arXiv subjects

John Quinn

Publications and source records attributed to John Quinn.

23 records · Page 2Linked to original sources

arXiv2019

Mobility profiles and calendars for food security and livelihoods analysis

Social vulnerability is defined as the capacity of individuals and social groups to respond to any external stress placed on their livelihoods and wellbeing. Mobility and migrations are relevant when assessing vulnerability since the movements of a population reflect on their livelihoods, coping strategies and social safety nets. Although in general migration characterization is complex and open to controversy, changes in mobility patterns for vulnerable population groups are likely to indicate a change in livelihoods or coping strategies. These changes can also indicate that the population groups may be exposed to new shocks; hence, monitoring of changes in mobility patterns can be a powerful early warning mechanism.

cs.CY↗

arXiv2018

ASR-free CNN-DTW keyword spotting using multilingual bottleneck features for almost zero-resource languages

We consider multilingual bottleneck features (BNFs) for nearly zero-resource keyword spotting. This forms part of a United Nations effort using keyword spotting to support humanitarian relief programmes in parts of Africa where languages are severely under-resourced. We use 1920 isolated keywords (40 types, 34 minutes) as exemplars for dynamic time warping (DTW) template matching, which is performed on a much larger body of untranscribed speech. These DTW costs are used as targets for a convolutional neural network (CNN) keyword spotter, giving a much faster system than direct DTW. Here we consider how available data from well-resourced languages can improve this CNN-DTW approach. We show that multilingual BNFs trained on ten languages improve the area under the ROC curve of a CNN-DTW system by 10.9% absolute relative to the MFCC baseline. By combining low-resource DTW-based supervision with information from well-resourced languages, CNN-DTW is a competitive option for low-resource keyword spotting.

cs.CL↗

arXiv2018

Automatic Speech Recognition for Humanitarian Applications in Somali

We present our first efforts in building an automatic speech recognition system for Somali, an under-resourced language, using 1.57 hrs of annotated speech for acoustic model training. The system is part of an ongoing effort by the United Nations (UN) to implement keyword spotting systems supporting humanitarian relief programmes in parts of Africa where languages are severely under-resourced. We evaluate several types of acoustic model, including recent neural architectures. Language model data augmentation using a combination of recurrent neural networks (RNN) and long short-term memory neural networks (LSTMs) as well as the perturbation of acoustic data are also considered. We find that both types of data augmentation are beneficial to performance, with our best system using a combination of convolutional neural networks (CNNs), time-delay neural networks (TDNNs) and bi-directional long short term memory (BLSTMs) to achieve a word error rate of 53.75%.

cs.CL↗

arXiv2018

Fast ASR-free and almost zero-resource keyword spotting using DTW and CNNs for humanitarian monitoring

We use dynamic time warping (DTW) as supervision for training a convolutional neural network (CNN) based keyword spotting system using a small set of spoken isolated keywords. The aim is to allow rapid deployment of a keyword spotting system in a new language to support urgent United Nations (UN) relief programmes in parts of Africa where languages are extremely under-resourced and the development of annotated speech resources is infeasible. First, we use 1920 recorded keywords (40 keyword types, 34 minutes of speech) as exemplars in a DTW-based template matching system and apply it to untranscribed broadcast speech. Then, we use the resulting DTW scores as targets to train a CNN on the same unlabelled speech. In this way we use just 34 minutes of labelled speech, but leverage a large amount of unlabelled data for training. While the resulting CNN keyword spotter cannot match the performance of the DTW-based system, it substantially outperforms a CNN classifier trained only on the keywords, improving the area under the ROC curve from 0.54 to 0.64. Because our CNN system is several orders of magnitude faster at runtime than the DTW system, it represents the most viable keyword spotter on this extremely limited dataset.

cs.CL↗

arXiv2015

Testing a Novel Self-Assembling Data Paradigm in the Context of IACT Data

The process of gathering and associating data from multiple sensors or sub-detectors due to a common physical event (the process of event-building) is used in many fields, including high-energy physics and $γ$-ray astronomy. Fault tolerance in event-building is a challenging problem that increases in difficulty with higher data throughput rates and increasing numbers of sub-detectors. We draw on biological self-assembly models in the development of a novel event-building paradigm that treats each packet of data from an individual sensor or sub-detector as if it were a molecule in solution. Just as molecules are capable of forming chemical bonds, "bonds" can be defined between data packets using metadata-based discriminants. A database -- which plays the role of a beaker of solution -- continually selects pairs of assemblies at random to test for bonds, which allows single packets and small assemblies to aggregate into larger assemblies. During this process higher-quality associations supersede spurious ones. The database thereby becomes fluid, dynamic, and self-correcting rather than static. We will describe tests of the self-assembly paradigm using our first fluid database prototype and data from the VERITAS $γ$-ray telescope.

astro-ph.IM↗