Related papers: Polyphonic audio tagging with sequentially labelle…

Recent work on end-to-end automatic speech recognition (ASR) has shown that the connectionist temporal classification (CTC) loss can be used to convert acoustics to phone or character sequences. Such systems are used with a dictionary and…

Connectionist temporal classification (CTC) is commonly adopted for sequence modeling tasks like speech recognition, where it is necessary to preserve order between the input and target sequences. However, CTC is only applied to…

Accurate multi-label classification of electrocardiogram (ECG) signals remains challenging due to the coexistence of multiple cardiac conditions, pronounced class imbalance, and long-range temporal dependencies in multi-lead recordings.…

Automatic tagging of music is an important research topic in Music Information Retrieval and audio analysis algorithms proposed for this task have achieved improvements with advances in deep learning. In particular, many state-of-the-art…

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…

This paper proposes a novel framework for lung sound event detection, segmenting continuous lung sound recordings into discrete events and performing recognition on each event. Exploiting the lightweight nature of Temporal Convolution…

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…

Given a continuous-time signal that can be modeled as the superposition of localized, time-shifted events from multiple sources, the goal of Convolutional Dictionary Learning (CDL) is to identify the location of the events--by Convolutional…

Advanced deep learning architectures, particularly recurrent neural networks (RNNs), have been widely applied in audio, bioacoustic, and biomedical signal analysis, especially in data-scarce environments. While gated RNNs remain effective,…

Extensive works have tackled Language Identification (LID) in the speech domain, however their application to the singing voice trails and performances on Singing Language Identification (SLID) can be improved leveraging recent progresses…

Neural network based architectures used for sound recognition are usually adapted from other application domains such as image recognition, which may not harness the time-frequency representation of a signal. The ConditionaL Neural Networks…

We introduce Label-Combination Prototypical Networks (LC-Protonets) to address the problem of multi-label few-shot classification, where a model must generalize to new classes based on only a few available examples. Extending Prototypical…

Recent studies have shown that neural models can achieve high performance on several sequence labelling/tagging problems without the explicit use of linguistic features such as part-of-speech (POS) tags. These models are trained only using…

Recent advances in generating synthetic captions based on audio and related metadata allow using the information contained in natural language as input for other audio tasks. In this paper, we propose a novel method to guide a sound event…

Multi-label classification (MLC) faces challenges from label noise in training data due to annotating diverse semantic labels for each image. Current methods mainly target identifying and correcting label mistakes using trained MLC models,…

End-to-end speech recognition systems usually require huge amounts of labeling resource, while annotating the speech data is complicated and expensive. Active learning is the solution by selecting the most valuable samples for annotation.…

Unsupervised and self-supervised learning methods have leveraged unlabelled data to improve the pretrained models. However, these methods need significantly large amount of unlabelled data and the computational cost of training models with…

In this study, we propose advancing all-neural speech recognition by directly incorporating attention modeling within the Connectionist Temporal Classification (CTC) framework. In particular, we derive new context vectors using time…

Previous researches on acoustic word embeddings used in query-by-example spoken term detection have shown remarkable performance improvements when using a triplet network. However, the triplet network is trained using only a limited…

Current state-of-the-art systems for sequence labeling are typically based on the family of Recurrent Neural Networks (RNNs). However, the shallow connections between consecutive hidden states of RNNs and insufficient modeling of global…