English
Related papers

Related papers: Adversarial Speaker Disentanglement Using Unannota…

200 papers

The fast increase of web services and mobile apps, which collect personal data from users, increases the risk that their privacy may be severely compromised. In particular, the increasing variety of spoken language interfaces and voice…

In recent years, speech-based self-supervised learning (SSL) has made significant progress in various tasks, including automatic speech recognition (ASR). An ASR model with decent performance can be realized by fine-tuning an SSL model with…

Audio and Speech Processing · Electrical Eng. & Systems 2023-08-30 Zhisheng Zheng , Ziyang Ma , Yu Wang , Xie Chen

Self-supervised learning (SSL) has become a popular method for generating invariant representations without the need for human annotations. Nonetheless, the desired invariant representation is achieved by utilising prior online…

Machine Learning · Computer Science 2024-09-30 Foivos Ntelemis , Yaochu Jin , Spencer A. Thomas

Most current zero-shot voice conversion methods rely on externally supervised components, particularly speaker encoders, for training. To explore alternatives that eliminate this dependency, this paper introduces GenVC, a novel framework…

Audio and Speech Processing · Electrical Eng. & Systems 2025-08-21 Zexin Cai , Henry Li Xinyuan , Ashi Garg , Leibny Paola García-Perera , Kevin Duh , Sanjeev Khudanpur , Matthew Wiesner , Nicholas Andrews

Zero-shot voice conversion is a technique that alters the speaker identity of an input speech to match a target speaker using only a single reference utterance, without requiring additional training. Recent approaches extensively utilize…

Sound · Computer Science 2025-09-11 Youngjun Sim , Jinsung Yoon , Wooyeol Jeong , Young-Joo Suh

The use of synthetic speech as data augmentation is gaining increasing popularity in fields such as automatic speech recognition and speech classification tasks. Despite novel text-to-speech systems with voice cloning capabilities, that…

Sound · Computer Science 2024-09-20 Sebastião Quintas , Isabelle Ferrané , Thomas Pellegrini

Large performance degradation is often observed for speaker ver-ification systems when applied to a new domain dataset. Givenan unlabeled target-domain dataset, unsupervised domain adaptation(UDA) methods, which usually leverage adversarial…

Sound · Computer Science 2021-09-01 Zhengyang Chen , Shuai Wang , Yanmin Qian

Disentanglement is the task of learning representations that identify and separate factors that explain the variation observed in data. Disentangled representations are useful to increase the generalizability, explainability, and fairness…

Audio and Speech Processing · Electrical Eng. & Systems 2023-08-09 Michael Kuhlmann , Adrian Meise , Fritz Seebauer , Petra Wagner , Reinhold Haeb-Umbach

In recent Text-to-Speech (TTS) systems, a neural vocoder often generates speech samples by solely conditioning on acoustic features predicted from an acoustic model. However, there are always distortions existing in the predicted acoustic…

Sound · Computer Science 2023-04-25 Jianzong Wang , Xulong Zhang , Haobin Tang , Aolan Sun , Ning Cheng , Jing Xiao

In this paper, we address the problem of speaker recognition in challenging acoustic conditions using a novel method to extract robust speaker-discriminative speech representations. We adopt a recently proposed unsupervised adversarial…

Audio and Speech Processing · Electrical Eng. & Systems 2019-11-05 Raghuveer Peri , Monisankha Pal , Arindam Jati , Krishna Somandepalli , Shrikanth Narayanan

In this paper we investigate the use of adversarial domain adaptation for addressing the problem of language mismatch between speaker recognition corpora. In the context of speaker verification, adversarial domain adaptation methods aim at…

Audio and Speech Processing · Electrical Eng. & Systems 2018-11-07 Johan Rohdin , Themos Stafylakis , Anna Silnova , Hossein Zeinali , Lukas Burget , Oldrich Plchot

In this paper, we propose an effective training strategy to ex-tract robust speaker representations from a speech signal. Oneof the key challenges in speaker recognition tasks is to learnlatent representations or embeddings containing…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-05 Yoohwan Kwon , Soo-Whan Chung , Hong-Goo Kang

Leveraging the fact that speaker identity and content vary on different time scales, \acrlong{fhvae} (\acrshort{fhvae}) uses different latent variables to symbolize these two attributes. Disentanglement of these attributes is carried out by…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-16 Yuying Xie , Thomas Arildsen , Zheng-Hua Tan

The awareness for biased ASR datasets or models has increased notably in recent years. Even for English, despite a vast amount of available training data, systems perform worse for non-native speakers. In this work, we improve an…

Computation and Language · Computer Science 2023-03-03 Philipp Klumpp , Pooja Chitkara , Leda Sarı , Prashant Serai , Jilong Wu , Irina-Elena Veliche , Rongqing Huang , Qing He

State-of-the-art speaker verification systems are inherently dependent on some kind of human supervision as they are trained on massive amounts of labeled data. However, manually annotating utterances is slow, expensive and not scalable to…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-25 Théo Lepage , Réda Dehak

Supervised speech enhancement relies on parallel databases of degraded speech signals and their clean reference signals during training. This setting prohibits the use of real-world degraded speech data that may better represent the…

Audio and Speech Processing · Electrical Eng. & Systems 2021-09-22 Yangyang Xia , Buye Xu , Anurag Kumar

Self-supervised learning (SSL)-based speech models are extensively used for full-stack speech processing. However, it has been observed that improving SSL-based speech representations using unlabeled speech for content-related tasks is…

Computation and Language · Computer Science 2024-06-14 Amit Meghanani , Thomas Hain

Human speech can be characterized by different components, including semantic content, speaker identity and prosodic information. Significant progress has been made in disentangling representations for semantic content and speaker identity…

Sound · Computer Science 2023-09-27 Leyuan Qu , Taihao Li , Cornelius Weber , Theresa Pekarek-Rosin , Fuji Ren , Stefan Wermter

Recent studies find existing self-supervised speech encoders contain primarily acoustic rather than semantic information. As a result, pipelined supervised automatic speech recognition (ASR) to large language model (LLM) systems achieve…

Voice conversion (VC) and text-to-speech (TTS) are two tasks that share a similar objective, generating speech with a target voice. However, they are usually developed independently under vastly different frameworks. In this paper, we…

Audio and Speech Processing · Electrical Eng. & Systems 2019-09-17 Hieu-Thi Luong , Junichi Yamagishi