相关论文: Learning Music Representations with wav2vec 2.0

In this paper, we work on a sound recognition system that continually incorporates new sound classes. Our main goal is to develop a framework where the model can be updated without relying on labeled data. For this purpose, we propose…

Self-supervised learning has attracted plenty of recent research interest. However, most works for self-supervision in speech are typically unimodal and there has been limited work that studies the interaction between audio and visual…

Consumer-grade music recordings such as those captured by mobile devices typically contain distortions in the form of background noise, reverb, and microphone-induced EQ. This paper presents a deep learning approach to enhance low-quality…

Self-supervised learning (SSL) based speech pre-training has attracted much attention for its capability of extracting rich representations learned from massive unlabeled data. On the other hand, the use of weakly-supervised data is less…

To reduce the need for skilled clinicians in heart sound interpretation, recent studies on automating cardiac auscultation have explored deep learning approaches. However, despite the demands for large data for deep learning, the size of…

In this work, we investigate if the wav2vec 2.0 self-supervised pretraining helps mitigate the overfitting issues with connectionist temporal classification (CTC) training to reduce its performance gap with flat-start lattice-free MMI…

ASR systems designed for native English (L1) usually underperform on non-native English (L2). To address this performance gap, \textbf{(i)} we extend our previous work to investigate fine-tuning of a pre-trained wav2vec 2.0 model…

Recently, there have been tremendous research outcomes in the fields of speech recognition and natural language processing. This is due to the well-developed multi-layers deep learning paradigms such as wav2vec2.0, Wav2vecU, WavBERT, and…

To be able to interact better with humans, it is crucial for machines to understand sound - a primary modality of human perception. Previous works have used sound to learn embeddings for improved generic textual similarity assessment. In…

Perch is a performant pre-trained model for bioacoustics. It was trained in supervised fashion, providing both off-the-shelf classification scores for thousands of vocalizing species as well as strong embeddings for transfer learning. In…

Over the last decade, numerous studies have shown that deep neural networks exhibit sensory representations similar to those of the mammalian brain, in that their activations linearly map onto cortical responses to the same sensory inputs.…

Recent progress in network-based audio event classification has shown the benefit of pre-training models on visual data such as ImageNet. While this process allows knowledge transfer across different domains, training a model on large-scale…

How language-specific are speech representations learned by self-supervised models? Existing work has shown that a range of linguistic features can be successfully decoded from end-to-end models trained only on speech recordings. However,…

Benefiting from large-scale datasets and pre-trained models, the field of generative models has recently gained significant momentum. However, most datasets for symbolic music are very small, which potentially limits the performance of…

Music Information Retrieval (MIR) research is increasingly leveraging representation learning to obtain more compact, powerful music audio representations for various downstream MIR tasks. However, current representation evaluation methods…

In this paper, we present our comprehensive study aimed at enhancing the generalization capabilities of audio deepfake detection models. We investigate the performance of various pre-trained backbones, including Wav2Vec2, WavLM, and…

While both the data volume and heterogeneity of the digital music content is huge, it has become increasingly important and convenient to build a recommendation or search system to facilitate surfacing these content to the user or consumer…

Many current natural language processing applications for social media rely on representation learning and utilize pre-trained word embeddings. There currently exist several publicly-available, pre-trained sets of word embeddings, but they…

Representation learning seeks to expose certain aspects of observed data in a learned representation that's amenable to downstream tasks like classification. For instance, a good representation for 2D images might be one that describes only…

Pre-training on large-scale datasets and then fine-tuning on downstream tasks have become a standard practice in deep learning. However, pre-training data often contain label noise that may adversely affect the generalization of the model.…