Sorry, you need to enable JavaScript to visit this website.

Conformer-based Hybrid ASR System for Switchboard Dataset

Citation Author(s):
Submitted by:
Jingjing Xu
Last updated:
14 May 2022 - 6:33am
Document Type:
Demo
Document Year:
2022
Event:
Presenters:
Jingjing Xu
Paper Code:
SPE-50.3

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.

up
0 users have voted:

Files

ICASSP-presentation-slides.pdf

(30)

ICASSP-paper-poster.pdf

(45)