Rogier van Dalen
@rogiercvd.bsky.social
Researcher in machine learning (speech recognition / private federated learning) in Cambridge
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...
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...
ieeexplore.ieee.org
April 1, 2025 at 3:47 PM
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...
Reposted by Rogier van Dalen
