Related papers: CNN-based Discriminative Training for Domain Compe…
Recent advances in domain adaptation reveal that adversarial learning on deep neural networks can learn domain invariant features to reduce the shift between source and target domains. While such adversarial approaches achieve domain-level…
This paper proposes a benchmark of submissions to Detection and Classification Acoustic Scene and Events 2021 Challenge (DCASE) Task 4 representing a sampling of the state-of-the-art in Sound Event Detection task. The submissions are…
Unsupervised Domain adaptation (UDA) attempts to recognize the unlabeled target samples by building a learning model from a differently-distributed labeled source domain. Conventional UDA concentrates on extracting domain-invariant features…
Machine hearing or listening represents an emerging area. Conventional approaches rely on the design of handcrafted features specialized to a specific audio task and that can hardly generalized to other audio fields. For example,…
With the increased deployment of face recognition systems in our daily lives, face presentation attack detection (PAD) is attracting much attention and playing a key role in securing face recognition systems. Despite the great performance…
The performance of sound event detection methods can significantly degrade when they are used in unseen conditions (e.g. recording devices, ambient noise). Domain adaptation is a promising way to tackle this problem. In this paper, we…
Adapting speaker recognition systems to new environments is a widely-used technique to improve a well-performing model learned from large-scale data towards a task-specific small-scale data scenarios. However, previous studies focus on…
Despite the recent success of stereo matching with convolutional neural networks (CNNs), it remains arduous to generalize a pre-trained deep stereo model to a novel domain. A major difficulty is to collect accurate ground-truth disparities…
Convolutional neural networks (CNNs) have demonstrated gratifying results at learning discriminative features. However, when applied to unseen domains, state-of-the-art models are usually prone to errors due to domain shift. After…
This paper demonstrates the potential of convolutional neural networks (CNN) for detecting and classifying prosodic events on words, specifically pitch accents and phrase boundary tones, from frame-based acoustic features. Typical…
The performance of speech emotion recognition is affected by the differences in data distributions between train (source domain) and test (target domain) sets used to build and evaluate the models. This is a common problem, as multiple…
Recently, more and more personalized speech enhancement systems (PSE) with excellent performance have been proposed. However, two critical issues still limit the performance and generalization ability of the model: 1) Acoustic environment…
Time series anomaly detection is a challenging task with a wide range of real-world applications. Due to label sparsity, training a deep anomaly detector often relies on unsupervised approaches. Recent efforts have been devoted to time…
In this paper, we propose a stacked convolutional and recurrent neural network (CRNN) with a 3D convolutional neural network (CNN) in the first layer for the multichannel sound event detection (SED) task. The 3D CNN enables the network to…
We describe in this report our audio scene recognition system submitted to the DCASE 2016 challenge. Firstly, given the label set of the scenes, a label tree is automatically constructed. This category taxonomy is then used in the feature…
Acoustic scene classification (ASC) is a crucial research problem in computational auditory scene analysis, and it aims to recognize the unique acoustic characteristics of an environment. One of the challenges of the ASC task is the domain…
In this study, we proposed a novel semi-supervised training method that uses unlabeled data with a class distribution that is completely different from the target data or data without a target label. To this end, we introduce a contrastive…
Recently the problem of cross-domain object detection has started drawing attention in the computer vision community. In this paper, we propose a novel unsupervised cross-domain detection model that exploits the annotated data in a source…
We present a method to develop low-complexity convolutional neural networks (CNNs) for acoustic scene classification (ASC). The large size and high computational complexity of typical CNNs is a bottleneck for their deployment on…
Acoustic scene classification (ASC) aims to classify an audio clip based on the characteristic of the recording environment. In this regard, deep learning based approaches have emerged as a useful tool for ASC problems. Conventional…