English
Related papers

Related papers: Simultaneous or Sequential Training? How Speech Re…

200 papers

In this paper, we describe our submissions to the ZeroSpeech 2021 Challenge and SUPERB benchmark. Our submissions are based on the recently proposed FaST-VGS model, which is a Transformer-based model that learns to associate raw speech…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-03 Puyuan Peng , David Harwath

This paper proposes a voice conversion (VC) method based on a sequence-to-sequence (S2S) learning framework, which enables simultaneous conversion of the voice characteristics, pitch contour, and duration of input speech. We previously…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-10 Hirokazu Kameoka , Wen-Chin Huang , Kou Tanaka , Takuhiro Kaneko , Nobukatsu Hojo , Tomoki Toda

Multilingual end-to-end(E2E) models have shown a great potential in the expansion of the language coverage in the realm of automatic speech recognition(ASR). In this paper, we aim to enhance the multilingual ASR performance in two ways,…

Computation and Language · Computer Science 2021-10-18 Rimita Lahiri , Kenichi Kumatani , Eric Sun , Yao Qian

Advances in deep learning are re-defining how visual data is processed and understand by the machines. Vision Transformers (ViTs) have recently demonstrated prominent performance in computer vision related tasks. However, their performance…

Simultaneous speech translation (SST) outputs translations in parallel with streaming speech input, balancing translation quality and latency. While large language models (LLMs) have been extended to handle the speech modality, streaming…

Computation and Language · Computer Science 2025-04-23 Keqi Deng , Wenxi Chen , Xie Chen , Philip C. Woodland

Self-Supervised Learning (SSL) has gained traction for its ability to learn rich representations with low labeling costs, applicable across diverse downstream tasks. However, assessing the downstream-task performance remains challenging due…

Sound · Computer Science 2025-10-07 Takashi Maekaku , Keita Goto , Jinchuan Tian , Yusuke Shinohara , Shinji Watanabe

Self-Supervised Learning (SSL) models have been successfully applied in various deep learning-based speech tasks, particularly those with a limited amount of data. However, the quality of SSL representations depends highly on the…

Computation and Language · Computer Science 2022-04-20 Dan Berrebbi , Jiatong Shi , Brian Yan , Osbel Lopez-Francisco , Jonathan D. Amith , Shinji Watanabe

Visual Speech Recognition (VSR) differs from the common perception tasks as it requires deeper reasoning over the video sequence, even by human experts. Despite the recent advances in VSR, current approaches rely on labeled data to fully…

Self-supervised models have revolutionized speech processing, achieving new levels of performance in a wide variety of tasks with limited resources. However, the inner workings of these models are still opaque. In this paper, we aim to…

Sound · Computer Science 2024-06-25 Yassine El Kheir , Ahmed Ali , Shammur Absar Chowdhury

Self-supervised learning (SSL) approaches have shown promising capabilities in learning the representation from unlabeled data. Amongst them, momentum-based frameworks have attracted significant attention. Despite being a great success,…

Computer Vision and Pattern Recognition · Computer Science 2022-11-22 Trung X. Pham , Axi Niu , Zhang Kang , Sultan Rizky Madjid , Ji Woo Hong , Daehyeok Kim , Joshua Tian Jin Tee , Chang D. Yoo

Self-Supervised Learning (SSL) for Vision Transformers (ViTs) has recently demonstrated considerable potential as a pre-training strategy for a variety of computer vision tasks, including image classification and segmentation, both in…

Computer Vision and Pattern Recognition · Computer Science 2025-09-22 Yannis Kaltampanidis , Alexandros Doumanoglou , Dimitrios Zarpalas

Self-supervised learning (SSL) has grown in interest within the speech processing community, since it produces representations that are useful for many downstream tasks. SSL uses global and contextual methods to produce robust…

Audio and Speech Processing · Electrical Eng. & Systems 2024-11-08 Subrina Sultana , Donald S. Williamson

Self-supervised learning (SSL) has transformed speech processing, yet its reliance on massive pre-training datasets remains a bottleneck. While robustness is often attributed to scale and diversity, the role of the data distribution is less…

Sound · Computer Science 2026-04-24 Ryan Whetten , Titouan Parcollet , Marco Dinarelli , Yannick Estève

Voice conversion (VC) systems are widely used for several applications, from speaker anonymisation to personalised speech synthesis. Supervised approaches learn a mapping between different speakers using parallel data, which is expensive to…

End-to-end speech-to-speech translation (S2ST) without relying on intermediate text representations is a rapidly emerging frontier of research. Recent works have demonstrated that the performance of such direct S2ST systems is approaching…

Computation and Language · Computer Science 2022-06-29 Ye Jia , Yifan Ding , Ankur Bapna , Colin Cherry , Yu Zhang , Alexis Conneau , Nobuyuki Morioka

Automatic speech recognition (ASR) has progressed significantly in recent years due to the emergence of large-scale datasets and the self-supervised learning (SSL) paradigm. However, as its counterpart problem in the singing domain, the…

Audio and Speech Processing · Electrical Eng. & Systems 2022-10-18 Longshen Ou , Xiangming Gu , Ye Wang

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…

Audio and Speech Processing · Electrical Eng. & Systems 2021-03-19 Abhinav Shukla , Stavros Petridis , Maja Pantic

Self-supervised learning (SSL) has significantly advanced acoustic representation learning. However, most existing models are optimised for either speech or audio event understanding, resulting in a persistent gap between these two domains.…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-05 Xiaoyu Yang , Yifan Yang , Zengrui Jin , Ziyun Cui , Wen Wu , Baoxiang Li , Chao Zhang , Phil Woodland

The ICML Expressive Vocalizations (ExVo) Multi-task challenge 2022, focuses on understanding the emotional facets of the non-linguistic vocalizations (vocal bursts (VB)). The objective of this challenge is to predict emotional intensities…

Sound · Computer Science 2022-07-26 Tilak Purohit , Imen Ben Mahmoud , Bogdan Vlasenko , Mathew Magimai. -Doss

The inherent synchronization between a speaker's lip movements, voice, and the underlying linguistic content offers a rich source of information for improving speech processing tasks, especially in challenging conditions where traditional…

Sound · Computer Science 2025-05-16 Detao Bai , Zhiheng Ma , Xihan Wei , Liefeng Bo