no code implementations • 3 Mar 2024 • Ravi Shankar, Ke Tan, Buye Xu, Anurag Kumar
Self-supervised learned models have been found to be very effective for certain speech tasks such as automatic speech recognition, speaker identification, keyword spotting and others.
no code implementations • 9 Nov 2022 • Ravi Shankar, Abdouh Harouna Kenfack, Arjun Somayazulu, Archana Venkataraman
In parallel to these models, researchers have proposed several data augmentation techniques to increase the size and variability of existing labeled datasets.
no code implementations • 9 Nov 2022 • Ravi Shankar, Hsi-Wei Hsieh, Nicolas Charon, Archana Venkataraman
We term this new architecture a variational CycleGAN (VCGAN).
no code implementations • LREC 2022 • Ankush Agarwal, Raj Gite, Shreya Laddha, Pushpak Bhattacharyya, Satyanarayan Kar, Asif Ekbal, Prabhjit Thind, Rajesh Zele, Ravi Shankar
We construct a Knowledge Graph from Aircraft Accident reports and contribute this resource to the community of researchers.
no code implementations • 29 Sep 2021 • Ravi Shankar, Archana Venkataraman
We propose the first method to adaptively modify the duration of a given speechsignal.
no code implementations • 11 Jul 2021 • Ravi Shankar, Archana Venkataraman
During inference, we generate the attention map as a proxy for the similarity matrix between the given input speech and an unknown target speech signal.
no code implementations • 25 Jul 2020 • Ravi Shankar, Hsi-Wei Hsieh, Nicolas Charon, Archana Venkataraman
Finally, the predictor uses the original spectrum and the modified F0 contour to generate a corresponding target spectrum.
no code implementations • 25 Jul 2020 • Ravi Shankar, Jacob Sager, Archana Venkataraman
We introduce a novel method for emotion conversion in speech that does not require parallel training data.