English
Related papers

Related papers: End-to-End Lyrics Recognition with Self-supervised…

200 papers

Self-supervised learning (SSL) can be used to solve complex visual tasks without human labels. Self-supervised representations encode useful semantic information about images, and as a result, they have already been used for tasks such as…

Computer Vision and Pattern Recognition · Computer Science 2023-11-27 Paul Engstler , Luke Melas-Kyriazi , Christian Rupprecht , Iro Laina

Spoken language understanding system is traditionally designed as a pipeline of a number of components. First, the audio signal is processed by an automatic speech recognizer for transcription or n-best hypotheses. With the recognition…

Computation and Language · Computer Science 2018-02-26 Dmitriy Serdyuk , Yongqiang Wang , Christian Fuegen , Anuj Kumar , Baiyang Liu , Yoshua Bengio

Recently, end-to-end mispronunciation detection and diagnosis (MD&D) systems has become a popular alternative to greatly simplify the model-building process of conventional hybrid DNN-HMM systems by representing complicated modules with a…

Computation and Language · Computer Science 2021-04-20 Kaiqi Fu , Jones Lin , Dengfeng Ke , Yanlu Xie , Jinsong Zhang , Binghuai Lin

Speech Language Models (SLMs) have recently emerged as a unified paradigm for addressing a wide range of speech-related tasks, including text-to-speech (TTS), speech enhancement (SE), and automatic speech recognition (ASR). However, the…

Sound · Computer Science 2025-12-17 Yiwen Zhao , Jiatong Shi , Jinchuan Tian , Yuxun Tang , Jiarui Hai , Jionghao Han , Shinji Watanabe

Disfluency detection is usually an intermediate step between an automatic speech recognition (ASR) system and a downstream task. By contrast, this paper aims to investigate the task of end-to-end speech recognition and disfluency removal.…

Audio and Speech Processing · Electrical Eng. & Systems 2020-09-30 Paria Jamshid Lou , Mark Johnson

Self-supervised learning (SSL) has recently achieved impressive performance on various time series tasks. The most prominent advantage of SSL is that it reduces the dependence on labeled data. Based on the pre-training and fine-tuning…

Machine Learning · Computer Science 2024-04-09 Kexin Zhang , Qingsong Wen , Chaoli Zhang , Rongyao Cai , Ming Jin , Yong Liu , James Zhang , Yuxuan Liang , Guansong Pang , Dongjin Song , Shirui Pan

In this paper, we apply Semi-Supervised Learning (SSL) along with Data Augmentation (DA) for improving the accuracy of End-to-End ASR. We focus on the consistency regularization principle, which has been successfully applied to image…

Audio and Speech Processing · Electrical Eng. & Systems 2020-07-29 Felix Weninger , Franco Mana , Roberto Gemello , Jesús Andrés-Ferrer , Puming Zhan

Performance in Speech Emotion Recognition (SER) on a single language has increased greatly in the last few years thanks to the use of deep learning techniques. However, cross-lingual SER remains a challenge in real-world applications due to…

Self-supervised learning (SSL) has great potential for molecular representation learning given the complexity of molecular graphs, the large amounts of unlabelled data available, the considerable cost of obtaining labels experimentally, and…

Machine Learning · Computer Science 2023-11-30 Yuankai Luo , Lei Shi , Veronika Thost

Aggregating multiple sources of weak supervision (WS) can ease the data-labeling bottleneck prevalent in many machine learning applications, by replacing the tedious manual collection of ground truth labels. Current state of the art…

Machine Learning · Computer Science 2021-12-01 Salva Rühling Cachay , Benedikt Boecking , Artur Dubrawski

One of the main challenges for end-to-end speech translation is data scarcity. We leverage pseudo-labels generated from unlabeled audio by a cascade and an end-to-end speech translation model. This provides 8.3 and 5.7 BLEU gains over a…

Computation and Language · Computer Science 2020-10-14 Juan Pino , Qiantong Xu , Xutai Ma , Mohammad Javad Dousti , Yun Tang

Recent years have witnessed great strides in self-supervised learning (SSL) on the speech processing. The SSL model is normally pre-trained on a great variety of unlabelled data and a large model size is preferred to increase the modeling…

Audio and Speech Processing · Electrical Eng. & Systems 2025-05-08 Yujin Wang , Changli Tang , Ziyang Ma , Zhisheng Zheng , Xie Chen , Wei-Qiang Zhang

Prior work on Sign Language Translation has shown that having a mid-level sign gloss representation (effectively recognizing the individual signs) improves the translation performance drastically. In fact, the current state-of-the-art in…

Computer Vision and Pattern Recognition · Computer Science 2020-04-02 Necati Cihan Camgoz , Oscar Koller , Simon Hadfield , Richard Bowden

In recent years, self-supervised learning (SSL) frameworks have been extensively applied to sensor-based Human Activity Recognition (HAR) in order to learn deep representations without data annotations. While SSL frameworks reach…

Machine Learning · Computer Science 2023-08-01 Bulat Khaertdinov , Stylianos Asteriadis

Self-supervised learning (SSL) has emerged as a promising paradigm in medical imaging, addressing the chronic challenge of limited labeled data in healthcare settings. While SSL has shown impressive results, existing studies in the medical…

Computer Vision and Pattern Recognition · Computer Science 2025-07-29 Valay Bundele , Karahan Sarıtaş , Bora Kargi , Oğuz Ata Çal , Kıvanç Tezören , Zohreh Ghaderi , Hendrik Lensch

Recently, self-supervised learning (SSL) has achieved tremendous success in learning image representation. Despite the empirical success, most self-supervised learning methods are rather "inefficient" learners, typically taking hundreds of…

Computer Vision and Pattern Recognition · Computer Science 2023-04-11 Shengbang Tong , Yubei Chen , Yi Ma , Yann Lecun

Self-training (ST) and self-supervised learning (SSL) methods have demonstrated strong improvements in automatic speech recognition (ASR). In spite of these advances, to the best of our knowledge, there is no analysis of how the composition…

Machine Learning · Computer Science 2023-03-03 Dan Berrebbi , Ronan Collobert , Navdeep Jaitly , Tatiana Likhomanenko

Self-supervised learning (SSL) models like Wav2Vec2, HuBERT, and WavLM have been widely used in speech processing. These transformer-based models consist of multiple layers, each capturing different levels of representation. While prior…

Audio and Speech Processing · Electrical Eng. & Systems 2025-08-13 Xinyu Liang , Fredrik Cumlin , Victor Ungureanu , Chandan K. A. Reddy , Christian Schuldt , Saikat Chatterjee

Deep models trained in supervised mode have achieved remarkable success on a variety of tasks. When labeled samples are limited, self-supervised learning (SSL) is emerging as a new paradigm for making use of large amounts of unlabeled…

Machine Learning · Computer Science 2022-04-26 Yaochen Xie , Zhao Xu , Jingtun Zhang , Zhengyang Wang , Shuiwang Ji

Semi-supervised learning (SSL) methods effectively leverage unlabeled data to improve model generalization. However, SSL models often underperform in open-set scenarios, where unlabeled data contain outliers from novel categories that do…

Computer Vision and Pattern Recognition · Computer Science 2023-11-20 Yue Fan , Anna Kukleva , Dengxin Dai , Bernt Schiele