Related papers: MERT: Acoustic Music Understanding Model with Larg…

Self-supervised learning (SSL) has attracted increased attention for learning meaningful speech representations. Speech SSL models, such as WavLM, employ masked prediction training to encode general-purpose representations. In contrast,…

Recent works of music representation learning mainly focus on learning acoustic music representations with unlabeled audios or further attempt to acquire multi-modal music representations with scarce annotated audio-text pairs. They either…

Semi-supervised learning in automatic speech recognition (ASR) typically relies on pseudo-labeling, which often suffers from confirmation bias and error accumulation due to noisy supervision. To address this limitation, we propose ReHear, a…

Nowadays, supervised deep learning techniques yield the best state-of-the-art prediction performances for a wide variety of computer vision tasks. However, such supervised techniques generally require a large amount of manually labeled…

Symbolic Music Emotion Recognition(SMER) is to predict music emotion from symbolic data, such as MIDI and MusicXML. Previous work mainly focused on learning better representation via (mask) language model pre-training but ignored the…

Artificial intelligence (AI) is anticipated to play a pivotal role in 6G. However, a key challenge in developing AI-powered solutions is the extensive data collection and labeling efforts required to train supervised deep learning models.…

Supervised learning demands large amounts of precisely annotated data to achieve promising results. Such data curation is labor-intensive and imposes significant overhead regarding time and costs. Self-supervised learning (SSL) partially…

Recent advances in self-supervised learning (SSL) methods offer a range of strategies for capturing useful representations from music audio without the need for labeled data. While some techniques focus on preserving comprehensive details…

Self-supervised learning (SSL) has become the de facto training paradigm of large models where pre-training is followed by supervised fine-tuning using domain-specific data and labels. Hypothesizing that SSL models would learn more generic,…

Self-supervised Transformer based models, such as wav2vec 2.0 and HuBERT, have produced significant improvements over existing approaches to automatic speech recognition (ASR). This is evident in the performance of the wav2vec 2.0 based…

Micro-Action Recognition (MAR) aims to classify subtle human actions in video. However, annotating MAR datasets is particularly challenging due to the subtlety of actions. To this end, we introduce the setting of Semi-Supervised MAR…

Deep learning with noisy labels is a challenging task. Recent prominent methods that build on a specific sample selection (SS) strategy and a specific semi-supervised learning (SSL) model achieved state-of-the-art performance. Intuitively,…

Pseudo-label-based semi-supervised learning (SSL) has achieved great success on raw data utilization. However, its training procedure suffers from confirmation bias due to the noise contained in self-generated artificial labels. Moreover,…

Self-supervised language models are very effective at predicting high-level cortical responses during language comprehension. However, the best current models of lower-level auditory processing in the human brain rely on either…

We present a method for transferring pre-trained self-supervised (SSL) speech representations to multiple languages. There is an abundance of unannotated speech, so creating self-supervised representations from raw audio and fine-tuning on…

This paper studies compressing pre-trained language models, like BERT (Devlin et al.,2019), via teacher-student knowledge distillation. Previous works usually force the student model to strictly mimic the smoothed labels predicted by the…

We study pseudo-labeling for the semi-supervised training of ResNet, Time-Depth Separable ConvNets, and Transformers for speech recognition, with either CTC or Seq2Seq loss functions. We perform experiments on the standard LibriSpeech…

The training of deep learning models generally requires a large amount of annotated data for effective convergence and generalisation. However, obtaining high-quality annotations is a laboursome and expensive process due to the need of…

Emotion recognition is a challenging task due to limited availability of in-the-wild labeled datasets. Self-supervised learning has shown improvements on tasks with limited labeled datasets in domains like speech and natural language.…

Much recent work on Spoken Language Understanding (SLU) is limited in at least one of three ways: models were trained on oracle text input and neglected ASR errors, models were trained to predict only intents without the slot values, or…