Related papers: Efficient Large-scale Audio Tagging via Transforme…
In computer vision, convolutional neural networks (CNN) such as ConvNeXt, have been able to surpass state-of-the-art transformers, partly thanks to depthwise separable convolutions (DSC). DSC, as an approximation of the regular convolution,…
Significant improvement has been achieved in automated audio captioning (AAC) with recent models. However, these models have become increasingly large as their performance is enhanced. In this work, we propose a knowledge distillation (KD)…
Music auto-tagging is often handled in a similar manner to image classification by regarding the 2D audio spectrogram as image data. However, music auto-tagging is distinguished from image classification in that the tags are highly diverse…
The deep complex convolution recurrent network (DCCRN) achieves excellent speech enhancement performance by utilizing the audio spectrum's complex features. However, it has a large number of model parameters. We propose a smaller model,…
Many Internet-of-Things (IoT) applications demand fast and accurate understanding of a few key events in their surrounding environment. Deep Convolutional Neural Networks (CNNs) have emerged as an effective approach to understand speech,…
In the past decade, convolutional neural networks (CNNs) have been widely adopted as the main building block for end-to-end audio classification models, which aim to learn a direct mapping from audio spectrograms to corresponding labels. To…
Non-autoregressive machine translation (NAT) systems predict a sequence of output tokens in parallel, achieving substantial improvements in generation speed compared to autoregressive models. Existing NAT models usually rely on the…
Deep learning has significantly advanced state-of-the-art of speech recognition in the past few years. However, compared to conventional Gaussian mixture acoustic models, neural network models are usually much larger, and are therefore not…
In this work we propose approaches to effectively transfer knowledge from weakly labeled web audio data. We first describe a convolutional neural network (CNN) based framework for sound event detection and classification using weakly…
Deep Neural Networks (DNNs) have achieved notable performance in the fields of computer vision and natural language processing with various applications in both academia and industry. However, with recent advancements in DNNs and…
In this paper, we study the performance of variants of well-known Convolutional Neural Network (CNN) architectures on different audio tasks. We show that tuning the Receptive Field (RF) of CNNs is crucial to their generalization. An…
The smaller memory bandwidth in smart devices prompts development of smaller Automatic Speech Recognition (ASR) models. To obtain a smaller model, one can employ the model compression techniques. Knowledge distillation (KD) is a popular…
Convolutional neural networks (CNNs), such as the time-delay neural network (TDNN), have shown their remarkable capability in learning speaker embedding. However, they meanwhile bring a huge computational cost in storage size, processing,…
In recent years, Sound AI is being increasingly used to predict machine failures. By attaching a microphone to the machine of interest, one can get real time data on machine behavior from the field. Traditionally, Convolutional Neural Net…
Conventional Convolutional Neural Networks (CNNs) in the real domain have been widely used for audio classification. However, their convolution operations process multi-channel inputs independently, limiting the ability to capture…
This paper discusses four facets of the Knowledge Distillation (KD) process for Convolutional Neural Networks (CNNs) and Vision Transformer (ViT) architectures, particularly when executed on edge devices with constrained processing…
Audio pattern recognition is an important research topic in the machine learning area, and includes several tasks such as audio tagging, acoustic scene classification, music classification, speech emotion classification and sound event…
Generative Adversarial Networks (GANs) have achieved excellent audio synthesis quality in the last years. However, making them operable with semantically meaningful controls remains an open challenge. An obvious approach is to control the…
Environmental audio tagging is a newly proposed task to predict the presence or absence of a specific audio event in a chunk. Deep neural network (DNN) based methods have been successfully adopted for predicting the audio tags in the…
In the past few years, transformers have achieved promising performances on various computer vision tasks. Unfortunately, the immense inference overhead of most existing vision transformers withholds their from being deployed on edge…