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.

通过本文研究发现，使用简单的自监督预训练音频模型能够实现与复杂的预训练模型相媲美的推理效率，同时采用自注意力模块与卷积模块相结合的语音转换器能够在ASR上取得最先进的性能表现，同时使用较低位权重量化技术的神经网络的简单方法，能够提高效率并防止在量化模块之间传播误差。

注意力还是卷积：用于推理效率的音频语言模型中的Transformer编码器