In this paper we describe the ForSpec Temporal Logic (FTL), the new temporal property-specification logic of ForSpec, Intel's new formal specification language. The key features of FTL are as follows: it is a linear temporal logic, based on Pnueli's LTL, it is based on a rich set of logical and arithmetical operations on bit vectors to describe state properties, it enables the user to define temporal connectives over time windows, it enables the user to define regular events, which are regular sequences of Boolean events, and then relate such events via special connectives, it enables the user to express properties about the past, and it includes constructs that enable the user to model multiple clock and reset signals, which is useful in the verification of hardware design.
We propose a new end-to-end neural acoustic model for automatic speech recognition. The model is composed of multiple blocks with residual connections between them. Each block consists of one or more modules with 1D time-channel separable convolutional layers, batch normalization, and ReLU layers. It is trained with CTC loss. The proposed network achieves near state-of-the-art accuracy on LibriSpeech and Wall Street Journal, while having fewer parameters than all competing models. We also demonstrate that this model can be effectively fine-tuned on new datasets.
In this paper we report state-of-the-art results on LibriSpeech among end-to-end speech recognition models without any external training data. Our model, Jasper, uses only 1D convolutions, batch normalization, ReLU, dropout, and residual connections. To improve training, we further introduce a new layer-wise optimizer called NovoGrad. Through experiments, we demonstrate that the proposed deep architecture performs as well or better than more complex choices. Our deepest Jasper variant uses 54 convolutional layers. With this architecture, we achieve 2.95% WER using a beam-search decoder with an external neural language model and 3.86% WER with a greedy decoder on LibriSpeech test-clean. We also report competitive results on Wall Street Journal and the Hub5'00 conversational evaluation datasets.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.