English
Related papers

Related papers: Robust Speech Representation Learning via Flow-bas…

200 papers

When working with textual data, a natural application of disentangled representations is fair classification where the goal is to make predictions without being biased (or influenced) by sensitive attributes that may be present in the data…

Computation and Language · Computer Science 2022-10-10 Pierre Colombo , Guillaume Staerman , Nathan Noiry , Pablo Piantanida

With recent research advancements, deep learning models are becoming attractive and powerful choices for speech enhancement in real-time applications. While state-of-the-art models can achieve outstanding results in terms of speech quality…

Audio and Speech Processing · Electrical Eng. & Systems 2021-05-20 Sebastian Braun , Hannes Gamper , Chandan K. A. Reddy , Ivan Tashev

This paper proposes a deep speech enhancement method which exploits the high potential of residual connections in a wide neural network architecture, a topology known as Wide Residual Network. This is supported on single dimensional…

Sound · Computer Science 2019-01-04 Dayana Ribas , Jorge Llombart , Antonio Miguel , Luis Vicente

In this paper, we explore various approaches for semi supervised learning in an end to end automatic speech recognition (ASR) framework. The first step in our approach involves training a seed model on the limited amount of labelled data.…

Audio and Speech Processing · Electrical Eng. & Systems 2019-08-15 Subhadeep Dey , Petr Motlicek , Trung Bui , Franck Dernoncourt

Large speech emotion recognition datasets are hard to obtain, and small datasets may contain biases. Deep-net-based classifiers, in turn, are prone to exploit those biases and find shortcuts such as speaker characteristics. These shortcuts…

Machine Learning · Computer Science 2022-11-08 Itai Gat , Hagai Aronowitz , Weizhong Zhu , Edmilson Morais , Ron Hoory

The cross-entropy loss commonly used in deep learning is closely related to the defining properties of optimal representations, but does not enforce some of the key properties. We show that this can be solved by adding a regularization…

Machine Learning · Statistics 2017-02-14 Alessandro Achille , Stefano Soatto

This paper proposes the target speaker enhancement based speaker verification network (TASE-SVNet), an all neural model that couples target speaker enhancement and speaker embedding extraction for robust speaker verification (SV).…

Audio and Speech Processing · Electrical Eng. & Systems 2021-03-17 Chunlei Zhang , Meng Yu , Chao Weng , Dong Yu

Machine translation models have discrete vocabularies and commonly use subword segmentation techniques to achieve an 'open vocabulary.' This approach relies on consistent and correct underlying unicode sequences, and makes models…

Computation and Language · Computer Science 2021-12-13 Elizabeth Salesky , David Etter , Matt Post

Deep learning based on artificial neural networks is a powerful machine learning method that, in the last few years, has been successfully used to realize tasks, e.g., image classification, speech recognition, translation of languages,…

Information Theory · Computer Science 2019-06-18 Alessio Zappone , Marco Di Renzo , Mérouane Debbah , Thanh Tu Lam , Xuewen Qian

Robustness is essential for deep neural networks, especially in security-sensitive applications. To this end, randomized smoothing provides theoretical guarantees for certifying robustness against adversarial perturbations. Recently,…

Computer Vision and Pattern Recognition · Computer Science 2025-07-02 Jiachen Lei , Julius Berner , Jiongxiao Wang , Zhongzhu Chen , Zhongjia Ba , Kui Ren , Jun Zhu , Anima Anandkumar

In recent years, various flow-based generative models have been proposed to generate high-fidelity waveforms in real-time. However, these models require either a well-trained teacher network or a number of flow steps making them…

Sound · Computer Science 2020-07-06 Hyeongju Kim , Hyeonseung Lee , Woo Hyun Kang , Sung Jun Cheon , Byoung Jin Choi , Nam Soo Kim

We introduce a training method for both better word representation and performance, which we call GROVER (Gradual Rumination On the Vector with maskERs). The method is to gradually and iteratively add random noises to word embeddings while…

Machine Learning · Computer Science 2019-11-12 Hwiyeol Jo , Byoung-Tak Zhang

Conventional deep neural network (DNN)-based speech enhancement (SE) approaches aim to minimize the mean square error (MSE) between enhanced speech and clean reference. The MSE-optimized model may not directly improve the performance of an…

Audio and Speech Processing · Electrical Eng. & Systems 2018-11-13 Yih-Liang Shen , Chao-Yuan Huang , Syu-Siang Wang , Yu Tsao , Hsin-Min Wang , Tai-Shih Chi

Deep speaker embedding represents the state-of-the-art technique for speaker recognition. A key problem with this approach is that the resulting deep speaker vectors tend to be irregularly distributed. In previous research, we proposed a…

Sound · Computer Science 2020-11-02 Yunqi Cai , Lantian Li , Dong Wang , Andrew Abel

This paper proposes SEFGAN, a Deep Neural Network (DNN) combining maximum likelihood training and Generative Adversarial Networks (GANs) for efficient speech enhancement (SE). For this, a DNN is trained to synthesize the enhanced speech…

Audio and Speech Processing · Electrical Eng. & Systems 2023-12-05 Martin Strauss , Nicola Pia , Nagashree K. S. Rao , Bernd Edler

Supervised machine learning models often associate irrelevant nuisance factors with the prediction target, which hurts generalization. We propose a framework for training robust neural networks that induces invariance to nuisances through…

Machine Learning · Computer Science 2019-12-03 Ayush Jaiswal , Rob Brekelmans , Daniel Moyer , Greg Ver Steeg , Wael AbdAlmageed , Premkumar Natarajan

Consistency training regularizes a model by enforcing predictions of original and perturbed inputs to be similar. Previous studies have proposed various augmentation methods for the perturbation but are limited in that they are agnostic to…

Computation and Language · Computer Science 2022-04-29 Jungsoo Park , Gyuwan Kim , Jaewoo Kang

Enhancing speech signal quality in adverse acoustic environments is a persistent challenge in speech processing. Existing deep learning based enhancement methods often struggle to effectively remove background noise and reverberation in…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-19 Heming Wang , Meng Yu , Hao Zhang , Chunlei Zhang , Zhongweiyang Xu , Muqiao Yang , Yixuan Zhang , Dong Yu

Speaker modeling is essential for many related tasks, such as speaker recognition and speaker diarization. The dominant modeling approach is fixed-dimensional vector representation, i.e., speaker embedding. This paper introduces a research…

Word embedding, a high-dimensional (HD) numerical representation of words generated by machine learning models, has been used for different natural language processing tasks, e.g., translation between two languages. Recently, there has been…

Human-Computer Interaction · Computer Science 2024-03-26 Haoyu Li , Junpeng Wang , Yan Zheng , Liang Wang , Wei Zhang , Han-Wei Shen