Rogier van Dalen

BLOG | Samsung Research Globally Normalizing the Transducer for Streaming Speech Recognition

There is now a blog post explaining how to fix the mathematics of streaming speech recognisers. research.samsung.com/blog/Globall...

Globally Normalizing the Transducer for Streaming Speech Recognition 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, where it generates p...

Your streaming speech recognizer is probably mathematically flawed, degrading its accuracy. Ask me to explain how to fix this next week in the Thursday morning poster session at #ICASSP, or look at ieeexplore.ieee.org/abstract/doc...

a person is using a bosch drill to drill the f5 and f6 keys ALT: a person is using a bosch drill to drill the f5 and f6 keys

#ICASSP2025