Affiliations: [a] School of Computer, Electronics and Information, Guangxi University, Nanning, Guangxi, China | [b] Guangxi Key Laboratory of Multimedia Communications and Network Technology, Guangxi University, Nanning, Guangxi, China | [c] School of Foreign Language, Guangxi University, Nanning, Guangxi, China
Correspondence:
[*]
Corresponding author: Xuejun Zhang, School of Computer, Electronics and Information, Guangxi University, Nanning, Guangxi, China. E-mail: xjzhang@gxu.edu.cn.
Abstract: The Convolution-augmented Transformer (Conformer) model, which was recently introduced, has attained state-of-the-art(SOTA) results in Automatic Speech Recognition (ASR). In this paper, a series of methodical investigations uncover that the Conformer’s design decisions may not represent the most efficient choices when operating within the constraints of a limited computational budget. After a thorough re-evaluation of the Conformer architecture’s design choices, we propose Sampleformer which reduces the Conformer architecture complexity and has more robust performance. We introduce downsampling to the Conformer Encoder, and to exploit the information in the speech features, we incorporate an additional downsampling module to enhance the efficiency and accuracy of our model. Additionally, we propose a novel and adaptable attention mechanism called multi-group attention, effectively reducing the attention complexity from O(n2d) to O(n2d⋅f/g). We performed experiments on the AISHELL-1 corpora, our 13.3 million-parameter CTC model demonstrates a 3.0%/2.6% relative reduction in character error rate (CER) on the dev/test sets, all without the utilization of a language model (LM). Additionally, the model exhibits a 30% improvement in inference compared to our CTC Conformer baseline and trains 27% faster.
