Related papers: Temporal Bilinear Encoding Network of Audio-Visual…

We introduce a method to learn unsupervised semantic visual information based on the premise that complex events can be decomposed into simpler events and that these simple events are shared across several complex events. We first employ a…

Binarization is an attractive strategy for implementing lightweight Deep Convolutional Neural Networks (CNNs). Despite the unquestionable savings offered, memory footprint above all, it may induce an excessive accuracy loss that prevents a…

Previous methods for audio-image matching generally fall into one of two categories: pipeline models or End-to-End models. Pipeline models first transcribe speech and then encode the resulting text; End-to-End models encode speech directly.…

Onsets are a key factor to split audio into several notes. In this paper, we ensemble multiple temporal convolution network (TCN) based model and utilize a restricted frequency range spectrogram to achieve more robust onset detection.…

This paper addresses the problem of global tempo estimation in musical audio. Given that annotating tempo is time-consuming and requires certain musical expertise, few publicly available data sources exist to train machine learning models…

In this paper, we propose a framework for environmental sound classification in a low-data context (less than 100 labeled examples per class). We show that using pre-trained image classification models along with the usage of data…

In this paper, we study the problem of learning image classification models with label noise. Existing approaches depending on human supervision are generally not scalable as manually identifying correct or incorrect labels is…

We introduce in this work an efficient approach for audio scene classification using deep recurrent neural networks. An audio scene is firstly transformed into a sequence of high-level label tree embedding feature vectors. The vector…

Time-frequency images (TFIs) provide a joint time-frequency representation of a signal and have become an effective tool for analyzing, characterizing, and processing non-stationary signals. Deep learning (DL) techniques have become…

Audio-language models (ALMs) are increasingly used for audio captioning, question answering, and open-ended audio understanding, but their inference cost remains high when audio inputs are represented as long prefix-token sequences. These…

This work addresses the problem of accurate semantic labelling of short videos. To this end, a multitude of different deep nets, ranging from traditional recurrent neural networks (LSTM, GRU), temporal agnostic networks (FV,VLAD,BoW), fully…

Sound event detection systems typically consist of two stages: extracting hand-crafted features from the raw audio waveform, and learning a mapping between these features and the target sound events using a classifier. Recently, the focus…

Integrate-and-fire time encoding machines (IF-TEMs) provide an efficient framework for asynchronous sampling of bandlimited signals through discrete firing times. However, conventional IF-TEMs often exhibit excessive oversampling, leading…

The usage of deep generative models for image compression has led to impressive performance gains over classical codecs while neural video compression is still in its infancy. Here, we propose an end-to-end, deep generative modeling…

Temporal action localization is an important task of computer vision. Though a variety of methods have been proposed, it still remains an open question how to predict the temporal boundaries of action segments precisely. Most works use…

This paper aims to improve the widely used deep speaker embedding x-vector model. We propose the following improvements: (1) a hybrid neural network structure using both time delay neural network (TDNN) and long short-term memory neural…

While capable of segregating visual data, humans take time to examine a single piece, let alone thousands or millions of samples. The deep learning models efficiently process sizeable information with the help of modern-day computing.…

We study the use of a time series encoder to learn representations that are useful on data set types with which it has not been trained on. The encoder is formed of a convolutional neural network whose temporal output is summarized by a…

When used with deep learning, the symbolic music modality is often coupled with language model architectures. To do so, the music needs to be tokenized, i.e. converted into a sequence of discrete tokens. This can be achieved by different…

In this paper, we present an end-to-end approach for environmental sound classification based on a 1D Convolution Neural Network (CNN) that learns a representation directly from the audio signal. Several convolutional layers are used to…