相关论文: Less is More: Data Curation Matters in Scaling Spe…

Most state-of-the-art speech systems are using Deep Neural Networks (DNNs). Those systems require a large amount of data to be learned. Hence, learning state-of-the-art frameworks on under-resourced speech languages/problems is a difficult…

This paper presents a new method for training sequence-to-sequence models for speech recognition and translation tasks. Instead of the traditional approach of training models on short segments containing only lowercase or partial…

In end-to-end automatic speech recognition system, one of the difficulties for language expansion is the limited paired speech and text training data. In this paper, we propose a novel method to generate augmented samples with unpaired…

Despite the clear performance benefits of data augmentations, little is known about why they are so effective. In this paper, we disentangle several key mechanisms through which data augmentations operate. Establishing an exchange rate…

Dataset creation is typically one of the first steps when applying Artificial Intelligence methods to a new task; and the real world performance of models hinges on the quality and quantity of data available. Producing an image dataset for…

How can we train models to perform well on hard test data when hard training data is by definition difficult to label correctly? This question has been termed the scalable oversight problem and has drawn increasing attention as language…

The rapid advancement of Large Language Models (LLMs) has improved text understanding and generation but poses challenges in computational resources. This study proposes a curriculum learning-inspired, data-centric training strategy that…

Data cleaning is the initial stage of any machine learning project and is one of the most critical processes in data analysis. It is a critical step in ensuring that the dataset is devoid of incorrect or erroneous data. It can be done…

Enhancing speech quality is an indispensable yet difficult task as it is often complicated by a range of degradation factors. In addition to additive noise, reverberation, clipping, and speech attenuation can all adversely affect speech…

The success of Large Language Models (LLMs) has established that scaling compute, through joint increases in model capacity and dataset size, is the primary driver of performance in modern machine learning. While machine learning has long…

Own voice pickup for hearables in noisy environments benefits from using both an outer and an in-ear microphone outside and inside the occluded ear. Due to environmental noise recorded at both microphones, and amplification of the own voice…

Despite the strong modeling power of neural network acoustic models, speech enhancement has been shown to deliver additional word error rate improvements if multi-channel data is available. However, there has been a longstanding debate…

The potential of synthetic data in text-to-speech (TTS) model training has gained increasing attention, yet its rationality and effectiveness require systematic validation. In this study, we systematically investigate the feasibility of…

Recently, SpecAugment, an augmentation scheme for automatic speech recognition that acts directly on the spectrogram of input utterances, has shown to be highly effective in enhancing the performance of end-to-end networks on public…

Advances in natural language processing, such as transfer learning from pre-trained language models, have impacted how models are trained for programming language tasks too. Previous research primarily explored code pre-training and…

Recently, Language Models (LMs) instruction-tuned on multiple tasks, also known as multitask-prompted fine-tuning (MT), have shown the capability to generalize to unseen tasks. Previous work has shown that scaling the number of training…

As it is cumbersome and expensive to acquire a huge amount of data for training neural dialog models, data augmentation is proposed to effectively utilize existing training samples. However, current data augmentation techniques on the…

Achieving high-performing language models which include medium- and lower-resource languages remains a challenge. Massively multilingual models still underperform compared to language-specific adaptations, especially at smaller model…

Deep learning (DL) models have gained prominence in domains such as computer vision and natural language processing but remain underutilized for regression tasks involving tabular data. In these cases, traditional machine learning (ML)…

Conversational assistants are increasingly popular across diverse real-world applications, highlighting the need for advanced multimodal speech modeling. Speech, as a natural mode of communication, encodes rich user-specific characteristics…