Related papers: Exploring Train and Test-Time Augmentations for Au…
Data synthesis and augmentation are essential for Sound Event Detection (SED) due to the scarcity of temporally labeled data. While augmentation methods like SpecAugment and Mix-up can enhance model performance, they remain constrained by…
This paper investigates the design of effective prompt strategies for generating realistic datasets using Text-To-Audio (TTA) models. We also analyze different techniques for efficiently combining these datasets to enhance their utility in…
Data augmentation methods usually apply the same augmentation (or a mix of them) to all the training samples. For example, to perturb data with noise, the noise is sampled from a Normal distribution with a fixed standard deviation, for all…
Self-supervised language and audio models effectively predict brain responses to speech. However, traditional prediction models rely on linear mappings from unimodal features, despite the complex integration of auditory signals with…
Many applications of speech technology require more and more audio data. Automatic assessment of the quality of the collected recordings is important to ensure they meet the requirements of the related applications. However, effective and…
Data augmentation has been actively studied for robust neural networks. Most of the recent data augmentation methods focus on augmenting datasets during the training phase. At the testing phase, simple transformations are still widely used…
Tutoring is an effective instructional method for enhancing student learning, yet its success relies on the skill and experience of the tutors. This reliance presents challenges for the widespread implementation of tutoring, particularly in…
Training Transformer-based models demands a large amount of data, while obtaining aligned and labelled data in multimodality is rather cost-demanding, especially for audio-visual speech recognition (AVSR). Thus it makes a lot of sense to…
Grounding-based vision and language models have been successfully applied to low-level vision tasks, aiming to precisely locate objects referred in captions. The effectiveness of grounding representation learning heavily relies on the scale…
Multilingual speech recognition with supervised learning has achieved great results as reflected in recent research. With the development of pretraining methods on audio and text data, it is imperative to transfer the knowledge from…
Prior work has demonstrated that data augmentation is useful for improving dialogue state tracking. However, there are many types of user utterances, while the prior method only considered the simplest one for augmentation, raising the…
While recent neural text-to-speech (TTS) systems perform remarkably well, they typically require a substantial amount of recordings from the target speaker reading in the desired speaking style. In this work, we present a novel 3-step…
Text augmentation is a technique for constructing synthetic data from an under-resourced corpus to improve predictive performance. Synthetic data generation is common in numerous domains. However, recently text augmentation has emerged in…
Large models, encompassing large language and diffusion models, have shown exceptional promise in approximating human-level intelligence, garnering significant interest from both academic and industrial spheres. However, the training of…
In supervised machine learning (SML) research, large training datasets are essential for valid results. However, obtaining primary data in learning analytics (LA) is challenging. Data augmentation can address this by expanding and…
Data augmentation is an effective approach to tackle over-fitting. Many previous works have proposed different data augmentations strategies for NLP, such as noise injection, word replacement, back-translation etc. Though effective, they…
Recently, there has been an increasing interest in two-pass streaming end-to-end speech recognition (ASR) that incorporates a 2nd-pass rescoring model on top of the conventional 1st-pass streaming ASR model to improve recognition accuracy…
Test-Time Augmentation (TTA) is a very powerful heuristic that takes advantage of data augmentation during testing to produce averaged output. Despite the experimental effectiveness of TTA, there is insufficient discussion of its…
Recent advances in synthetic speech quality have enabled us to train text-to-speech (TTS) systems by using synthetic corpora. However, merely increasing the amount of synthetic data is not always advantageous for improving training…
Handwritten text and scene text suffer from various shapes and distorted patterns. Thus training a robust recognition model requires a large amount of data to cover diversity as much as possible. In contrast to data collection and…