Structured Pruning of Self-Supervised Pre-trained Models for Speech Recognition and Understanding

Autor:	Peng, Yifan, Kim, Kwangyoun, Wu, Felix, Sridhar, Prashant, Watanabe, Shinji
Rok vydání:	2023
Předmět:	Computer Science - Computation and Language Computer Science - Sound Electrical Engineering and Systems Science - Audio and Speech Processing
Druh dokumentu:	Working Paper
Popis:	Self-supervised speech representation learning (SSL) has shown to be effective in various downstream tasks, but SSL models are usually large and slow. Model compression techniques such as pruning aim to reduce the model size and computation without degradation in accuracy. Prior studies focus on the pruning of Transformers; however, speech models not only utilize a stack of Transformer blocks, but also combine a frontend network based on multiple convolutional layers for low-level feature representation learning. This frontend has a small size but a heavy computational cost. In this work, we propose three task-specific structured pruning methods to deal with such heterogeneous networks. Experiments on LibriSpeech and SLURP show that the proposed method is more accurate than the original wav2vec2-base with 10% to 30% less computation, and is able to reduce the computation by 40% to 50% without any degradation. Comment: Accepted at ICASSP 2023
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2302.14132 Zobrazit plný text záznamu View this record from Arxiv