no code implementations • NAACL 2022 • Saiteja Kosgi, Sarath Sivaprasad, Niranjan Pedanekar, Anil Nelakanti, Vineet Gandhi
We present a method to control the emotional prosody of Text to Speech (TTS) systems by using phoneme-level intermediate features (pitch, energy, and duration) as levers.
no code implementations • 16 Feb 2024 • Sarath Sivaprasad, Pramod Kaushik, Sahar Abdelnabi, Mario Fritz
We study this sampling of LLMs in light of value bias and show that the sampling of LLMs tends to favour high-value options.
no code implementations • 1 Oct 2023 • Sarath Sivaprasad, Mario Fritz
We propose a novel approach to AD using explainability to capture such novel features as unexplained observations in the input space.
2 code implementations • 29 Sep 2023 • Sahar Abdelnabi, Amr Gomaa, Sarath Sivaprasad, Lea Schönherr, Mario Fritz
There is a growing interest in using Large Language Models (LLMs) as agents to tackle real-world tasks that may require assessing complex situations.
no code implementations • 18 Mar 2022 • Ragja Palakkadavath, Sarath Sivaprasad, Shirish Karande, Niranjan Pedanekar
The approach incorporates insights and business rules from domain experts in the form of easily observable and specifiable constraints, which are used as weak supervision by a machine learning model.
no code implementations • 7 Nov 2021 • Sarath Sivaprasad, Saiteja Kosgi, Vineet Gandhi
The proposed TTS system can generate speech from the text in any speaker's style, with fine control of emotion.
no code implementations • 15 Oct 2021 • Sarath Sivaprasad, Akshay Goindani, Vaibhav Garg, Ritam Basu, Saiteja Kosgi, Vineet Gandhi
We find that the presence of multiple domains incentivizes domain agnostic learning and is the primary reason for generalization in Tradition DG.
no code implementations • 9 Jun 2020 • Sarath Sivaprasad, Ankur Singh, Naresh Manwani, Vineet Gandhi
In this paper, we investigate a constrained formulation of neural networks where the output is a convex function of the input.