Penny Karanasou — accepted AI-conference papers

2025

Long-Short Decision Transformer: Bridging Global and Local Dependencies for Generalized Decision-Making

Jincheng Wang, Penny Karanasou, Pengyuan Wei, Elia Gatti, Diego Martinez Plasencia, Dimitrios Kanoulas

ICLR 2025poster

Decision Transformers (DTs) effectively capture long-range dependencies using self-attention but struggle with fine-grained local relationships, especially the Markovian properties in many offline-RL datasets. Conversely, Decision Convformer (DC) utilizes convolutional filters for capturing local pa…

Cited by 1 Source ↗PDF ↗Scholar ↗

2021

Camp: A Two-Stage Approach to Modelling Prosody in Context

Zack Hodari, Alexis Moinet, Sri Karlapati, Jaime Lorenzo-Trueba, Thomas Merritt, Arnaud Joly +3

ICASSP 2021accepted

Prosody is an integral part of communication, but remains an open problem in state-of-the-art speech synthesis. There are two major issues faced when modelling prosody: (1) prosody varies at a slower rate compared with other content in the acoustic signal (e.g. segmental information and background n…

Cited by 33 Source ↗Scholar ↗

2021

Prosodic Representation Learning and Contextual Sampling for Neural Text-to-Speech

Sri Karlapati, Ammar Abbas, Zack Hodari, Alexis Moinet, Arnaud Joly, Penny Karanasou +1

ICASSP 2021accepted

In this paper, we introduce Kathaka, a model trained with a novel two-stage training process for neural speech synthesis with contextually appropriate prosody. In Stage I, we learn a prosodic distribution at the sentence level from mel-spectrograms available during training. In Stage II, we propose…

Cited by 0 Source ↗Scholar ↗

2016

Combining i-vector representation and structured neural networks for rapid adaptation

Chunyang Wu, Penny Karanasou, Mark J. F. Gales

ICASSP 2016accepted

Rapid adaptation of deep neural networks (DNNs) with limited unsupervised data remains a significant challenge. This paper investigates the combination of two schemes that have been proposed to address this problem: i-vector representations and multi-basis adaptive neural networks (MBANNs). Two appr…

Cited by 0 Source ↗Scholar ↗

2015

An investigation into speaker informed DNN front-end for LVCSR

Yulan Liu, Penny Karanasou, Thomas Hain

ICASSP 2015accepted

Deep Neural Network (DNN) has become a standard method in many ASR tasks. Recently there is considerable interest in “informed training” of DNNs, where DNN input is augmented with auxiliary codes, such as i-vectors, speaker codes, speaker separation bottleneck (SSBN) features, etc. This paper compar…

Cited by 0 Source ↗Scholar ↗