2019 · 41 citations · 30 references
ComputingComputer ScienceComputational LinguisticsMachine LearningNatural Language ProcessingDeep LearningDialogue SystemsLanguage ModelingLanguage ModelsSpeech RecognitionAccuracyCommandsLanguage Model PretrainingPhoneme RecognitionPretraining ObjectivesSpeech Understanding
Whereas conventional spoken language understanding (SLU) systems map speech to text, and then text to intent, end-to-end SLU systems map speech directly to intent through a single trainable model. Achieving high accuracy with these end-to-end models without a large amount of training data is difficult. We propose a method to reduce the data requirements of end-to-end SLU in which the model is first pre-trained to predict words and phonemes, thus learning good features for SLU. We introduce a new SLU dataset, Fluent Speech Commands, and show that our method improves performance both when the full dataset is used for training and when only a small subset is used. We also describe preliminary experiments to gauge the model's ability to generalize to new phrases not heard during training.
30
Gradient-based learning applied to document recognition
Yann LeCun, Léon Bottou, Yoshua Bengio et al. · Proceedings of the IEEE · 1998 · 58.2K citations · Full text
Efficient Estimation of Word Representations in Vector Space
Tomáš Mikolov, Kai Chen, Greg S. Corrado et al. · arXiv (Cornell University) · 2013 · 11.7K citations · Full text
Rich Caruana · Machine Learning · 1997 · 6.3K citations · Full text
Librispeech: An ASR corpus based on public domain audio books
Vassil Panayotov, Guoguo Chen, Daniel Povey et al. · 2015 · 6K citations
Computing, Computer Science, English +17