This book will help readers understand fundamental and advanced statistical models and deep learning models for robust speaker recognition and domain adaptation. This useful toolkit enables readers to apply machine learning techniques to address practical issues, such as robustness under adverse acoustic environments and domain mismatch, when deploying speaker recognition systems. Presenting state-of-the-art machine learning techniques for speaker recognition and featuring a range of probabilistic models, learning algorithms, case studies, and new trends and directions for speaker recognition based on modern machine learning and deep learning, this is the perfect resource for graduates, researchers, practitioners and engineers in electrical engineering, computer science and applied mathematics. Presents the inference procedures from maximum likelihood to approximate Bayesian for linear and non-linear probabilistic models based on different types of latent variables Features comprehensive treatments of noise robustness and domain adaptation in speaker recognition Provides in-depth coverage of deep learning models, ranging from deep neural networks, and deep belief networks to variational autoencoders and generative adversarial networks, for feature representation and data augmentation in speaker recognition
- ISBN: 9781108428125
- Editorial: CAMBRIDGE UNIVERSITY PRESS
- Encuadernacion: Tela
- Páginas: 334
- Fecha Publicación: 15/11/2020
- Nº Volúmenes: 1
- Idioma: