Conformer-based Hybrid ASR System for Switchboard Dataset
This work addresses the performance of hybrid ASR systems for speech recognition tasks, but it is incremental as it adapts an existing architecture to a different model type.
The paper tackled the problem of applying the conformer architecture to hybrid automatic speech recognition (ASR) systems, achieving competitive results on the Switchboard 300h dataset and significantly outperforming a BLSTM-based hybrid model on the Hub5'01 test set.
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.