Increasing demand for on-device Automatic Speech Recognition (ASR) systems has resulted in renewed interests in developing automatic model compression techniques. Past research have shown that AutoML-based Low Rank Factorization (LRF) technique, when applied to an end-to-end Encoder-Attention-Decoder style ASR model, can achieve a speedup of up to 3.7x, outperforming laborious manual rank-selection approaches. However, we show that current AutoML-based search techniques only work up to a certain compression level, beyond which they fail to produce compressed models with acceptable word error rates (WER). In this work, we propose an iterative AutoML-based LRF approach that achieves over 5x compression without degrading the WER, thereby advancing the state-of-the-art in ASR compression.

LPCNet is an efficient vocoder that combines linear prediction and deep neural network modules to keep the computational complexity low. In this work, we present two techniques to further reduce it's complexity, aiming for a low-cost LPCNet vocoder-based neural Text-to-Speech (TTS) System. These techniques are: 1) Sample-bunching, which allows LPCNet to generate more than one audio sample per inference; and 2) Bit-bunching, which reduces the computations in the final layer of LPCNet. With the proposed bunching techniques, LPCNet, in conjunction with a Deep Convolutional TTS (DCTTS) acoustic model, shows a 2.19x improvement over the baseline run-time when running on a mobile device, with a less than 0.1 decrease in TTS mean opinion score (MOS).

Representing a new class of tool for biological modeling, Bio Model Analyzer (BMA) uses sophisticated computational techniques to determine stabilization in cellular networks. This paper presents designs aimed at easing the problems that can arise when such techniques - \'14using distinct approaches to conceptualizing networks\'14 - are applied in biology. The work also engages with more fundamental issues being discussed in the philosophy of science and science studies. It shows how scientific ways of knowing are constituted in routine interactions with tools like BMA, where the emphasis is on the practical business at hand, even when seemingly deep conceptual problems exist. For design, this perspective refigures the frictions raised when computation is used to model biology. Rather than obstacles, they can be seen as opportunities for opening up different ways of knowing.