相关论文: ImportantAug: a data augmentation agent for speech

Text data augmentation is a complex problem due to the discrete nature of sentences. Although rule-based augmentation methods are widely adopted in real-world applications because of their simplicity, they suffer from potential semantic…

Most of the current speech data augmentation methods operate on either the raw waveform or the amplitude spectrum of speech. In this paper, we propose a novel speech data augmentation method called PhasePerturbation that operates…

Language identification from speech is a common preprocessing step in many spoken language processing systems. In recent years, this field has seen fast progress, mostly due to the use of self-supervised models pretrained on multilingual…

Speech-based virtual assistants, such as Amazon Alexa, Google assistant, and Apple Siri, typically convert users' audio signals to text data through automatic speech recognition (ASR) and feed the text to downstream dialog models for…

Data Augmentation (DA) -- generating extra training samples beyond original training set -- has been widely-used in today's unbiased VQA models to mitigate the language biases. Current mainstream DA strategies are synthetic-based methods,…

We introduce a data augmentation technique based on byte pair encoding and a BERT-like self-attention model to boost performance on spoken language understanding tasks. We compare and evaluate this method with a range of augmentation…

Neural network models for audio tasks, such as automatic speech recognition (ASR) and acoustic scene classification (ASC), are susceptible to noise contamination for real-life applications. To improve audio quality, an enhancement module,…

Applying changes to an input speech signal to change the perceived speaker of speech to a target while maintaining the content of the input is a challenging but interesting task known as Voice conversion (VC). Over the last few years, this…

Accurate on-device keyword spotting (KWS) with low false accept and false reject rate is crucial to customer experience for far-field voice control of conversational agents. It is particularly challenging to maintain low false reject rate…

The performance of generative adversarial networks (GANs) heavily deteriorates given a limited amount of training data. This is mainly because the discriminator is memorizing the exact training set. To combat it, we propose Differentiable…

Adversarial training has been shown effective at endowing the learned representations with stronger generalization ability. However, it typically requires expensive computation to determine the direction of the injected perturbations. In…

The availability of highly convincing audio deepfake generators highlights the need for designing robust audio deepfake detectors. Existing works often rely solely on real and fake data available in the training set, which may lead to…

Data Augmentation (DA) is frequently used to provide additional training data without extra human annotation automatically. However, data augmentation may introduce noisy data that impairs training. To guarantee the quality of augmented…

Data augmentations are effective in improving the invariance of learning machines. We argue that the core challenge of data augmentations lies in designing data transformations that preserve labels. This is relatively straightforward for…

Data augmentation (DA) is widely used to improve the generalization of neural networks by enforcing the invariances and symmetries to pre-defined transformations applied to input data. However, a fixed augmentation policy may have different…

Vocal arousal, the non-linear acoustic features taken on by human and animal vocalizations when highly aroused, has an important communicative function because it signals aversive states such as fear, pain or distress. In this work, we…

The primary objective of this study is to demonstrate the impact of data augmentation using ChatGPT-4o-mini on food hazard and product analysis. The augmented data is generated using ChatGPT-4o-mini and subsequently used to train two large…

Neural network models have demonstrated impressive performance in predicting pathologies and outcomes from the 12-lead electrocardiogram (ECG). However, these models often need to be trained with large, labelled datasets, which are not…

Text augmentation techniques are widely used in text classification problems to improve the performance of classifiers, especially in low-resource scenarios. Whilst lots of creative text augmentation methods have been designed, they augment…

We address the problem of speech enhancement generalisation to unseen environments by performing two manipulations. First, we embed an additional recording from the environment alone, and use this embedding to alter activations in the main…