English
Related papers

Related papers: Disentangled representation learning for multiling…

200 papers

Accurately detecting dysfluencies in spoken language can help to improve the performance of automatic speech and language processing components and support the development of more inclusive speech and language technologies. Inspired by the…

The success of deep learning in speaker recognition relies heavily on the use of large datasets. However, the data-hungry nature of deep learning methods has already being questioned on account the ethical, privacy, and legal concerns that…

Existing speaker verification (SV) systems often suffer from performance degradation if there is any language mismatch between model training, speaker enrollment, and test. A major cause of this degradation is that most existing SV methods…

Sound · Computer Science 2017-06-27 Lantian Li , Dong Wang , Askar Rozi , Thomas Fang Zheng

Discrete audio representations are gaining traction in speech modeling due to their interpretability and compatibility with large language models, but are not always optimized for noisy or real-world environments. Building on existing works…

Computation and Language · Computer Science 2025-10-30 Shreyas Gopal , Ashutosh Anshul , Haoyang Li , Yue Heng Yeo , Hexin Liu , Eng Siong Chng

Deep neural networks are susceptible to learn biased models with entangled feature representations, which may lead to subpar performances on various downstream tasks. This is particularly true for under-represented classes, where a lack of…

Computer Vision and Pattern Recognition · Computer Science 2021-11-02 Sanghyeok Chu , Dongwan Kim , Bohyung Han

Contrary to i-vectors, speaker embeddings such as x-vectors are incapable of leveraging unlabelled utterances, due to the classification loss over training speakers. In this paper, we explore an alternative training strategy to enable the…

Computer Vision and Pattern Recognition · Computer Science 2019-04-24 Themos Stafylakis , Johan Rohdin , Oldrich Plchot , Petr Mizera , Lukas Burget

The presence of multiple talkers in the surrounding environment poses a difficult challenge for real-time speech communication systems considering the constraints on network size and complexity. In this paper, we present Personalized…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-09 Ritwik Giri , Shrikant Venkataramani , Jean-Marc Valin , Umut Isik , Arvindh Krishnaswamy

Image classification models tend to make decisions based on peripheral attributes of data items that have strong correlation with a target variable (i.e., dataset bias). These biased models suffer from the poor generalization capability…

Machine Learning · Computer Science 2021-10-26 Jungsoo Lee , Eungyeup Kim , Juyoung Lee , Jihyeon Lee , Jaegul Choo

Negative-free contrastive learning methods have attracted a lot of attention with simplicity and impressive performances for large-scale pretraining. However, its disentanglement property remains unexplored. In this paper, we examine…

Machine Learning · Computer Science 2022-10-18 Jinkun Cao , Ruiqian Nai , Qing Yang , Jialei Huang , Yang Gao

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

This paper aims to synthesize the target speaker's speech with desired speaking style and emotion by transferring the style and emotion from reference speech recorded by other speakers. We address this challenging problem with a two-stage…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-15 Xinfa Zhu , Yi Lei , Kun Song , Yongmao Zhang , Tao Li , Lei Xie

Self-supervised learning (SSL) is a long-standing goal for speech processing, since it utilizes large-scale unlabeled data and avoids extensive human labeling. Recent years witness great successes in applying self-supervised learning in…

Computation and Language · Computer Science 2021-10-13 Sanyuan Chen , Yu Wu , Chengyi Wang , Zhengyang Chen , Zhuo Chen , Shujie Liu , Jian Wu , Yao Qian , Furu Wei , Jinyu Li , Xiangzhan Yu

In this paper, we present the system submission for the VoxCeleb Speaker Recognition Challenge 2020 (VoxSRC-20) by the DKU-DukeECE team. For track 1, we explore various kinds of state-of-the-art front-end extractors with different pooling…

Audio and Speech Processing · Electrical Eng. & Systems 2020-10-27 Weiqing Wang , Danwei Cai , Xiaoyi Qin , Ming Li

Previous audio-visual speech separation methods use the synchronization of the speaker's facial movement and speech in the video to supervise the speech separation in a self-supervised way. In this paper, we propose a model to solve the…

Audio and Speech Processing · Electrical Eng. & Systems 2023-11-06 Jiasong Wu , Xuan Li , Taotao Li , Fanman Meng , Youyong Kong , Guanyu Yang , Lotfi Senhadji , Huazhong Shu

This paper proposes a unified deep speaker embedding framework for modeling speech data with different sampling rates. Considering the narrowband spectrogram as a sub-image of the wideband spectrogram, we tackle the joint modeling problem…

Audio and Speech Processing · Electrical Eng. & Systems 2020-12-02 Weicheng Cai , Ming Li

We make two theoretical contributions to disentanglement learning by (a) defining precise semantics of disentangled representations, and (b) establishing robust metrics for evaluation. First, we characterize the concept "disentangled…

Machine Learning · Computer Science 2021-03-22 Kien Do , Truyen Tran

Disentangled representation learning has been proposed as an approach to learning general representations even in the absence of, or with limited, supervision. A good general representation can be fine-tuned for new target tasks using…

Computer Vision and Pattern Recognition · Computer Science 2022-08-01 Xiao Liu , Pedro Sanchez , Spyridon Thermos , Alison Q. O'Neil , Sotirios A. Tsaftaris

Disentangled representation has been widely explored in many fields due to its maximal compactness, interpretability and versatility. Recommendation system also needs disentanglement to make representation more explainable and general for…

Social and Information Networks · Computer Science 2020-10-27 Weiguang Chen , Wenjun Jiang , Xueqi Li , Kenli Li , Albert Zomaya , Guojun Wang

Multilingual self-supervised speech representation models have greatly enhanced the speech recognition performance for low-resource languages, and the compression of these huge models has also become a crucial prerequisite for their…

Computation and Language · Computer Science 2023-06-05 Haoyu Wang , Siyuan Wang , Wei-Qiang Zhang , Jinfeng Bai

More than half of the 7,000 languages in the world are in imminent danger of going extinct. Traditional methods of documenting language proceed by collecting audio data followed by manual annotation by trained linguists at different levels…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-06 Sameer Khurana , Antoine Laurent , James Glass