Search Results - "Parekh, Jayneel"

Speech-To-Singing Conversion in an Encoder-Decoder Framework by Parekh, Jayneel, Rao, Preeti, Yang, Yi-Hsuan

“…In this paper our goal is to convert a set of spoken lines into sung ones. Unlike previous signal processing based methods, we take a learning based approach…”
Get full text

Tackling Interpretability in Audio Classification Networks With Non-negative Matrix Factorization by Parekh, Jayneel, Parekh, Sanjeel, Mozharovskyi, Pavlo, Richard, Gael, d'Alche-Buc, Florence

“…This article tackles two major problem settings for interpretability of audio processing networks, post-hoc and by-design interpretation. For post-hoc…”
Get full text

One Wave to Explain Them All: A Unifying Perspective on Post-hoc Explainability by Kasmi, Gabriel, Brunetto, Amandine, Fel, Thomas, Parekh, Jayneel

“…Despite the growing use of deep neural networks in safety-critical decision-making, their inherent black-box nature hinders transparency and interpretability…”
Get full text

A Concept-Based Explainability Framework for Large Multimodal Models by Parekh, Jayneel, Khayatan, Pegah, Shukor, Mustafa, Newson, Alasdair, Cord, Matthieu

“…Large multimodal models (LMMs) combine unimodal encoders and large language models (LLMs) to perform multimodal tasks. Despite recent advancements towards the…”
Get full text

Restyling Unsupervised Concept Based Interpretable Networks with Generative Models by Parekh, Jayneel, Bouniot, Quentin, Mozharovskyi, Pavlo, Newson, Alasdair, d'Alché-Buc, Florence

“…Developing inherently interpretable models for prediction has gained prominence in recent years. A subclass of these models, wherein the interpretable network…”
Get full text

A Framework to Learn with Interpretation by Parekh, Jayneel, Mozharovskyi, Pavlo, d'Alché-Buc, Florence

“…To tackle interpretability in deep learning, we present a novel framework to jointly learn a predictive model and its associated interpretation model. The…”
Get full text

Speech-to-Singing Conversion in an Encoder-Decoder Framework by Parekh, Jayneel, Rao, Preeti, Yang, Yi-Hsuan

“…In this paper our goal is to convert a set of spoken lines into sung ones. Unlike previous signal processing based methods, we take a learning based approach…”
Get full text

Tackling Interpretability in Audio Classification Networks with Non-negative Matrix Factorization by Parekh, Jayneel, Parekh, Sanjeel, Mozharovskyi, Pavlo, Richard, Gaël, d'Alché-Buc, Florence

“…This paper tackles two major problem settings for interpretability of audio processing networks, post-hoc and by-design interpretation. For post-hoc…”
Get full text

Listen to Interpret: Post-hoc Interpretability for Audio Networks with NMF by Parekh, Jayneel, Parekh, Sanjeel, Mozharovskyi, Pavlo, d'Alché-Buc, Florence, Richard, Gaël

“…This paper tackles post-hoc interpretability for audio processing networks. Our goal is to interpret decisions of a network in terms of high-level audio…”
Get full text

Flexible and Context-Specific AI Explainability: A Multidisciplinary Approach by Beaudouin, Valérie, Bloch, Isabelle, Bounie, David, Clémençon, Stéphan, d'Alché-Buc, Florence, Eagan, James, Maxwell, Winston, Mozharovskyi, Pavlo, Parekh, Jayneel

“…The recent enthusiasm for artificial intelligence (AI) is due principally to advances in deep learning. Deep learning methods are remarkably accurate, but also…”
Get full text