Recent advances in state-of-the-art DNN architecture design have been moving toward
Transformer models. These models achieve superior accuracy across a wide range of …

Reducing the latency and model size has always been a significant research problem for
live Automatic Speech Recognition (ASR) application scenarios. Along this direction, model …

Large speech models are rapidly gaining traction in research community. As a result, model
compression has become an important topic, so that these models can fit in memory and be …

For on-device automatic speech recognition (ASR), quantization aware training (QAT) is
ubiquitous to achieve the trade-off between model predictive performance and efficiency …

With the rapid increase in the size of neural networks, model compression has become an
important area of research. Quantization is an effective technique at decreasing the model …

With the growing need for large models in speech recognition, quantization has become a
valuable technique to reduce their compute and memory transfer costs. Quantized models …

Recent advancement in Automatic Speech Recognition (ASR) has produced large AI
models, which become impractical for deployment in mobile devices. Model quantization is …

State-of-the-art end-to-end automatic speech recognition (ASR) systems are becoming
increasingly complex and expensive for practical applications. This paper develops a high …

In the field of deep learning, researchers often focus on inventing novel neural network
models and improving benchmarks. In contrast, application developers are interested in …

Automatic speech recognition (ASR) is a fundamental technology in the field of artificial
intelligence. End-to-end (E2E) ASR is favored for its state-of-the-art performance. However …