1. [Publications](/publications)
2. Citrinet: Closing the Gap between Non-Autoregressive and Autoregressive End-to-End Models for Automatic Speech Recognition
 
 # Citrinet: Closing the Gap between Non-Autoregressive and Autoregressive End-to-End Models for Automatic Speech Recognition

  ![Publication image](/sites/default/files/styles/wide/public/default_images/default.jpeg?itok=qUFsuJCP "Publication image")

 We propose Citrinet - a new end-to-end convolutional Connectionist Temporal Classification (CTC) based automatic speech recognition (ASR) model. Citrinet is deep residual neural model which uses 1D time-channel separable convolutions combined with sub-word encoding and squeeze-and-excitation. The resulting architecture significantly reduces the gap between non-autoregressive and sequence-to-sequence and transducer models. We evaluate Citrinet on LibriSpeech, TED-LIUM2, AISHELL-1 and Multilingual LibriSpeech (MLS) English speech datasets. Citrinet accuracy on these datasets is close to the best autoregressive Transducer models.



 ## Authors



Somshubra Majumdar (NVIDIA)

Jagadeesh Balam (NVIDIA)

Oleksii Hrinchuk (NVIDIA)

Vitaly Lavrukhin (NVIDIA)

Vahid Noroozi (NVIDIA)

Boris Ginsburg (NVIDIA)

 

 

 ## Publication Date



Monday, April 5, 2021

 

 ## Research Area



[Speech Processing](/research-area/speech-processing)

 

 

 ## External Links



[Paper](https://arxiv.org/abs/2104.01721)