Related papers: Interrupted and cascaded permutation invariant tra…
Instance-dependent label noise is realistic but rather challenging, where the label-corruption process depends on instances directly. It causes a severe distribution shift between the distributions of training and test data, which impairs…
Acoustic word embedding models map variable duration speech segments to fixed dimensional vectors, enabling efficient speech search and discovery. Previous work explored how embeddings can be obtained in zero-resource settings where no…
In recent literature, few-shot classification has predominantly been defined by the N-way k-shot meta-learning problem. Models designed for this purpose are usually trained to excel on standard benchmarks following a restricted setup,…
Pre-trained vision-language models have notably accelerated progress of open-world concept recognition. Their impressive zero-shot ability has recently been transferred to multi-label image classification via prompt tuning, enabling to…
Recent studies on learning with noisy labels have shown remarkable performance by exploiting a small clean dataset. In particular, model agnostic meta-learning-based label correction methods further improve performance by correcting noisy…
Pre-training models are an important tool in Natural Language Processing (NLP), while the BERT model is a classic pre-training model whose structure has been widely adopted by followers. It was even chosen as the reference model for the…
We present RemixIT, a simple yet effective self-supervised method for training speech enhancement without the need of a single isolated in-domain speech nor a noise waveform. Our approach overcomes limitations of previous methods which make…
We study the problem of building text classifiers with little or no training data, commonly known as zero and few-shot text classification. In recent years, an approach based on neural textual entailment models has been found to give strong…
Self-supervised models for speech representation learning now see widespread use for their versatility and performance on downstream tasks, but the effect of model architecture on the linguistic information learned in their representations…
We approach the problem of improving robustness of deep learning algorithms in the presence of label noise. Building upon existing label correction and co-teaching methods, we propose a novel training procedure to mitigate the memorization…
In real-world applications, machine learning models face online label shift, where label distributions change over time. Effective adaptation requires careful learning rate selection: too low slows adaptation and too high causes…
Serialized Output Training (SOT) has showcased state-of-the-art performance in multi-talker speech recognition by sequentially decoding the speech of individual speakers. To address the challenging label-permutation issue, prior methods…
We consider the problem of training a model under the presence of label noise. Current approaches identify samples with potentially incorrect labels and reduce their influence on the learning process by either assigning lower weights to…
Recent mask proposal models have significantly improved the performance of zero-shot semantic segmentation. However, the use of a `background' embedding during training in these methods is problematic as the resulting model tends to…
Class incremental learning(CIL) has attracted much attention, but most existing related works focus on fine-tuning the entire representation model, which inevitably results in much catastrophic forgetting. In the contrast, with a…
Beyond class frequency, we recognize the impact of class-wise relationships among various class-specific predictions and the imbalance in label masks on long-tailed segmentation learning. To address these challenges, we propose an…
Code-switching (CS), a ubiquitous phenomenon due to the ease of communication it offers in multilingual communities still remains an understudied problem in language processing. The primary reasons behind this are: (1) minimal efforts in…
The proliferation of extensive neural network architectures, particularly deep learning models, presents a challenge in terms of resource-intensive training. GPU memory constraints have become a notable bottleneck in training such sizable…
Automated speaker identification (SID) is a crucial step for the personalization of a wide range of speech-enabled services. Typical SID systems use a symmetric enrollment-verification framework with a single model to derive embeddings both…
In many prediction problems, we have extra information during training (for example, measurements that are expensive or slow to collect) that will not be available when the model is deployed. A common strategy is to first train a model that…