Related papers: Pseudo-Label Transfer from Frame-Level to Note-Lev…

Recent progress in singing voice separation has primarily focused on supervised deep learning methods. However, the scarcity of ground-truth data with clean musical sources has been a problem for long. Given a limited set of labeled data,…

Self-training has been shown to be helpful in addressing data scarcity for many domains, including vision, speech, and language. Specifically, self-training, or pseudo-labeling, labels unsupervised data and adds that to the training pool.…

The lack of labeled data is a major obstacle in many music information retrieval tasks such as melody extraction, where labeling is extremely laborious or costly. Semi-supervised learning (SSL) provides a solution to alleviate the issue by…

Detecting singing-voice in polyphonic instrumental music is critical to music information retrieval. To train a robust vocal detector, a large dataset marked with vocal or non-vocal label at frame-level is essential. However, frame-level…

The high capacity of deep learning models to learn complex patterns poses a significant challenge when confronted with label noise. The inability to differentiate clean and noisy labels ultimately results in poor generalization. We approach…

The current lyrics transcription approaches heavily rely on supervised learning with labeled data, but such data are scarce and manual labeling of singing is expensive. How to benefit from unlabeled data and alleviate limited data problem…

The amount of labeled data to train models for speech tasks is limited for most languages, however, the data scarcity is exacerbated for speech translation which requires labeled data covering two different languages. To address this issue,…

Automatic music transcription converts audio recordings into symbolic representations, facilitating music analysis, retrieval, and generation. A musical note is characterized by pitch, onset, and offset in an audio domain, whereas it is…

Training deep neural networks with noisy labels remains a significant challenge, often leading to degraded performance. Existing methods for handling label noise typically rely on either transition matrix, noise detection, or meta-learning…

State-of-the-art automatic speech recognition (ASR) systems are trained with tens of thousands of hours of labeled speech data. Human transcription is expensive and time consuming. Factors such as the quality and consistency of the…

High accuracy speech recognition requires a large amount of transcribed data for supervised training. In the absence of such data, domain adaptation of a well-trained acoustic model can be performed, but even here, high accuracy usually…

In recent years, semi-supervised learning (SSL) has shown tremendous success in leveraging unlabeled data to improve the performance of deep learning models, which significantly reduces the demand for large amounts of labeled data. Many SSL…

The lack of labeled data is a common challenge in speech classification tasks, particularly those requiring extensive subjective assessment, such as cognitive state classification. In this work, we propose a Semi-Supervised Learning (SSL)…

Semi-supervised learning through pseudo-labeling has become a staple of state-of-the-art monolingual speech recognition systems. In this work, we extend pseudo-labeling to massively multilingual speech recognition with 60 languages. We…

Recent progress in semi- and self-supervised learning has caused a rift in the long-held belief about the need for an enormous amount of labeled data for machine learning and the irrelevancy of unlabeled data. Although it has been…

To learn target discriminative representations, using pseudo-labels is a simple yet effective approach for unsupervised domain adaptation. However, the existence of false pseudo-labels, which may have a detrimental influence on learning…

In this paper we revisit the idea of pseudo-labeling in the context of semi-supervised learning where a learning algorithm has access to a small set of labeled samples and a large set of unlabeled samples. Pseudo-labeling works by applying…

We propose a novel training scheme using self-label correction and data augmentation methods designed to deal with noisy labels and improve real-world accuracy on a polyphonic audio content detection task. The augmentation method reduces…

The study of label noise in sound event recognition has recently gained attention with the advent of larger and noisier datasets. This work addresses the problem of missing labels, one of the big weaknesses of large audio datasets, and one…

Language model pre-training has proven to be useful in many language understanding tasks. In this paper, we investigate whether it is still helpful to add the self-training method in the pre-training step and the fine-tuning step. Towards…