Human trafficking is a severe problem worldwide and social media platforms have emerged
as a potential tool to detect and prevent this crime. Machine learning (ML) algorithms have …

In this paper, we propose a Unified pre-training Framework for Online and Offline (UFO2)
Automatic Speech Recognition (ASR), which 1) simplifies the two separate training …

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

Recently, there has been an increasing interest in unifying streaming and non-streaming
speech recognition models to reduce development, training and deployment cost. The best …

Automatic Speech Recognition (ASR) models need to be optimized for specific hardware
before they can be deployed on devices. This can be done by tuning the model's …

随着深度学习技术的发展, 自动语音识别任务模型的参数数量越来越庞大, 使得模型的计算开销,
存储需求和功耗花费逐渐增加, 难以在资源受限设备上部署. 因此对基于深度学习的自动语音 …

Streaming automatic speech recognition (ASR) models are restricted from accessing future
context, which results in worse performance compared to the non-streaming models. To …

Human trafficking is a severe problem worldwide and social media platforms have emerged
as a potential tool to detect and prevent this crime. Machine learning (ML) algorithms have …

Conformer-based end-to-end automatic speech recognition (ASR) models have gained
popularity in recent years due to their exceptional performance at scale. However, there are …