12 accepted papers
Dialect identification (DID) addresses the challenge of recog-nizing regional variations within a language. The current deep learning approaches focus on audio-only, text-only, or multi-task setups combining automatic speech recognition (ASR) with DID. This work introduces a novel multimodal archite…
Loss of plasticity is a phenomenon where neural networks can become more difficult to train over the course of learning. Continual learning algorithms seek to mitigate this effect by sustaining good performance while maintaining network trainability. We develop a new technique for improving continua…
We introduce **RESPIN-S1.0**, the largest publicly available dialect-rich read-speech corpus for Indian languages, comprising more than 10,000 hours of validated audio across nine major languages: Bengali, Bhojpuri, Chhattisgarhi, Hindi, Kannada, Magahi, Maithili, Marathi, and Telugu. Indian languag…
Multi-exposure fusion combines bracketed exposure captures into a single image with enhanced details from a large dynamic range. It is an effective and resource-efficient way to obtain a high dynamic range image, which has broad applications. Despite significant advancements in the field, existing m…
Sentiment analysis, a fundamental aspect of Natural Language Processing (NLP), involves the classification of emotions, opinions, and attitudes in text data. In the context of India, with its vast linguistic diversity and low-resource languages, the challenge is to support sentiment analysis in nume…
The increasing number of Indian language users on the internet necessitates the development of Indian language technologies. In response to this demand, our paper presents a generalized representation vector for diverse text characteristics, including native scripts, transliterated text, multilingua…
Approaches to policy optimization have been motivated from diverse principles, based on how the parametric model is interpreted (e.g. value versus policy representation) or how the learning objective is formulated, yet they share a common goal of maximizing expected return. To better capture the com…
Actor-critic (AC) methods are ubiquitous in reinforcement learning. Although it is understood that AC methods are closely related to policy gradient (PG), their precise connection has not been fully characterized previously. In this paper, we explain the gap between AC and PG methods by identifying…
While deep learning and deep reinforcement learning (RL) systems have demonstrated impressive results in domains such as image classification, game playing, and robotic control, data efficiency remains a major challenge. Multi-task learning has emerged as a promising approach for sharing structure a…
While reinforcement learning algorithms can learn effective policies for complex tasks, these policies are often brittle to even minor task variations, especially when variations are not explicitly provided during training. One natural approach to this problem is to train agents with manually specif…
Many reinforcement learning (RL) tasks provide the agent with high-dimensional observations that can be simplified into low-dimensional continuous states. To formalize this process, we introduce the concept of a \texit{DeepMDP}, a parameterized latent space model that is trained via the minimization…
We present a unifying framework for designing and analysing distributional reinforcement learning (DRL) algorithms in terms of recursively estimating statistics of the return distribution. Our key insight is that DRL algorithms can be decomposed as the combination of some statistical estimator and a…