Automatic transmissions are a core component of modern vehicles, and achieving good shift quality is critical to enhance the driving experience. In companies that manufacture transmissions, expert engineers take great care in calibrating parameters for controlling hydraulic pressure with the goal of achieving targeted shift quality. Because we need human experts to evaluate shift quality, it is hard to shorten the time taken to calibrate the systems controlling hydraulic pressure. In this paper, to reduce such development time, we propose a novel framework of a Classifier of Shift Quality; it applies the standard Supervised Deep Learning techniques (CSQ-SDL) to time-series measurement data. The framework consists of five procedures: measurement data collection, labeling by experts, data augmentation, data standardization, and the training of deep convolutional neural networks. Moreover, we also carry out driving experiments in which CSQ-SDL is used to assess the engagement of the lock-up clutch of a specific transmission model. By using raw time-series data measured by ordinary sensors in advance, and labels written later by an expert engineer looking at the raw data, we build binary classifiers and test their performance. It turns out that the accuracy of predicting expert's judgment is high; the area under the curve is 0.94. The result indicates that the proposed method is capable shortening product development times and thus meeting the demands of today's competitive automotive market.