English
Related papers

Related papers: On Training Targets and Activation Functions for D…

200 papers

In this work, we observe a counterintuitive phenomenon in self-supervised learning (SSL): longer training may impair the performance of dense prediction tasks (e.g., semantic segmentation). We refer to this phenomenon as Self-supervised…

Computer Vision and Pattern Recognition · Computer Science 2025-10-21 Siran Dai , Qianqian Xu , Peisong Wen , Yang Liu , Qingming Huang

Single channel target speaker separation (TSS) aims at extracting a speaker's voice from a mixture of multiple talkers given an enrollment utterance of that speaker. A typical deep learning TSS framework consists of an upstream model that…

Sound · Computer Science 2022-10-27 Xiaoyu Liu , Xu Li , Joan Serrà

Semantic Role Labeling (SRL) is believed to be a crucial step towards natural language understanding and has been widely studied. Recent years, end-to-end SRL with recurrent neural networks (RNN) has gained increasing attention. However, it…

Computation and Language · Computer Science 2017-12-06 Zhixing Tan , Mingxuan Wang , Jun Xie , Yidong Chen , Xiaodong Shi

Achieving efficient and robust multi-channel data learning is a challenging task in data science. By exploiting low-rankness in the transformed domain, i.e., transformed low-rankness, tensor Singular Value Decomposition (t-SVD) has achieved…

Machine Learning · Computer Science 2023-12-21 Andong Wang , Chao Li , Mingyuan Bai , Zhong Jin , Guoxu Zhou , Qibin Zhao

The performance of deep learning models depends significantly on their capacity to encode input features efficiently and decode them into meaningful outputs. Better input and output representation has the potential to boost models'…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-10 Ahmed Adel Attia , Yashish M. Siriwardena , Carol Espy-Wilson

Learned feature representations and sub-phoneme posteriors from Deep Neural Networks (DNNs) have been used separately to produce significant performance gains for speaker and language recognition tasks. In this work we show how these gains…

Computation and Language · Computer Science 2015-04-06 Fred Richardson , Douglas Reynolds , Najim Dehak

We propose a novel adversarial multi-task learning scheme, aiming at actively curtailing the inter-talker feature variability while maximizing its senone discriminability so as to enhance the performance of a deep neural network (DNN) based…

Audio and Speech Processing · Electrical Eng. & Systems 2019-05-01 Zhong Meng , Jinyu Li , Zhuo Chen , Yong Zhao , Vadim Mazalov , Yifan Gong , Biing-Hwang , Juang

Self-supervised learning (SSL) has drawn an increased attention in the field of speech processing. Recent studies have demonstrated that contrastive learning is able to learn discriminative speaker embeddings in a self-supervised manner.…

Audio and Speech Processing · Electrical Eng. & Systems 2022-11-23 Chunlei Zhang , Dong Yu

Semantic segmentation is the task of assigning a label to each pixel in the image.In recent years, deep convolutional neural networks have been driving advances in multiple tasks related to cognition. Although, DCNNs have resulted in…

Machine Learning · Computer Science 2017-12-12 Aditya Ganeshan

In this paper, we propose a novel strategy for text-independent speaker identification system: Multi-Label Training (MLT). Instead of the commonly used one-to-one correspondence between the speech and the speaker label, we divide all the…

Audio and Speech Processing · Electrical Eng. & Systems 2024-08-19 Yuqi Xue

Motivated by the growing theoretical understanding of neural networks that employ the Rectified Linear Unit (ReLU) as their activation function, we revisit the use of ReLU activation functions for learning implicit neural representations…

Image and Video Processing · Electrical Eng. & Systems 2024-08-05 Joseph Shenouda , Yamin Zhou , Robert D. Nowak

The speech representations learned from large-scale unlabeled data have shown better generalizability than those from supervised learning and thus attract a lot of interest to be applied for various downstream tasks. In this paper, we…

Sound · Computer Science 2022-01-25 Zhengyang Chen , Sanyuan Chen , Yu Wu , Yao Qian , Chengyi Wang , Shujie Liu , Yanmin Qian , Michael Zeng

Recently, deep learning (DL)-based non-intrusive speech assessment models have attracted great attention. Many studies report that these DL-based models yield satisfactory assessment performance and good flexibility, but their performance…

Audio and Speech Processing · Electrical Eng. & Systems 2022-09-01 Ryandhimas E. Zezario , Szu-wei Fu , Fei Chen , Chiou-Shann Fuh , Hsin-Min Wang , Yu Tsao

Speaker recognition, recognizing speaker identities based on voice alone, enables important downstream applications, such as personalization and authentication. Learning speaker representations, in the context of supervised learning,…

Machine Learning · Computer Science 2022-07-13 Metehan Cekic , Ruirui Li , Zeya Chen , Yuguang Yang , Andreas Stolcke , Upamanyu Madhow

The deep learning models used for speaker verification rely heavily on large amounts of data and correct labeling. However, noisy (incorrect) labels often occur, which degrades the performance of the system. In this paper, we propose a…

Sound · Computer Science 2026-04-29 Zhihua Fang , Liang He , Hanhan Ma , Xiaochen Guo , Lin Li

Deep learning approaches are still not very common in the speaker verification field. We investigate the possibility of using deep residual convolutional neural network with spectrograms as an input features in the text-dependent speaker…

Sound · Computer Science 2017-05-31 Egor Malykh , Sergey Novoselov , Oleg Kudashev

Spoken language understanding (SLU) tasks involve mapping from speech audio signals to semantic labels. Given the complexity of such tasks, good performance might be expected to require large labeled datasets, which are difficult to collect…

Computation and Language · Computer Science 2022-07-12 Ankita Pasad , Felix Wu , Suwon Shon , Karen Livescu , Kyu J. Han

The objective of this paper is 'open-set' speaker recognition of unseen speakers, where ideal embeddings should be able to condense information into a compact utterance-level representation that has small intra-speaker and large…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-05 Joon Son Chung , Jaesung Huh , Seongkyu Mun , Minjae Lee , Hee Soo Heo , Soyeon Choe , Chiheon Ham , Sunghwan Jung , Bong-Jin Lee , Icksang Han

We propose TSELM, a novel target speaker extraction network that leverages discrete tokens and language models. TSELM utilizes multiple discretized layers from WavLM as input tokens and incorporates cross-attention mechanisms to integrate…

Sound · Computer Science 2024-09-18 Beilong Tang , Bang Zeng , Ming Li

Learning general representations of text is a fundamental problem for many natural language understanding (NLU) tasks. Previously, researchers have proposed to use language model pre-training and multi-task learning to learn robust…

Computation and Language · Computer Science 2019-08-29 Zi-Yi Dou , Keyi Yu , Antonios Anastasopoulos