Deep learning (DL) defines a new data-driven programming paradigm that constructs the internal system logic of a crafted neuron network through a set of training data. We have seen wide adoption of DL in many safety-critical scenarios. However, a plethora of studies have shown that the state-of-the-art DL systems suffer from various vulnerabilities which can lead to severe consequences when applied to real-world applications. Currently, the testing adequacy of a DL system is usually measured by the accuracy of test data. Considering the limitation of accessible high quality test data, good accuracy performance on test data can hardly provide confidence to the testing adequacy and generality of DL systems. Unlike traditional software systems that have clear and controllable logic and functionality, the lack of interpretability in a DL system makes system analysis and defect detection difficult, which could potentially hinder its real-world deployment. In this paper, we propose DeepGauge, a set of multi-granularity testing criteria for DL systems, which aims at rendering a multi-faceted portrayal of the testbed. The in-depth evaluation of our proposed testing criteria is demonstrated on two well-known datasets, five DL systems, and with four state-of-the-art adversarial attack techniques against DL. The potential usefulness of DeepGauge sheds light on the construction of more generic and robust DL systems. CCS CONCEPTS• Software and its engineering → Software testing and debugging; • Theory of computation → Adversarial learning;

Training a conventional automatic speech recognition (ASR) system to support multiple languages is challenging because the subword unit, lexicon and word inventories are typically language specific. In contrast, sequence-to-sequence models are well suited for multilingual ASR because they encapsulate an acoustic, pronunciation and language model jointly in a single network. In this work we present a single sequence-to-sequence ASR model trained on 9 different Indian languages, which have very little overlap in their scripts. Specifically, we take a union of language-specific grapheme sets and train a grapheme-based sequence-to-sequence model jointly on data from all languages. We find that this model, which is not explicitly given any information about language identity, improves recognition performance by 21% relative compared to analogous sequence-to-sequence models trained on each language individually. By modifying the model to accept a language identifier as an additional input feature, we further improve performance by an additional 7% relative and eliminate confusion between different languages.

No abstract

To investigate the phenomenon of technostress among university teachers in higher education, a multidimensional person-environment misfit framework of technostress was proposed and validated by 343 teachers from universities in China. The findings indicate that person-organization (P-O) misfit, person-technology (P-T) misfit, and person-people (P-P) misfit largely captured how university teachers interact with multiple dimensions of the higher education environment in an imbalanced way that causes technostress. P-O misfit predicted P-T misfit and P-P misfit. Relationships between multidimensional technostress and job performance were investigated. It was found that university requirements related to the use of ICT and the suitability of ICT for university teachers’ work were critical factors affecting their job performance. In addition, a comparison was made among university teachers from different grade levels, revealing that university management related to ICT use tended to affect university teachers of higher-grade levels more than those of lower-grade levels in generating technostress.

No abstract

No abstract

No abstract

Various neural network architectures have been proposed in the literature to model 2D correlations in the input signal, including convolutional layers, frequency LSTMs and 2D LSTMs such as time-frequency LSTMs, grid LSTMs and ReNet LSTMs. It has been argued that frequency LSTMs can model translational variations similar to CNNs, and 2D LSTMs can model even more variations [1], but no proper comparison has been done for speech tasks. While convolutional layers have been a popular technique in speech tasks, this paper compares convolutional and LSTM architectures to model time-frequency patterns as the first layer in an LDNN [2] architecture. This comparison is particularly interesting when the convolutional layer degrades performance, such as in noisy conditions or when the learned filterbank is not constant-Q [3]. We find that grid-LDNNs offer the best performance of all techniques, and provide between a 1-4% relative improvement over an LDNN and CLDNN on 3 different large vocabulary Voice Search tasks.