancement for Diverse Real-Time Applications

One Model, Many Latencies: Universal Speech Enhancement for Diverse Real-Time Applications

A universal speech enhancement model with configurable algorithmic and computational latency controls using parallel convolutions and early-exit mechanisms.

Hugging Face · Daily Papers ·Szu-Wei Fu, Rong Chao · ·▲ 16 upvotes

Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.

Autores: Szu-Wei Fu, Rong Chao, Xuesong Yang, Sung-Feng Huang, Ante Jukić, Yu Tsao

  • 16 upvotes da comunidade
  • Temas: speech enhancement, real-time, latency budget, look-ahead frames, parallel convolutional layers, early-exit mechanism

Resumo

Resumo original (em inglês), extraído do paper:

A universal speech enhancement model with configurable algorithmic and computational latency controls using parallel convolutions and early-exit mechanisms.

Onde ler

compartilhar: