Machine Learning Paradigms for Speech Recognition

Over the last few decades, there has been a huge development of machine learning paradigms used in automatic speech recognition (ASR) for home automation (smart home) for space exploration, etc. Although commercial speech recognizers are available for certain well-defined apps such as dictation and transcription, where the Android app "e-Dictate - Speech To Text & Translator" has a special place for recognizing all languages in the world, including Balkan languages, many problems in ASR such as recognition in noisy environments, multilingual recognition, and multimodal recognition have yet to be resolved. This book provides a comprehensive overview of common machine learning (ML) techniques such as artificial neural networks, vector support machines, and Gaussian mixture models, along with hidden Markov models presented in ASR.

Autorentext

MSc Dejan Dodi nació el 5 de octubre de 1977. en Vranje, República de Serbia. Máster por la Facultad de Informática de Skopje, República de Macedonia. Desarrollador de JAVA y fundador de la startup EDUKOM. Autor y coautor de un gran número de aplicaciones para Android. Es autor de varios artículos científicos en el campo del aprendizaje automático.