Related papers: Weight Averaging: A Simple Yet Effective Method to…
Humans and most animals can learn new tasks without forgetting old ones. However, training artificial neural networks (ANNs) on new tasks typically cause it to forget previously learned tasks. This phenomenon is the result of "catastrophic…
Not so long ago, a method was discovered that successfully overcomes the catastrophic forgetting in neural networks. Although we know about the cases of using this method to preserve skills when adapting pre-trained networks to particular…
Real-life multilingual systems should be able to efficiently incorporate new languages as data distributions fed to the system evolve and shift over time. To do this, systems need to handle the issue of catastrophic forgetting, where the…
End-to-end training of Spoken Language Models (SLMs) commonly involves adapting pre-trained text-based Large Language Models (LLMs) to the speech modality through multi-stage training on diverse tasks such as ASR, TTS and spoken question…
Continual Learning (CL) in Automatic Speech Recognition (ASR) suffers from catastrophic forgetting when adapting to new tasks, domains, or speakers. A common strategy to mitigate this is to store a subset of past data in memory for…
Medical AI systems face catastrophic forgetting when deployed in clinical settings, where models must learn new imaging protocols while retaining prior diagnostic capabilities. This challenge is particularly acute for medical…
Sequential learning of multiple tasks in artificial neural networks using gradient descent leads to catastrophic forgetting, whereby previously learned knowledge is erased during learning of new, disjoint knowledge. Here, we propose a new…
When learning tasks over time, artificial neural networks suffer from a problem known as Catastrophic Forgetting (CF). This happens when the weights of a network are overwritten during the training of a new task causing forgetting of old…
Transformer models have been used in automatic speech recognition (ASR) successfully and yields state-of-the-art results. However, its performance is still affected by speaker mismatch between training and test data. Further finetuning a…
Automatic Speech Recognition (ASR) is widely used within consumer devices such as mobile phones. Recently, personalization or on-device model fine-tuning has shown that adaptation of ASR models towards target user speech improves their…
End-to-end automatic speech recognition (ASR) systems are increasingly popular due to their relative architectural simplicity and competitive performance. However, even though the average accuracy of these systems may be high, the…
The development of resource-constrained approaches to automatic speech recognition (ASR) is of great interest due to its broad applicability to many low-resource languages for which there is scant usable data. Existing approaches to many…
Catastrophic forgetting is a significant challenge in the field of machine learning, particularly in neural networks. When a neural network learns to perform well on a new task, it often forgets its previously acquired knowledge or…
Continual learning on sequential data is critical for many machine learning (ML) deployments. Unfortunately, LSTM networks, which are commonly used to learn on sequential data, suffer from catastrophic forgetting and are limited in their…
End-to-end approaches for automatic speech recognition (ASR) benefit from directly modeling the probability of the word sequence given the input audio stream in a single neural network. However, compared to conventional ASR systems, these…
Human beings are able to master a variety of knowledge and skills with ongoing learning. By contrast, dramatic performance degradation is observed when new tasks are added to an existing neural network model. This phenomenon, termed as…
Training a multi-speaker Text-to-Speech (TTS) model from scratch is computationally expensive and adding new speakers to the dataset requires the model to be re-trained. The naive solution of sequential fine-tuning of a model for new…
Improving the representation of contextual information is key to unlocking the potential of end-to-end (E2E) automatic speech recognition (ASR). In this work, we present a novel and simple approach for training an ASR context mechanism with…
Continual learning refers to the problem where the training data is available in sequential chunks, termed "tasks". The majority of progress in continual learning has been stunted by the problem of catastrophic forgetting, which is caused…
In this paper, we propose a new method to overcome catastrophic forgetting by adding generative regularization to Bayesian inference framework. Bayesian method provides a general framework for continual learning. We could further construct…