English
Related papers

Related papers: Self-supervised Fine-tuning for Improved Content R…

200 papers

Self-supervised learning can significantly improve the performance of downstream tasks, however, the dimensions of learned representations normally lack explicit physical meanings. In this work, we propose a novel self-supervised approach…

Audio and Speech Processing · Electrical Eng. & Systems 2022-01-19 Yifan Sun , Xihong Wu

Existing speaker diarization systems typically rely on large amounts of manually annotated data, which is labor-intensive and difficult to obtain, especially in real-world scenarios. Additionally, language-specific constraints in these…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-13 Phat Lam , Lam Pham , Truong Nguyen , Dat Ngo , Thinh Pham , Tin Nguyen , Loi Khanh Nguyen , Alexander Schindler

In this paper, we propose a novel technique for direct recognition of multiple speech streams given the single channel of mixed speech, without first separating them. Our technique is based on permutation invariant training (PIT) for…

Sound · Computer Science 2018-12-06 Dong Yu , Xuankai Chang , Yanmin Qian

In this study, we propose a new spectral clustering framework that can auto-tune the parameters of the clustering algorithm in the context of speaker diarization. The proposed framework uses normalized maximum eigengap (NME) values to…

Audio and Speech Processing · Electrical Eng. & Systems 2020-06-29 Tae Jin Park , Kyu J. Han , Manoj Kumar , Shrikanth Narayanan

Self-supervised learning (SSL), which utilizes the input data itself for representation learning, has achieved state-of-the-art results for various downstream speech tasks. However, most of the previous studies focused on offline…

Audio and Speech Processing · Electrical Eng. & Systems 2022-11-11 Zili Huang , Zhuo Chen , Naoyuki Kanda , Jian Wu , Yiming Wang , Jinyu Li , Takuya Yoshioka , Xiaofei Wang , Peidong Wang

In this paper, we propose a novel algorithm for speaker diarization using metric learning for graph based clustering. The graph clustering algorithms use an adjacency matrix consisting of similarity scores. These scores are computed between…

Audio and Speech Processing · Electrical Eng. & Systems 2021-09-15 Prachi Singh , Sriram Ganapathy

Point cloud analysis without pose priors is very challenging in real applications, as the orientations of point clouds are often unknown. In this paper, we propose a brand new point-set learning framework PRIN, namely, Point-wise Rotation…

Computer Vision and Pattern Recognition · Computer Science 2021-11-23 Yang You , Yujing Lou , Ruoxi Shi , Qi Liu , Yu-Wing Tai , Lizhuang Ma , Weiming Wang , Cewu Lu

Most state-of-the-art Deep Learning (DL) approaches for speaker recognition work on a short utterance level. Given the speech signal, these algorithms extract a sequence of speaker embeddings from short segments and those are averaged to…

Sound · Computer Science 2019-07-03 Miquel India , Pooyan Safari , Javier Hernando

Image clustering is an important and open-challenging task in computer vision. Although many methods have been proposed to solve the image clustering task, they only explore images and uncover clusters according to the image features, thus…

Computer Vision and Pattern Recognition · Computer Science 2023-04-11 Shaotian Cai , Liping Qiu , Xiaojun Chen , Qin Zhang , Longteng Chen

Unsupervised learning has always been appealing to machine learning researchers and practitioners, allowing them to avoid an expensive and complicated process of labeling the data. However, unsupervised learning of complex data is…

Computer Vision and Pattern Recognition · Computer Science 2020-11-10 Evgenii Zheltonozhskii , Chaim Baskin , Alex M. Bronstein , Avi Mendelson

This paper presents an improved deep embedding learning method based on convolutional neural network (CNN) for text-independent speaker verification. Two improvements are proposed for x-vector embedding learning: (1) Multi-scale convolution…

Audio and Speech Processing · Electrical Eng. & Systems 2020-01-15 Bin Gu , Wu Guo

Model pruning in transformer-based language models, traditionally viewed as a means of achieving computational savings, can enhance the model's reasoning capabilities. In this work, we uncover a surprising phenomenon: the selective pruning…

Computation and Language · Computer Science 2025-06-10 Hieu Trung Nguyen , Bao Nguyen , Viet Anh Nguyen

Self-supervised pre-trained speech models have strongly improved speech recognition, yet they are still sensitive to domain shifts and accented or atypical speech. Many of these models rely on quantisation or clustering to learn discrete…

Audio and Speech Processing · Electrical Eng. & Systems 2025-02-06 Jakob Poncelet , Hugo Van hamme

The most common approach to speaker diarization is clustering of speaker embeddings. However, the clustering-based approach has a number of problems; i.e., (i) it is not optimized to minimize diarization errors directly, (ii) it cannot…

Audio and Speech Processing · Electrical Eng. & Systems 2020-03-09 Yusuke Fujita , Shinji Watanabe , Shota Horiguchi , Yawen Xue , Kenji Nagamatsu

We study permutation invariant training (PIT), which targets at the permutation ambiguity problem for speaker independent source separation models. We extend two state-of-the-art PIT strategies. First, we look at the two-stage speaker…

Sound · Computer Science 2021-04-06 Xiaoyu Liu , Jordi Pons

We propose a self-supervised learning method using multiple sampling strategies to obtain general-purpose audio representation. Multiple sampling strategies are used in the proposed method to construct contrastive losses from different…

Sound · Computer Science 2025-05-27 Ibuki Kuroyanagi , Tatsuya Komatsu

The cross-domain performance of automatic speech recognition (ASR) could be severely hampered due to the mismatch between training and testing distributions. Since the target domain usually lacks labeled data, and domain shifts exist at…

Audio and Speech Processing · Electrical Eng. & Systems 2023-08-01 Han Zhu , Gaofeng Cheng , Jindong Wang , Wenxin Hou , Pengyuan Zhang , Yonghong Yan

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 achieved remarkable performance in pretraining the models that can be further used in downstream tasks via fine-tuning. However, these self-supervised models may not capture meaningful semantic information…

Computer Vision and Pattern Recognition · Computer Science 2022-08-02 Haolin Pan , Yong Guo , Qinyi Deng , Haomin Yang , Yiqun Chen , Jian Chen

Current state-of-the-art automatic speech recognition systems are trained to work in specific `domains', defined based on factors like application, sampling rate and codec. When such recognizers are used in conditions that do not match the…