Related papers: Power Pooling Operators and Confidence Learning fo…
Pseudo-labeling is the most adopted method for pre-training automatic speech recognition (ASR) models. However, its performance suffers from the supervised teacher model's degrading quality in low-resource setups and under domain transfer.…
Semi-supervised object detection (SSOD) has made significant progress with the development of pseudo-label-based end-to-end methods. However, many of these methods face challenges due to class imbalance, which hinders the effectiveness of…
Self-supervised learning (SSL) methods have proven to be very successful in automatic speech recognition (ASR). These great improvements have been reported mostly based on highly curated datasets such as LibriSpeech for non-streaming…
The computing power of mobile devices limits the end-user applications in terms of storage size, processing, memory and energy consumption. These limitations motivate researchers for the design of more efficient deep models. On the other…
Semi-supervised learning aims to boost the accuracy of a model by exploring unlabeled images. The state-of-the-art methods are consistency-based which learn about unlabeled images by encouraging the model to give consistent predictions for…
Polyphonic Sound Event Detection (SED) in real-world recordings is a challenging task because of the dynamic polyphony level, intensity, and duration of sound events. Current polyphonic SED systems fail to model the temporal structure of…
Self-training is a simple yet effective method for semi-supervised learning, during which pseudo-label selection plays an important role for handling confirmation bias. Despite its popularity, applying self-training to landmark detection…
In conventional deep speaker embedding frameworks, the pooling layer aggregates all frame-level features over time and computes their mean and standard deviation statistics as inputs to subsequent segment-level layers. Such statistics…
Recent semi-supervised learning (SSL) methods typically include a filtering strategy to improve the quality of pseudo labels. However, these filtering strategies are usually hand-crafted and do not change as the model is updated, resulting…
Recent advancements in semi-supervised deep learning have introduced effective strategies for leveraging both labeled and unlabeled data to improve classification performance. This work proposes a semi-supervised framework that utilizes a…
Iterative-based methods have become mainstream in stereo matching due to their high performance. However, these methods heavily rely on labeled data and face challenges with unlabeled real-world data. To this end, we propose a…
The recent research in semi-supervised learning (SSL) is mostly dominated by consistency regularization based methods which achieve strong performance. However, they heavily rely on domain-specific data augmentations, which are not easy to…
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…
Semi-supervised learning, i.e. jointly learning from labeled and unlabeled samples, is an active research topic due to its key role on relaxing human supervision. In the context of image classification, recent advances to learn from…
Recently, hybrid systems of clustering and neural diarization models have been successfully applied in multi-party meeting analysis. However, current models always treat overlapped speaker diarization as a multi-label classification…
Most pseudo-label selection strategies in semi-supervised learning rely on fixed confidence thresholds, implicitly assuming that prediction confidence reliably indicates correctness. In practice, deep networks are often overconfident:…
Strong semantic representations improve the convergence and generation quality of diffusion and flow models. Existing approaches largely rely on external models, which require separate training, operate on misaligned objectives, and exhibit…
Recent success of large-scale pre-trained language models crucially hinge on fine-tuning them on large amounts of labeled data for the downstream task, that are typically expensive to acquire. In this work, we study self-training as one of…
The lack of labeled data is a major obstacle in many music information retrieval tasks such as melody extraction, where labeling is extremely laborious or costly. Semi-supervised learning (SSL) provides a solution to alleviate the issue by…
State-of-the-art Deep Learning systems for speaker verification are commonly based on speaker embedding extractors. These architectures are usually composed of a feature extractor front-end together with a pooling layer to encode…