VFNet: A Convolutional Architecture for Accent Classification

no code implementations • 15 Oct 2019 • Asad Ahmed, Pratham Tangri, Anirban Panda, Dhruv Ramani, Samarjit Karmakar

Understanding accent is an issue which can derail any human-machine interaction.

Classification General Classification

Avoiding Negative Side-Effects and Promoting Safe Exploration with Imaginative Planning

no code implementations • 25 Sep 2019 • Dhruv Ramani, Benjamin Eysenbach

Our imaginative module can be seen as a ``plug-and-play'' approach to ensuring safety, as it is compatible with any existing RL algorithm and any task with discrete action space.

Reinforcement Learning (RL) Safe Exploration

A Short Survey On Memory Based Reinforcement Learning

no code implementations • 14 Apr 2019 • Dhruv Ramani

Reinforcement learning (RL) is a branch of machine learning which is employed to solve various sequential decision making problems without proper supervision.

Decision Making reinforcement-learning +1

Autoencoder Based Architecture For Fast & Real Time Audio Style Transfer

no code implementations • 18 Dec 2018 • Dhruv Ramani, Samarjit Karmakar, Anirban Panda, Asad Ahmed, Pratham Tangri

Recently, there has been great interest in the field of audio style transfer, where a stylized audio is generated by imposing the style of a reference audio on the content of a target audio.

Style Transfer