Related papers: Self-Train Before You Transcribe
Speech distortions are a long-standing problem that degrades the performance of supervisely trained speech processing models. It is high time that we enhance the robustness of speech processing models to obtain good performance when…
To discover intrinsic inter-class transition probabilities underlying data, learning with noise transition has become an important approach for robust deep learning on corrupted labels. Prior methods attempt to achieve such transition…
Deep learning models trained on large-scale data have achieved encouraging performance in many real-world tasks. Meanwhile, publishing those models trained on sensitive datasets, such as medical records, could pose serious privacy concerns.…
The performance of machine learning algorithms is known to be negatively affected by possible mismatches between training (source) and test (target) data distributions. In fact, this problem emerges whenever an acoustic scene classification…
In large-scale domain classification, an utterance can be handled by multiple domains with overlapped capabilities. However, only a limited number of ground-truth domains are provided for each training utterance in practice while knowing as…
In this work we address multi-target domain adaptation (MTDA) in semantic segmentation, which consists in adapting a single model from an annotated source dataset to multiple unannotated target datasets that differ in their underlying data…
Feature-based student-teacher learning, a training method that encourages the student's hidden features to mimic those of the teacher network, is empirically successful in transferring the knowledge from a pre-trained teacher network to the…
Automatic speech recognition models are often adapted to improve their accuracy in a new domain. A potential drawback of model adaptation to new domains is catastrophic forgetting, where the Word Error Rate on the original domain is…
Current self-training methods such as standard self-training, co-training, tri-training, and others often focus on improving model performance on a single task, utilizing differences in input features, model architectures, and training…
Transfer learning is a crucial concept within deep learning that allows artificial neural networks to benefit from a large pre-training data basis when confronted with a task of limited data. Despite its ubiquitous use and clear benefits,…
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…
Compared to supervised deep learning, self-supervision provides remote sensing a tool to reduce the amount of exact, human-crafted geospatial annotations. While image-level information for unsupervised pretraining efficiently works for…
Neural machine translation models have shown to achieve high quality when trained and fed with well structured and punctuated input texts. Unfortunately, the latter condition is not met in spoken language translation, where the input is…
Deep convolutional neural networks have considerably improved state-of-the-art results for semantic segmentation. Nevertheless, even modern architectures lack the ability to generalize well to a test dataset that originates from a different…
Noisy Labels are commonly present in data sets automatically collected from the internet, mislabeled by non-specialist annotators, or even specialists in a challenging task, such as in the medical field. Although deep learning models have…
The transcription quality of automatic speech recognition (ASR) systems degrades significantly when transcribing audios coming from unseen domains. We propose an unsupervised error correction method for unsupervised ASR domain adaption,…
Recent deep learning-based methods for medical image registration achieve results that are competitive with conventional optimization algorithms at reduced run times. However, deep neural networks generally require plenty of labeled…
Numerous new dialog domains are being created every day while collecting data for these domains is extremely costly since it involves human interactions. Therefore, it is essential to develop algorithms that can adapt to different domains…
Learning to adapt pretrained language models to unlabeled, out-of-distribution data is a critical challenge, as models often falter on structurally novel reasoning tasks even while excelling within their training distribution. We introduce…
Target-speaker speech recognition aims to recognize target-speaker speech from noisy environments with background noise and interfering speakers. This work presents a joint framework that combines time-domain target-speaker speech…