K
Kundan Kumar
Researcher at Indian Institute of Technology Kanpur
Publications - 17
Citations - 2230
Kundan Kumar is an academic researcher from Indian Institute of Technology Kanpur. The author has contributed to research in topics: Autoregressive model & Computer science. The author has an hindex of 8, co-authored 14 publications receiving 1726 citations.
Papers
More filters
Proceedings Article
MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis
Kundan Kumar,Rithesh Kumar,Thibault de Boissiere,Lucas Gestin,Wei Zhen Teoh,Jose Sotelo,Alexandre de Brebisson,Yoshua Bengio,Aaron Courville +8 more
TL;DR: The model is non-autoregressive, fully convolutional, with significantly fewer parameters than competing models and generalizes to unseen speakers for mel-spectrogram inversion, and suggests a set of guidelines to design general purpose discriminators and generators for conditional sequence synthesis tasks.
Proceedings Article
Char2Wav: End-to-End Speech Synthesis
Jose Sotelo,Soroush Mehri,Kundan Kumar,João Felipe Santos,Kyle Kastner,Aaron Courville,Yoshua Bengio +6 more
TL;DR: Char2Wav is an end-to-end model for speech synthesis that learns to produce audio directly from text and is a bidirectional recurrent neural network with attention that produces vocoder acoustic features.
Proceedings Article
SampleRNN: An Unconditional End-to-End Neural Audio Generation Model
Soroush Mehri,Kundan Kumar,Ishaan Gulrajani,Rithesh Kumar,Shubham Jain,Jose Sotelo,Aaron Courville,Yoshua Bengio +7 more
TL;DR: It is shown that the model, which profits from combining memory-less modules, namely autoregressive multilayer perceptrons, and stateful recurrent neural networks in a hierarchical structure is able to capture underlying sources of variations in the temporal sequences over very long time spans, on three datasets of different nature.
Posted Content
SampleRNN: An Unconditional End-to-End Neural Audio Generation Model
Soroush Mehri,Kundan Kumar,Ishaan Gulrajani,Rithesh Kumar,Shubham Jain,Jose Sotelo,Aaron Courville,Yoshua Bengio +7 more
TL;DR: In this article, the authors proposed a novel model for unconditional audio generation based on generating one audio sample at a time, which profits from combining memoryless modules, namely autoregressive multilayer perceptrons, and stateful recurrent neural networks in a hierarchical structure.
Posted Content
PixelVAE: A Latent Variable Model for Natural Images
Ishaan Gulrajani,Kundan Kumar,Faruk Ahmed,Adrien Ali Taïga,Francesco Visin,David Vazquez,Aaron Courville +6 more
TL;DR: PixelVAE as mentioned in this paper is a VAE model with an autoregressive decoder based on PixelCNN, which achieves state-of-the-art performance on binarized MNIST, competitive performance on 64x64 ImageNet, and high quality samples on the LSUN bedrooms dataset.