ISBN-13: 9781608454730 / Angielski / Miękka / 2013 / 162 str.
ISBN-13: 9781608454730 / Angielski / Miękka / 2013 / 162 str.
This book introduces the theory, algorithms and implementation techniques for efficient decoding in speech recognition mainly focusing on Weighted Finite-State Transducer (WFST) approach. Decoding process for speech recognition is viewed as a search problem to find a sequence of words that best matches an input speech signal. Since this process becomes computationally very expensive according as the vocabulary size of the system increases, many studies have been devoted to reducing the computational cost. Recently, the WFST approach is becoming the mainstream of state-of-the-art speech recognition technology, because it provides clear improvement in decoding speed with fewer recognition errors compared to conventional methods. However, it is not easy to follow all of the algorithms used in this framework. In this book, we review the WFST approach and aim to give comprehensive interpretations of WFST operations and decoding algorithms to help anyone who wants to understand, develop, and study WFST-based speech recognizers. We also mention recent advances in this framework and its applications to spoken language processing
This book introduces the theory, algorithms, and implementation techniques for efficient decoding in speech recognition mainly focusing on the Weighted Finite-State Transducer (WFST) approach. The decoding process for speech recognition is viewed as a search problem whose goal is to find a sequence of words that best matches an input speech signal. Since this process becomes computationally more expensive as the system vocabulary size increases, research has long been devoted to reducing the computational cost. Recently, the WFST approach has become an important state-of-the-art speech recognition technology, because it offers improved decoding speed with fewer recognition errors compared with conventional methods. However, it is not easy to understand all the algorithms used in this framework, and they are still in a black box for many people. In this book, we review the WFST approach and aim to provide comprehensive interpretations of WFST operations and decoding algorithms to help anyone who wants to understand, develop, and study WFST-based speech recognizers. We also mention recent advances in this framework and its applications to spoken language processing.