Darryl Wright

Shefali Garg, Zhouyuan Huo, Khe Chai Sim et al.

Automatic speech recognition (ASR) systems have been shown to have large quality disparities between the language varieties they are intended or expected to recognize. One way to mitigate this is to train or fine-tune models with more representative datasets. But this approach can be hindered by limited in-domain data for training and evaluation. We propose a new way to improve the robustness of a US English short-form speech recognizer using a small amount of out-of-domain (long-form) African American English (AAE) data. We use CORAAL, YouTube and Mozilla Common Voice to train an audio classifier to approximately output whether an utterance is AAE or some other variety including Mainstream American English (MAE). By combining the classifier output with coarse geographic information, we can select a subset of utterances from a large corpus of untranscribed short-form queries for semi-supervised learning at scale. Fine-tuning on this data results in a 38.5% relative word error rate disparity reduction between AAE and MAE without reducing MAE quality.

Mike Walmsley, Lewis Smith, Chris Lintott et al.

We use Bayesian convolutional neural networks and a novel generative model of Galaxy Zoo volunteer responses to infer posteriors for the visual morphology of galaxies. Bayesian CNN can learn from galaxy images with uncertain labels and then, for previously unlabelled galaxies, predict the probability of each possible label. Our posteriors are well-calibrated (e.g. for predicting bars, we achieve coverage errors of 11.8% within a vote fraction deviation of 0.2) and hence are reliable for practical use. Further, using our posteriors, we apply the active learning strategy BALD to request volunteer responses for the subset of galaxies which, if labelled, would be most informative for training our network. We show that training our Bayesian CNNs using active learning requires up to 35-60% fewer labelled galaxies, depending on the morphological feature being classified. By combining human and machine intelligence, Galaxy Zoo will be able to classify surveys of any conceivable scale on a timescale of weeks, providing massive and detailed morphology catalogues to support research into galaxy evolution.

Lucy Fortson, Darryl Wright, Chris Lintott et al.

Over the past decade, Citizen Science has become a proven method of distributed data analysis, enabling research teams from diverse domains to solve problems involving large quantities of data with complexity levels which require human pattern recognition capabilities. With over 120 projects built reaching nearly 1.7 million volunteers, the Zooniverse.org platform has led the way in the application of Citizen Science as a method for closing the Big Data analysis gap. Since the launch in 2007 of the Galaxy Zoo project, the Zooniverse platform has enabled significant contributions across many disciplines; e.g., in ecology, humanities, and astronomy. Citizen science as an approach to Big Data combines the twin advantages of the ability to scale analysis to the size of modern datasets with the ability of humans to make serendipitous discoveries. To cope with the larger datasets looming on the horizon such as astronomy's Large Synoptic Survey Telescope (LSST) or the 100's of TB from ecology projects annually, Zooniverse has been researching a system design that is optimized for efficiency in task assignment and incorporating human and machine classifiers into the classification engine. By making efficient use of smart task assignment and the combination of human and machine classifiers, we can achieve greater accuracy and flexibility than has been possible to date. We note that creating the most efficient system must consider how best to engage and retain volunteers as well as make the most efficient use of their classifications. Our work thus focuses on understanding the factors that optimize efficiency of the combined human-machine system. This paper summarizes some of our research to date on integration of machine learning with Zooniverse, while also describing new infrastructure developed on the Zooniverse platform to carry out this research.