2023/11/05 by Sungho Jeon, Jeon, Sungho, Ching-Feng Yeh +11
Computer Science · #Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Electrical engineering #Music and Audio Processing #Sound (cs.SD) #Speech Recognition and Synthesis #Speech and Audio Processing #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2311.02772
openalex publication_date 2023/11/05 · openalex created_date 2023/11/08 · openalex updated_date 2026/07/28
In this paper, we show that a simple self-supervised pre-trained audio model can achieve comparable inference efficiency to more complicated pre-trained models with speech transformer encoders. These speech transformers rely on mixing convolutional modules with self-attention modules. They achieve state-of-the-art performance on ASR with top efficiency. We first show that employing these speech transformers as an encoder significantly improves the efficiency of pre-trained audio models as well. However, our study shows that we can achieve comparable efficiency with advanced self-attention solely. We demonstrate that this simpler approach is particularly beneficial with a low-bit weight quantization technique of a neural network to improve efficiency. We hypothesize that it prevents propagating the errors between different quantized modules compared to recent speech transformers mixing quantized convolution and the quantized self-attention modules.