相关论文: Sample Mixed-Based Data Augmentation for Domestic …

Automatic recognition of disordered speech remains a highly challenging task to date due to data scarcity. This paper presents a reinforcement learning (RL) based on-the-fly data augmentation approach for training state-of-the-art PyChain…

Anomalous Sound Detection (ASD) has gained significant interest through the application of various Artificial Intelligence (AI) technologies in industrial settings. Though possessing great potential, ASD systems can hardly be readily…

Distant speech recognition is a challenge, particularly due to the corruption of speech signals by reverberation caused by large distances between the speaker and microphone. In order to cope with a wide range of reverberations in…

Dialect variation hampers automatic recognition of bird calls collected by passive acoustic monitoring. We address the problem on DB3V, a three-region, ten-species corpus of 8-s clips, and propose a deployable framework built on Time-Delay…

Feature learning and deep learning have drawn great attention in recent years as a way of transforming input data into more effective representations using learning algorithms. Such interest has grown in the area of music information…

We introduce a new audio processing technique that increases the sampling rate of signals such as speech or music using deep convolutional neural networks. Our model is trained on pairs of low and high-quality audio examples; at test-time,…

We study the problem of robust data augmentation for regression tasks in the presence of noisy data. Data augmentation is essential for generalizing deep learning models, but most of the techniques like the popular Mixup are primarily…

In this paper, we aim to unveil the impact of data augmentation in audio-language multi-modal learning, which has not been explored despite its importance. We explore various augmentation methods at not only train-time but also test-time…

In this paper, we empirically investigate the effect of audio preprocessing on music tagging with deep neural networks. We perform comprehensive experiments involving audio preprocessing using different time-frequency representations,…

Automated audio captioning (AAC) aims to generate informative descriptions for various sounds from nature and/or human activities. In recent years, AAC has quickly attracted research interest, with state-of-the-art systems now relying on a…

Clients in a distributed or federated environment will often hold data skewed towards differing subsets of labels. This scenario, referred to as heterogeneous or non-iid federated learning, has been shown to significantly hinder model…

Automatic speech recognition (ASR) systems often degrade on accented speech because acoustic-phonetic and prosodic shifts induce a mismatch to training data, making labeled accent adaptation costly. However, common pseudo-label selection…

Although music is typically multi-label, many works have studied hierarchical music tagging with simplified settings such as single-label data. Moreover, there lacks a framework to describe various joint training methods under the…

Health-related acoustic signals, such as cough and breathing sounds, are relevant for medical diagnosis and continuous health monitoring. Most existing machine learning approaches for health acoustics are trained and evaluated on specific…

This paper describes our best system and methodology for ADD 2022: The First Audio Deep Synthesis Detection Challenge\cite{Yi2022ADD}. The very same system was used for both two rounds of evaluation in Track 3.2 with a similar training…

In this paper we investigate the importance of the extent of memory in sequential self attention for sound recognition. We propose to use a memory controlled sequential self attention mechanism on top of a convolutional recurrent neural…

Data augmentation (DA) is indispensable in modern machine learning and deep neural networks. The basic idea of DA is to construct new training data to improve the model's generalization by adding slightly disturbed versions of existing data…

Deep learning has emerged as a powerful alternative to hand-crafted methods for emotion recognition on combined acoustic and text modalities. Baseline systems model emotion information in text and acoustic modes independently using Deep…

Music tag words that describe music audio by text have different levels of abstraction. Taking this issue into account, we propose a music classification approach that aggregates multi-level and multi-scale features using pre-trained…

Audio tagging aims to predict one or several labels in an audio clip. Many previous works use weakly labelled data (WLD) for audio tagging, where only presence or absence of sound events is known, but the order of sound events is unknown.…