Robust Automatic Speech Recognition: A Bridge to Practical Applications

Robust Automatic Speech Recognition: A Bridge to Practical Applications establishes a solid and consistent foundation for noise-robust automatic speech recognition (ASR) and provides a thorough overview of modern noise-robust techniques which have been developed over the past 30 years. The book emphasizes practical methods that are proven to be successful, also discussing those that are likely to be developed further for future applications. In addition, the pros and cons of using noise-robust ASR techniques for different applications are given, providing users with a practical guide to selecting the best methods for future applications. Connects noise-robust speech recognition methods to machine learning technologiesContains a unified, state-of-the-art survey of successful noise robust speech recognition technologiesProvides several ways to classify noise-robust speech recognition technologies into different categoriesAuthored by leading researchers at Microsoft INDICE: IntroductionFundamentals of speech recognitionBackground of robust speech recognitionFeature and model domain processingCompensation with prior knowledgeExplicit distortion modelingUncertainty processingJoint model trainingReverberant speech recognitionMulti-channel processingSummary

• ISBN: 978-0-12-802398-3
• Editorial: Academic Press
• Encuadernacion: Cartoné
• Páginas: 250
• Fecha Publicación: 15/10/2015
• Nº Volúmenes: 1
• Idioma: Inglés