This paper introduces FunASR, an open-source speech recognition toolkit designed to
bridge the gap between academic research and industrial applications. FunASR offers …

Conditional computation algorithms, such as the early exiting (EE) algorithm, can be applied
to accelerate the inference of pretrained language models (PLMs) while maintaining …

The computational cost of the vision and language pretrained models (VL-PTMs) limits their
deployment in resource-constrained devices that require low latency. One existing solution …

From wearables to powerful smart devices, modern automatic speech recognition (ASR)
models run on a variety of edge devices with different computational budgets. To navigate …

Recently, end-to-end ASR models based on connectionist temporal classification (CTC)
have achieved impressive results, but their performance is limited in lightweight models …

Memory constraint of always-on devices is one of the major concerns when deploying
speech processing models on these devices. While larger models trained with sufficiently …

Even though deep speaker models have demonstrated impressive accuracy in speaker
verification tasks, this often comes at the expense of increased model size and computation …

Neural network pruning offers an effective method for compressing a multilingual automatic
speech recognition (ASR) model with minimal performance loss. However, it entails several …

Conditional computation algorithms, eg, the early exiting (EE) strategy, can accelerate the
inference of pretrained language models (PLMs) by exiting shallow layers without …

Abstract Knowledge distillation (KD) is a popular model compression method to improve the
performance of lightweight models by transferring knowledge from a teacher model to a …