English
Related papers

Related papers: A Multi-Discriminator CycleGAN for Unsupervised No…

200 papers

Current speaker recognition technology provides great performance with the x-vector approach. However, performance decreases when the evaluation domain is different from the training domain, an issue usually addressed with domain adaptation…

Audio and Speech Processing · Electrical Eng. & Systems 2019-10-29 Phani Sankar Nidadavolu , Saurabh Kataria , Jesús Villalba , Najim Dehak

Training a model to perform a task typically requires a large amount of data from the domains in which the task will be applied. However, it is often the case that data are abundant in some domains but scarce in others. Domain adaptation…

Machine Learning · Computer Science 2019-01-25 Ehsan Hosseini-Asl , Yingbo Zhou , Caiming Xiong , Richard Socher

In general, the performance of automatic speech recognition (ASR) systems is significantly degraded due to the mismatch between training and test environments. Recently, a deep-learning-based image-to-image translation technique to…

Audio and Speech Processing · Electrical Eng. & Systems 2019-04-15 Jong-Hyeon Park , Myungwoo Oh , Hyung-Min Park

With the increase in the availability of speech from varied domains, it is imperative to use such out-of-domain data to improve existing speech systems. Domain adaptation is a prominent pre-processing approach for this. We investigate it…

Audio and Speech Processing · Electrical Eng. & Systems 2021-04-06 Saurabh Kataria , Jesús Villalba , Piotr Żelasko , Laureano Moro-Velázquez , Najim Dehak

Although voice conversion (VC) algorithms have achieved remarkable success along with the development of machine learning, superior performance is still difficult to achieve when using nonparallel data. In this paper, we propose using a…

Audio and Speech Processing · Electrical Eng. & Systems 2018-04-03 Fuming Fang , Junichi Yamagishi , Isao Echizen , Jaime Lorenzo-Trueba

Automatic speech recognition is a difficult problem in pattern recognition because several sources of variability exist in the speech input like the channel variations, the input might be clean or noisy, the speakers may have different…

Audio and Speech Processing · Electrical Eng. & Systems 2021-08-09 Rupam Ojha , C Chandra Sekhar

In classification tasks, the classification accuracy diminishes when the data is gathered in different domains. To address this problem, in this paper, we investigate several adversarial models for domain adaptation (DA) and their effect on…

Sound · Computer Science 2023-09-08 Stanisław Kacprzak , Konrad Kowalczyk

Neural audio super-resolution models are typically trained on low- and high-resolution audio signal pairs. Although these methods achieve highly accurate super-resolution if the acoustic characteristics of the input data are similar to…

Audio and Speech Processing · Electrical Eng. & Systems 2023-02-28 Reo Yoneyama , Ryuichi Yamamoto , Kentaro Tachibana

This paper presents our latest investigations on improving automatic speech recognition for noisy speech via speech enhancement. We propose a novel method named Multi-discriminators CycleGAN to reduce noise of input speech and therefore…

Computation and Language · Computer Science 2021-12-14 Chia-Yu Li , Ngoc Thang Vu

Recently, convolution-augmented transformer (Conformer) has achieved promising performance in automatic speech recognition (ASR) and time-domain speech enhancement (SE), as it can capture both local and global dependencies in the speech…

Sound · Computer Science 2024-05-07 Ruizhe Cao , Sherif Abdulatif , Bin Yang

In a recent paper, we have presented a generative adversarial network (GAN)-based model for unconditional generation of the mel-spectrograms of singing voices. As the generator of the model is designed to take a variable-length sequence of…

Audio and Speech Processing · Electrical Eng. & Systems 2021-05-13 Jen-Yu Liu , Yu-Hua Chen , Yin-Cheng Yeh , Yi-Hsuan Yang

We investigated an enhancement and a domain adaptation approach to make speaker verification systems robust to perturbations of far-field speech. In the enhancement approach, using paired (parallel) reverberant-clean speech, we trained a…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-19 Phani Sankar Nidadavolu , Saurabh Kataria , Paola García-Perera , Jesús Villalba , Najim Dehak

For the lack of adequate paired noisy-clean speech corpus in many real scenarios, non-parallel training is a promising task for DNN-based speech enhancement methods. However, because of the severe mismatch between input and target speeches,…

Sound · Computer Science 2022-02-15 Guochen Yu , Andong Li , Yutian Wang , Yinuo Guo , Hui Wang , Chengshi Zheng

We introduce a novel method for emotion conversion in speech that does not require parallel training data. Our approach loosely relies on a cycle-GAN schema to minimize the reconstruction error from converting back and forth between emotion…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-12 Ravi Shankar , Jacob Sager , Archana Venkataraman

Transferring knowledge across different datasets is an important approach to successfully train deep models with a small-scale target dataset or when few labeled instances are available. In this paper, we aim at developing a model that can…

Computer Vision and Pattern Recognition · Computer Science 2018-12-04 Eman T. Hassan , Xin Chen , David Crandall

Domain mismatch between training and testing can lead to significant degradation in performance in many machine learning scenarios. Unfortunately, this is not a rare situation for automatic speech recognition deployments in real-world…

Computation and Language · Computer Science 2017-09-25 Wei-Ning Hsu , Yu Zhang , James Glass

Non-parallel training is a difficult but essential task for DNN-based speech enhancement methods, for the lack of adequate noisy and paired clean speech corpus in many real scenarios. In this paper, we propose a novel adaptive…

Sound · Computer Science 2021-09-15 Guochen Yu , Yutian Wang , Chengshi Zheng , Hui Wang , Qin Zhang

Speaking rate refers to the average number of phonemes within some unit time, while the rhythmic patterns refer to duration distributions for realizations of different phonemes within different phonetic structures. Both are key components…

Sound · Computer Science 2018-08-10 Cheng-chieh Yeh , Po-chun Hsu , Ju-chieh Chou , Hung-yi Lee , Lin-shan Lee

Recent advancement in Generative Adversarial Networks in speech synthesis domain[3],[2] have shown, that it's possible to train GANs [8] in a reliable manner for high quality coherent waveform generation from mel-spectograms. We propose…

Audio and Speech Processing · Electrical Eng. & Systems 2020-06-16 Luka Chkhetiani , Levan Bejanidze

Unsupervised domain adaptation of speech signal aims at adapting a well-trained source-domain acoustic model to the unlabeled data from target domain. This can be achieved by adversarial training of deep neural network (DNN) acoustic models…

Computation and Language · Computer Science 2019-05-01 Zhong Meng , Zhuo Chen , Vadim Mazalov , Jinyu Li , Yifan Gong
‹ Prev 1 2 3 10 Next ›