Dynamic Sparsity Neural Networks For Automatic Speech Recognition

Abstract

In automatic speech recognition (ASR), model pruning is a widely adopted technique that reduces model size and latency to deploy neural network models on edge devices with resource constraints. However, multiple models with different sparsity levels usually need to be separately trained and deployed to heterogeneous target hardware with different resource specifications and for applications that have various latency requirements. In this paper, we present Dynamic Sparsity Neural Networks (DSNN) that, once trained, can instantly switch to any predefined sparsity configuration at run-time. We demonstrate the effectiveness and flexibility of DSNN using experiments on internal production datasets with Google Voice Search data, and show that the performance of a DSNN model is on par with that of individually trained single sparsity networks. Our trained DSNN model, therefore, can greatly ease the training process and simplify deployment in diverse scenarios with resource constraints.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keywu2020dynamic

Related papers

• Accurate And Structured Pruning For Efficient Automatic Speech Recognition (2023)7.81
• Dynamic Encoder Size Based On Data-driven Layer-wise Pruning For Speech Recognition (2024)5.24
• Training Dynamic Models Using Early Exits For Automatic Speech Recognition On Resource-constrained Devices (2023)0.00
• Dyn-asr: Compact, Multilingual Speech Recognition Via Spoken Language And Accent Identification (2021)5.24
• SNIPER Training: Single-shot Sparse Training For Text-to-speech (2022)0.00
• Sparse Architectures For Text-independent Speaker Verification Using Deep Neural Networks (2018)0.00
• Dynamic Gated Recurrent Neural Network For Compute-efficient Speech Enhancement (2024)8.35
• Structured Pruning Of Self-supervised Pre-trained Models For Speech Recognition And Understanding (2023)11.39