相关论文: Power Pooling Operators and Confidence Learning fo…

Pre-trained multilingual language models (e.g., mBERT, XLM-RoBERTa) have significantly advanced the state-of-the-art for zero-shot cross-lingual information extraction. These language models ubiquitously rely on word segmentation techniques…

We propose the application of a semi-supervised learning method to improve the performance of acoustic modelling for automatic speech recognition based on deep neural net- works. As opposed to unsupervised initialisation followed by…

Recent progress in singing voice separation has primarily focused on supervised deep learning methods. However, the scarcity of ground-truth data with clean musical sources has been a problem for long. Given a limited set of labeled data,…

Due to abundance of data from multiple modalities, cross-modal retrieval tasks with image-text, audio-image, etc. are gaining increasing importance. Of the different approaches proposed, supervised methods usually give significant…

In recent years, Event Sound Source Localization has been widely applied in various fields. Recent works typically relying on the contrastive learning framework show impressive performance. However, all work is based on large relatively…

Speaker representation learning is crucial for voice recognition systems, with recent advances in self-supervised approaches reducing dependency on labeled data. Current two-stage iterative frameworks, while effective, suffer from…

In many wireless application scenarios, acquiring labeled data can be prohibitively costly, requiring complex optimization processes or measurement campaigns. Semi-supervised learning leverages unlabeled samples to augment the available…

Sound event detection (SED) aims at identifying audio events (audio tagging task) in recordings and then locating them temporally (localization task). This last task ends with the segmentation of the frame-level class predictions, that…

Deep subspace clustering has attracted increasing attention in recent years. Almost all the existing works are required to load the whole training data into one batch for learning the self-expressive coefficients in the framework of deep…

For sequence transduction tasks like speech recognition, a strong structured prior model encodes rich information about the target space, implicitly ruling out invalid sequences by assigning them low probability. In this work, we propose…

Most state-of-the-art Deep Learning systems for speaker verification are based on speaker embedding extractors. These architectures are commonly composed of a feature extractor front-end together with a pooling layer to encode…

This paper considers a semi-supervised learning framework for weakly labeled polyphonic sound event detection problems for the DCASE 2019 challenge's task4 by combining both the tri-training and adversarial learning. The goal of the task4…

Sound event detection (SED) is the task of identifying sound events along with their onset and offset times. A recent, convolutional neural networks based SED method, proposed the usage of depthwise separable (DWS) and time-dilated…

Recent semi-supervised object detection (SSOD) has achieved remarkable progress by leveraging unlabeled data for training. Mainstream SSOD methods rely on Consistency Regularization methods and Exponential Moving Average (EMA), which form a…

In pseudo-labeling (PL), which is a type of semi-supervised learning, pseudo-labels are assigned based on the confidence scores provided by the classifier; therefore, accurate confidence is important for successful PL. In this study, we…

Acoustic word embeddings are typically created by training a pooling function using pairs of word-like units. For unsupervised systems, these are mined using k-nearest neighbor (KNN) search, which is slow. Recently, mean-pooled…

Self-training is a classical approach in semi-supervised learning which is successfully applied to a variety of machine learning problems. Self-training algorithm generates pseudo-labels for the unlabeled examples and progressively refines…

Speaker embeddings carry valuable emotion-related information, which makes them a promising resource for enhancing speech emotion recognition (SER), especially with limited labeled data. Traditionally, it has been assumed that emotion…

Semi-supervised object detection (SSOD) aims to boost detection performance by leveraging extra unlabeled data. The teacher-student framework has been shown to be promising for SSOD, in which a teacher network generates pseudo-labels for…

Federated learning enables multiple clients, such as mobile phones and organizations, to collaboratively learn a shared model for prediction while protecting local data privacy. However, most recent research and applications of federated…