Conformer-Based Hybrid ASR System For Switchboard Dataset

IEEE International Conference on Acoustics Speech and Signal Processing, pp. 7437–7441

Abstract

The recently proposed conformer architecture has been successfully used for end-to-end automatic speech recognition (ASR) architectures achieving state-of-the-art performance on different datasets. To our best knowledge, the impact of using conformer acoustic model for hybrid ASR is not investigated. In this paper, we present and evaluate a competitive conformer-based hybrid model training recipe. We study different training aspects and methods to improve worderror-rate as well as to increase training speed. We apply time downsampling methods for efficient training and use transposed convolutions to upsample the output sequence again. We conduct experiments on Switchboard 300h dataset and our conformer-based hybrid model achieves competitive results compared to other architectures. It generalizes very well on Hub5’01 test set and outperforms the BLSTM-based hybrid model significantly.

Authors 6

1. Mohammad Zeineldeen Aachen Computer Science Department

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University,Human Language Technology and Pattern Recognition,Computer Science Department,Aachen,Germany,52074

   AppTek GmbH, Aachen, Germany

2. Jingjing Xu Aachen Computer Science Department

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University,Human Language Technology and Pattern Recognition,Computer Science Department,Aachen,Germany,52074

3. Wilfried Michel Aachen Computer Science Department

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University,Human Language Technology and Pattern Recognition,Computer Science Department,Aachen,Germany,52074

   AppTek GmbH, Aachen, Germany

4. Alexander Gerstenberger Aachen Computer Science Department

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University,Human Language Technology and Pattern Recognition,Computer Science Department,Aachen,Germany,52074

5. Ralf Schlüter Aachen Computer Science Department

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University,Human Language Technology and Pattern Recognition,Computer Science Department,Aachen,Germany,52074

   AppTek GmbH, Aachen, Germany

6. Hermann Ney Aachen Computer Science Department

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University,Human Language Technology and Pattern Recognition,Computer Science Department,Aachen,Germany,52074

   AppTek GmbH, Aachen, Germany