Puming Zhan

Improving Speed/Accuracy Tradeoff for Online Streaming ASR via Real-Valued and Trainable Strides

The Conformer Transducer (CT) is arguably the most popular architecture for online streaming end-to-end (E2E) ASR systems. Since it has quadratic complexity in the input sequence length for computing the attention weights, downsampling the input sequence to reduce its length is an effective way to m…