Search Results for author:
Found 12 papers, 3 papers with code
Creating New Voices using Normalizing Flows
As there is growing interest in synthesizing voices of new speakers, here we investigate the ability of normalizing flows in text-to-speech (TTS) and voice conversion (VC) modes to extrapolate from speakers observed during training to create unseen speaker identities.
Comparing normalizing flows and diffusion models for prosody and acoustic modelling in text-to-speech
Neural text-to-speech systems are often optimized on L1/L2 losses, which make strong assumptions about the distributions of the target data space.
SCRAPS: Speech Contrastive Representations of Acoustic and Phonetic Spaces
We train a CLIP-based model with the aim to learn shared representations of phonetic and acoustic spaces.
ML framework for global river flood predictions based on the Caravan dataset
Here, we offer the first global river flood prediction framework based on the newly published Caravan dataset.
Remap, warp and attend: Non-parallel many-to-many accent conversion with Normalizing Flows
Regional accents of the same language affect not only how words are pronounced (i. e., phonetic content), but also impact prosodic aspects of speech such as speaking rate and intonation.
RainBench: Towards Global Precipitation Forecasting from Satellite Imagery
Extreme precipitation events, such as violent rainfall and hail storms, routinely ravage economies and livelihoods around the developing world.
G3AN: Disentangling Appearance and Motion for Video Generation
Creating realistic human videos entails the challenge of being able to simultaneously generate both appearance, as well as motion.
Mapping Informal Settlements in Developing Countries using Machine Learning and Low Resolution Multi-spectral Data
2) We show that it is possible to detect informal settlements using freely available low-resolution (LR) data, in contrast to previous studies that use very-high resolution (VHR) satellite and aerial imagery, something that is cost-prohibitive for NGOs.
Multi$^{\mathbf{3}}$Net: Segmenting Flooded Buildings via Fusion of Multiresolution, Multisensor, and Multitemporal Satellite Imagery
We propose a novel approach for rapid segmentation of flooded buildings by fusing multiresolution, multisensor, and multitemporal satellite imagery in a convolutional neural network.
Generating Material Maps to Map Informal Settlements
Detecting and mapping informal settlements encompasses several of the United Nations sustainable development goals.
Mapping Informal Settlements in Developing Countries with Multi-resolution, Multi-spectral Data
We propose two effective methods for detecting and mapping the locations of informal settlements.
Dense Decoder Shortcut Connections for Single-Pass Semantic Segmentation
We propose a novel end-to-end trainable, deep, encoder-decoder architecture for single-pass semantic segmentation.
Ranked #7 on
Semantic Segmentation
on CamVid
