Search Results for author:
Found 8 papers, 1 papers with code
Empathic Machines: Using Intermediate Features as Levers to Emulate Emotions in Text-To-Speech Systems
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.
Exploring Value Biases: How LLMs Deviate Towards the Ideal
We study this sampling of LLMs in light of value bias and show that the sampling of LLMs tends to favour high-value options.
Don't Miss Out on Novelty: Importance of Novel Features for Deep Anomaly Detection
We propose a novel approach to AD using explainability to capture such novel features as unexplained observations in the input space.
LLM-Deliberation: Evaluating LLMs with Interactive Multi-Agent Negotiation Games
There is a growing interest in using Large Language Models (LLMs) as agents to tackle real-world tasks that may require assessing complex situations.
I Know Therefore I Score: Label-Free Crafting of Scoring Functions using Constraints Based on Domain Expertise
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.
Emotional Prosody Control for Speech Generation
The proposed TTS system can generate speech from the text in any speaker's style, with fine control of emotion.
Reappraising Domain Generalization in Neural Networks
We find that the presence of multiple domains incentivizes domain agnostic learning and is the primary reason for generalization in Tradition DG.
The Curious Case of Convex Neural Networks
In this paper, we investigate a constrained formulation of neural networks where the output is a convex function of the input.
