Linear Time Complexity Conformers with SummaryMixing for Streaming Speech Recognition

Titouan Parcollet,Rogier van Dalen,Shucong Zhang, Sourav Batthacharya

CoRR（2024）

引用 0|浏览2

关键词

Time Complexity,Speech Recognition,Linear Time Complexity,Length Of Utterance,Speech Utterances,Time Step,Decoding,Sequence Length,Convolutional Layers,Nonlinear Function,Input Sequence,Recognition Accuracy,Convolution Kernel,Language Model,Single Vector,Memory Consumption,Self-supervised Learning,Current Frame,Multi-head Self-attention,Word Error Rate,Automatic Speech Recognition System,Quadratic Complexity,Chunk Size,Future Frames,Peak Memory

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要