Generative Adversarial Networks (GANs) are machine learning networks based around creating synthetic data. Voice Conversion (VC) is a subset of voice translation that involves translating the paralinguistic features of a source speaker to a target speaker while preserving the linguistic information. The aim of non-parallel conditional GANs for VC is to translate an acoustic speech feature sequence from one domain to another without the use of paired data. In the study reported here, we investigated the interpretability of state-of-the-art implementations of non-parallel GANs in the domain of VC. We show that the learned representations in the repeating layers of a particular GAN architecture remain close to their original random initialised parameters, demonstrating that it is the number of repeating layers that is more responsible for the quality of the output. We also analysed the learned representations of a model trained on one particular dataset when used during transfer learning on another dataset. This showed extremely high levels of similarity across the entire network. Together, these results provide new insight into how the learned representations of deep generative networks change during learning and the importance in the number of layers.
Implementation of interactive tools for investigating fundamental frequency response of voiced sounds to auditory stimulation
Wakayama University(和歌山大学);Toyohashi University of Technology(丰桥技术科学大学);Waseda University(早稻田大学);Health Science University of Hokkaido(北海道医疗大学);Kyoto City University of Arts(京都造形艺术大学);Meiji University(明治大学)
Profiling the Voice: Speaker-Specific Phoneme Fingerprinting for Speech Deepfake Detection
Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education(航空航天信息安全与可信计算重点实验室,教育部);School of Cyber Science and Engineering, Wuhan University(武汉大学计算机科学与工程学院)
A Concept-based approach to Voice Disorder Detection
Politecnico di Torino;CENTAI Institute(CENTAI研究院);San Feliciano Hospital(San Feliciano医院);SCDU Otorinolaringoiatria, Head Neck Cancer Unit, Ospedale San Giovanni Bosco(SCDU耳鼻喉科,头颈癌症单元,San Giovanni Bosco医院);Dipartimento di Oncologia, Università degli Studi di Torino(肿瘤学系,托里尼大学)
Investigating the Effectiveness of Explainability Methods in Parkinson's Detection from Speech
University of Bologna(博洛尼亚大学);Fondazione Bruno Kessler(布鲁诺·凯斯勒基金会);Mila-Québec AI Institute(米拉-魁北克人工智能研究所);Concordia University(康考迪亚大学);Laval University(拉瓦尔大学);Université de Montréal(蒙特利尔大学)
Generative Multi-modal Feedback for Singing Voice Synthesis Evaluation
Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);University of Science and Technology of China(中国科学技术大学);Columbia University(哥伦比亚大学);Dalian University of Technology(大连理工大学);The Chinese University of Hong Kong(香港中文大学)
Interpretability Analysis of Deep Models for COVID-19 Detection
Federal University of Technology - Paraná(巴拉那联邦理工大学);University of São Paulo(圣保罗大学);Federal University of Goias(戈亚斯联邦大学);São Paulo State University(圣保罗州立大学);CeDRI - Instituto Politécnico de Bragança(布拉干萨理工学院CeDRI)