David Chan

David M. Chan, Shalini Ghosh

Deep neural networks have largely demonstrated their ability to perform automated speech recognition (ASR) by extracting meaningful features from input audio frames. Such features, however, may consist not only of information about the spoken language content, but also may contain information about unnecessary contexts such as background noise and sounds or speaker identity, accent, or protected attributes. Such information can directly harm generalization performance, by introducing spurious correlations between the spoken words and the context in which such words were spoken. In this work, we introduce an unsupervised, encoder-agnostic method for factoring speech-encoder representations into explicit content-encoding representations and spurious context-encoding representations. By doing so, we demonstrate improved performance on standard ASR benchmarks, as well as improved performance in both real-world and artificially noisy ASR scenarios.

David M. Chan, Shalini Ghosh, Debmalya Chakrabarty et al.

Traditionally, research in automated speech recognition has focused on local-first encoding of audio representations to predict the spoken phonemes in an utterance. Unfortunately, approaches relying on such hyper-local information tend to be vulnerable to both local-level corruption (such as audio-frame drops, or loud noises) and global-level noise (such as environmental noise, or background noise) that has not been seen during training. In this work, we introduce a novel approach which leverages a self-supervised learning technique based on masked language modeling to compute a global, multi-modal encoding of the environment in which the utterance occurs. We then use a new deep-fusion framework to integrate this global context into a traditional ASR method, and demonstrate that the resulting method can outperform baseline methods by up to 7% on Librispeech; gains on internal datasets range from 6% (on larger models) to 45% (on smaller models).

Aatif Jiwani, Shubhrakanti Ganguly, Chao Ding et al.

Urban areas consume over two-thirds of the world's energy and account for more than 70 percent of global CO2 emissions. As stated in IPCC's Global Warming of 1.5C report, achieving carbon neutrality by 2050 requires a clear understanding of urban geometry. High-quality building footprint generation from satellite images can accelerate this predictive process and empower municipal decision-making at scale. However, previous Deep Learning-based approaches face consequential issues such as scale invariance and defective footprints, partly due to ever-present class-wise imbalance. Additionally, most approaches require supplemental data such as point cloud data, building height information, and multi-band imagery - which has limited availability and are tedious to produce. In this paper, we propose a modified DeeplabV3+ module with a Dilated Res-Net backbone to generate masks of building footprints from three-channel RGB satellite imagery only. Furthermore, we introduce an F-Beta measure in our objective function to help the model account for skewed class distributions and prevent false-positive footprints. In addition to F-Beta, we incorporate an exponentially weighted boundary loss and use a cross-dataset training strategy to further increase the quality of predictions. As a result, we achieve state-of-the-art performances across three public benchmarks and demonstrate that our RGB-only method produces higher quality visual results and is agnostic to the scale, resolution, and urban density of satellite imagery.