30 citations · 36 across the 16 of their papers we have counts for
Showing 2023Show all
2 papers · 1 filter
eess.AS2023
Globally Normalising the Transducer for Streaming Speech Recognition
Rogier van Dalen
The Transducer (e.g. RNN-Transducer or Conformer-Transducer) generates an output label sequence as it traverses the input sequence. It is straightforward to use in streaming mode,…
cs.CL2023★ 1 cited
SummaryMixing: A Linear-Complexity Alternative to Self-Attention for Speech Recognition and Understanding
Titouan Parcollet, Rogier van Dalen, Shucong Zhang +1
Modern speech processing systems rely on self-attention. Unfortunately, token mixing with self-attention takes quadratic time in the length of the speech utterance, slowing down in…