Related papers: INT8 Winograd Acceleration for Conv1D Equipped ASR…

While significant improvements have been made in recent years in terms of end-to-end automatic speech recognition (ASR) performance, such improvements were obtained through the use of very large neural networks, unfit for embedded use on…

Deep neural networks have been proven effective in a wide range of tasks. However, their high computational and memory costs make them impractical to deploy on resource-constrained devices. To address this issue, quantization schemes have…

The RISC-V "V" extension introduces vector processing to the RISC-V architecture. Unlike most SIMD extensions, it supports long vectors which can result in significant improvement of multiple applications. In this paper, we present our…

Low-bit quantization is widely used to compress super-resolution (SR) models and reduce storage and computation costs for deployment on resource-limited devices. However, when SR models are pushed to ultra-low precision (2-4 bits),…

In this paper, we show that a simple self-supervised pre-trained audio model can achieve comparable inference efficiency to more complicated pre-trained models with speech transformer encoders. These speech transformers rely on mixing…

Recent convolutional neural network (CNN) development continues to advance the state-of-the-art model accuracy for various applications. However, the enhanced accuracy comes at the cost of substantial memory bandwidth and storage…

Recent literature has shown that convolutional neural networks (CNNs) with large kernels outperform vision transformers (ViTs) and CNNs with stacked small kernels in many computer vision tasks, such as object detection and image…

Automated speech recognition (ASR) models have gained prominence for applications such as captioning, speech translation, and live transcription. This paper studies Whisper and two model variants: one optimized for live speech streaming and…

End-to-end automatic speech recognition (ASR) models have seen revolutionary quality gains with the recent development of large-scale universal speech models (USM). However, deploying these massive USMs is extremely expensive due to the…

Automatic speech recognition (ASR) is a crucial tool for linguists aiming to perform a variety of language documentation tasks. However, modern ASR systems use data-hungry transformer architectures, rendering them generally unusable for…

Mixed-precision quantization methods have been proposed to reduce model size while minimizing accuracy degradation. However, existing studies require retraining and do not consider the computational overhead and intermediate representations…

In this paper, we analyzed how audio-visual speech enhancement can help to perform the ASR task in a cocktail party scenario. Therefore we considered two simple end-to-end LSTM-based models that perform single-channel audio-visual speech…

Improving the deployment efficiency of transformer-based language models has been challenging given their high computation and memory cost. While INT8 quantization has recently been shown to be effective in reducing both the memory cost and…

The problem how to speed up the convolution computations in Deep Neural Networks is widely investigated in recent years. The Winograd convolution algorithm is a common used method that significantly reduces time consumption. However, it…

Automatic speech recognition (ASR) has reached a level of accuracy in recent years, that even outperforms humans in transcribing speech to text. Nevertheless, all current ASR approaches show a certain weakness against ambient noise. To…

Visual speech recognition (VSR) is the task of recognizing spoken language from video input only, without any audio. VSR has many applications as an assistive technology, especially if it could be deployed in mobile devices and embedded…

This paper proposes a simple yet effective way of regularising the encoder-decoder-based automatic speech recognition (ASR) models that enhance the robustness of the model and improve the generalisation to out-of-domain scenarios. The…

We propose a novel one-pass multiple ASR systems joint compression and quantization approach using an all-in-one neural model. A single compression cycle allows multiple nested systems with varying Encoder depths, widths, and quantization…

Vector quantization(VQ) is a hardware-friendly DNN compression method that can reduce the storage cost and weight-loading datawidth of hardware accelerators. However, conventional VQ techniques lead to significant accuracy loss because the…

Along with the rapid development of real-world applications, higher requirements on the accuracy and efficiency of image super-resolution (SR) are brought forward. Though existing methods have achieved remarkable success, the majority of…