Training Augmentation with Adversarial Examples for Robust Speech Recognition
This paper explores the use of adversarial examples in training speech recognition systems to increase robustness of deep neural network acoustic models. During training, the fast gradient sign method is used to generate adversarial examples augmenting the original training data. Different from conventional data augmentation based on data transformations, the examples are dynamically generated based on current acoustic model parameters. We assess the impact of adversarial data augmentation in experiments on the Aurora-4 and CHiME-4 single-channel tasks, showing improved robustness against noise and channel variation. Further improvement is obtained when combining adversarial examples with teacher/student training, leading to a 23% relative word error rate reduction on Aurora-4.
Code (0)
등록된 구현이 없습니다.
Tasks
Data AugmentationRobust Speech Recognitionspeech-recognitionSpeech RecognitionSimilar Papers 제목 키워드 기반
Characterizing Speech Adversarial Examples Using Self-Attention U-Net Enhancement
Recent studies have highlighted adversarial examples as ubiquitous threats to the deep neural network (DNN) based speech recognition systems. In this work, we present a U-Net based attention model, U-Net$_{At}$, to enhan…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Data AugmentationSpeech Enhancement+2Robust Automatic Speech Recognition via WavAugment Guided Phoneme Adversarial Training
Developing a practically-robust automatic speech recognition (ASR) is challenging since the model should not only maintain the original performance on clean samples, but also achieve consistent efficacy under small volum…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionAdversarial Data Augmentation for Disordered Speech Recognition
Automatic recognition of disordered speech remains a highly challenging task to date. The underlying neuro-motor conditions, often compounded with co-occurring physical disabilities, lead to the difficulty in collecting …
Data Augmentationspeech-recognitionSpeech RecognitionReassessing Noise Augmentation Methods in the Context of Adversarial Speech
In this study, we investigate if noise-augmented training can concurrently improve adversarial robustness in automatic speech recognition (ASR) systems. We conduct a comparative analysis of the adversarial robustness of …
Adversarial RobustnessAutomatic Speech RecognitionAutomatic Speech Recognition (ASR)Data Augmentation+2Adversarial Machine Learning And Speech Emotion Recognition: Utilizing Generative Adversarial Networks For Robustness
Although deep learning has enabled unprecedented improvements in the performance of the state-of-the-art speech emotion recognition (SER) systems, recent research on adversarial examples has cast a shadow of doubt on th…
Adversarial AttackBIG-bench Machine LearningEmotion RecognitionGenerative Adversarial Network+1