English
Related papers

Related papers: Unsupervised Cross-Domain Speech-to-Speech Convers…

200 papers

Traditional speech enhancement techniques modify the magnitude of a speech in time-frequency domain, and use the phase of a noisy speech to resynthesize a time domain speech. This work proposes a complex-valued Gaussian process latent…

Sound · Computer Science 2017-01-02 Sih-Huei Chen , Yuan-Shan Lee , Jia-Ching Wang

Recent single-channel speech enhancement methods usually convert waveform to the time-frequency domain and use magnitude/complex spectrum as the optimizing target. However, both magnitude-spectrum-based methods and complex-spectrum-based…

Sound · Computer Science 2021-10-13 Wenxin Tai , Jiajia Li , Yixiang Wang , Tian Lan , Qiao Liu

We investigate the effectiveness of generative adversarial networks (GANs) for speech enhancement, in the context of improving noise robustness of automatic speech recognition (ASR) systems. Prior work demonstrates that GANs can effectively…

Sound · Computer Science 2018-11-01 Chris Donahue , Bo Li , Rohit Prabhavalkar

Voice conversion (VC) refers to transforming the speaker characteristics of an utterance without altering its linguistic contents. Many works on voice conversion require to have parallel training data that is highly expensive to acquire.…

Sound · Computer Science 2020-02-18 Shindong Lee , BongGu Ko , Keonnyeong Lee , In-Chul Yoo , Dongsuk Yook

Pre-trained Language Model (PLM) is nowadays the mainstay of Unsupervised Sentence Representation Learning (USRL). However, PLMs are sensitive to the frequency information of words from their pre-training corpora, resulting in anisotropic…

Computation and Language · Computer Science 2023-05-16 Bing Wang , Ximing Li , Zhiyao Yang , Yuanyuan Guan , Jiayin Li , Shengsheng Wang

Training models that are robust to data domain shift has gained an increasing interest both in academia and industry. Question-Answering language models, being one of the typical problem in Natural Language Processing (NLP) research, has…

Computation and Language · Computer Science 2022-06-27 Shubham Shrivastava , Kaiyue Wang

In the development of neural text-to-speech systems, model pre-training with a large amount of non-target speakers' data is a common approach. However, in terms of ultimately achieved system performance for target speaker(s), the actual…

Audio and Speech Processing · Electrical Eng. & Systems 2021-10-11 Guangyan Zhang , Yichong Leng , Daxin Tan , Ying Qin , Kaitao Song , Xu Tan , Sheng Zhao , Tan Lee

Full-duplex speech interaction, as the most natural and intuitive mode of human communication, is driving artificial intelligence toward more human-like conversational systems. Traditional cascaded speech processing pipelines suffer from…

Artificial Intelligence · Computer Science 2026-05-01 Yadong Li , Guoxin Wu , Haiping Hou , Biye Li

Large Language Model (LLM) based text-to-speech (TTS) systems have demonstrated remarkable capabilities in handling large speech datasets and generating natural speech for new speakers. However, LLM-based TTS models are not robust as the…

Recent work on speech representation models jointly pre-trained with text has demonstrated the potential of improving speech representations by encoding speech and text in a shared space. In this paper, we leverage such shared…

Computation and Language · Computer Science 2023-10-10 Chung-Ming Chien , Mingjiamei Zhang , Ju-Chieh Chou , Karen Livescu

In cross-lingual speech synthesis, the speech in various languages can be synthesized for a monoglot speaker. Normally, only the data of monoglot speakers are available for model training, thus the speaker similarity is relatively low…

Sound · Computer Science 2022-01-21 J. Yang , Lei He

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 this article we propose a novel approach for adapting speaker embeddings to new domains based on adversarial training of neural networks. We apply our embeddings to the task of text-independent speaker verification, a challenging,…

Audio and Speech Processing · Electrical Eng. & Systems 2018-11-08 Gautam Bhattacharya , Jahangir Alam , Patrick Kenny

For individuals who have experienced traumatic events such as strokes, speech may no longer be a viable means of communication. While text-to-speech (TTS) can be used as a communication aid since it generates synthetic speech, it fails to…

Sound · Computer Science 2025-11-11 Yejin Jeon , Youngjae Kim , Jihyun Lee , Hyounghun Kim , Gary Geunbae Lee

This paper tackles GAN optimization and stability issues in the context of voice conversion. First, to simplify the conversion task, we propose to use spectral envelopes as inputs. Second we propose two adversarial weight training…

Audio and Speech Processing · Electrical Eng. & Systems 2020-07-14 Rafael Ferro , Nicolas Obin , Axel Roebel

We propose an optimization-based method for reconstructing a time-domain signal from a low-dimensional spectral representation such as a mel-spectrogram. Phase reconstruction has been studied to reconstruct a time-domain signal from the…

Sound · Computer Science 2023-07-25 Yoshiki Masuyama , Natsuki Ueno , Nobutaka Ono

Recently, it has become easier to obtain speech data from various media such as the internet or YouTube, but directly utilizing them to train a neural text-to-speech (TTS) model is difficult. The proportion of clean speech is insufficient…

Audio and Speech Processing · Electrical Eng. & Systems 2021-03-05 Hanbin Bae , Jae-Sung Bae , Young-Sun Joo , Young-Ik Kim , Hoon-Young Cho

Speech distortions are a long-standing problem that degrades the performance of supervisely trained speech processing models. It is high time that we enhance the robustness of speech processing models to obtain good performance when…

Sound · Computer Science 2022-07-26 Kuan Po Huang , Yu-Kuan Fu , Yu Zhang , Hung-yi Lee

We examine the speech modeling potential of generative spoken language modeling (GSLM), which involves using learned symbols derived from data rather than phonemes for speech analysis and synthesis. Since GSLM facilitates textless spoken…

Computation and Language · Computer Science 2023-06-02 Joonyong Park , Shinnosuke Takamichi , Tomohiko Nakamura , Kentaro Seki , Detai Xin , Hiroshi Saruwatari

Nowadays vast amounts of speech data are recorded from low-quality recorder devices such as smartphones, tablets, laptops, and medium-quality microphones. The objective of this research was to study the automatic generation of high-quality…

‹ Prev 1 8 9 10 Next ›