Related papers: A Sequential Self Teaching Approach for Improving …

In a noisy environment, a lossy speech signal can be automatically restored by a listener if he/she knows the language well. That is, with the built-in knowledge of a "language model", a listener may effectively suppress noise interference…

This paper proposes to use low-level spatial features extracted from multichannel audio for sound event detection. We extend the convolutional recurrent neural network to handle more than one type of these multichannel features by learning…

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…

Continuously learning new classes without catastrophic forgetting is a challenging problem for on-device environmental sound classification given the restrictions on computation resources (e.g., model size, running memory). To address this…

Label noise is emerging as a pressing issue in sound event classification. This arises as we move towards larger datasets that are difficult to annotate manually, but it is even more severe if datasets are collected automatically from…

Sound event detection is a challenging task, especially for scenes with multiple simultaneous events. While event classification methods tend to be fairly accurate, event localization presents additional challenges, especially when large…

Sound Event Detection (SED) aims to predict the temporal boundaries of all the events of interest and their class labels, given an unconstrained audio sample. Taking either the splitand-classify (i.e., frame-level) strategy or the more…

We propose a simple but efficient method termed Guided Learning for weakly-labeled semi-supervised sound event detection (SED). There are two sub-targets implied in weakly-labeled SED: audio tagging and boundary detection. Instead of…

In conventional sound event detection (SED) models, two types of events, namely, those that are present and those that do not occur in an acoustic scene, are regarded as the same type of events. The conventional SED methods cannot…

In this paper we propose a novel learning framework called Supervised and Weakly Supervised Learning where the goal is to learn simultaneously from weakly and strongly labeled data. Strongly labeled data can be simply understood as fully…

Real-world sound scenes consist of time-varying collections of sound sources, each generating characteristic sound events that are mixed together in audio recordings. The association of these constituent sound events with their mixture and…

This paper proposes an active learning system for sound event detection (SED). It aims at maximizing the accuracy of a learned SED model with limited annotation effort. The proposed system analyzes an initially unlabeled audio dataset, from…

Humans do not acquire perceptual abilities in the way we train machines. While machine learning algorithms typically operate on large collections of randomly-chosen, explicitly-labeled examples, human acquisition relies more heavily on…

Existing audio analysis methods generally first transform the audio stream to spectrogram, and then feed it into CNN for further analysis. A standard CNN recognizes specific visual patterns over feature map, then pools for high-level…

Combining multiple machine learning models into an ensemble is known to provide superior performance levels compared to the individual components forming the ensemble. This is because models can complement each other in taking better…

Deep learning techniques for separating audio into different sound sources face several challenges. Standard architectures require training separate models for different types of audio sources. Although some universal separators employ a…

Acoustic scene classification (ASC) predominantly relies on supervised approaches. However, acquiring labeled data for training ASC models is often costly and time-consuming. Recently, self-supervised learning (SSL) has emerged as a…

Automatic detection and classification of animal sounds has many applications in biodiversity monitoring and animal behaviour. In the past twenty years, the volume of digitised wildlife sound available has massively increased, and automatic…

Sequential sensor data is generated in a wide variety of practical applications. A fundamental challenge involves learning effective classifiers for such sequential data. While deep learning has led to impressive performance gains in recent…

Labeled data is a critical resource for training and evaluating machine learning models. However, many real-life datasets are only partially labeled. We propose a semi-supervised machine learning training strategy to improve event detection…