Conformer-based Hybrid ASR System for Switchboard Dataset

arXiv (Cornell University)

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 word-error-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 AppTek GmbH Human Language Technology and Pattern Recognition Computer Science Department

   RWTH Aachen University · FH Aachen

   Affiliation as printed

   AppTek GmbH , 52062 Aachen , Germany

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

2. Jingjing Xu Aachen Human Language Technology and Pattern Recognition Computer Science Department

   RWTH Aachen University

   Affiliation as printed

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

3. Wilfried Michel Aachen AppTek GmbH Human Language Technology and Pattern Recognition Computer Science Department

   RWTH Aachen University · FH Aachen

   Affiliation as printed

   AppTek GmbH , 52062 Aachen , Germany

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

4. Alexander Gerstenberger Aachen Human Language Technology and Pattern Recognition Computer Science Department

   RWTH Aachen University

   Affiliation as printed

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

5. Ralf Schlüter
6. Hermann Ney Aachen AppTek GmbH Human Language Technology and Pattern Recognition Computer Science Department

   RWTH Aachen University · FH Aachen

   Affiliation as printed

   AppTek GmbH , 52062 Aachen , Germany

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