Techniques for Noise Robustness in Automatic Speech Recognition

Beschreibung

Automatic speech recognition (ASR) systems are findingincreasing use in everyday life. Many of the commonplaceenvironments where the systems are used are noisy, for exampleusers calling up a voice search system from a busy cafeteria or astreet. This can result in degraded speech recordings and adverselyaffect the performance of speech recognition systems. As theuse of ASR systems increases, knowledge of the state-of-the-art intechniques to deal with such problems becomes critical to systemand application engineers and researchers who work with or on ASRtechnologies. This book presents a comprehensive survey of thestate-of-the-art in techniques used to improve the robustness ofspeech recognition systems to these degrading externalinfluences. Key features: * Reviews all the main noise robust ASR approaches, includingsignal separation, voice activity detection, robust featureextraction, model compensation and adaptation, missing datatechniques and recognition of reverberant speech. * Acts as a timely exposition of the topic in light of morewidespread use in the future of ASR technology in challengingenvironments. * Addresses robustness issues and signal degradation which areboth key requirements for practitioners of ASR. * Includes contributions from top ASR researchers from leadingresearch units in the field

Autor*in

Tuomas Virtanen

Themen in »Techniques for Noise Robustness in Automatic Speech Recognition«

Audio & Speech Processing & Broadcasting Audio-, Sprachverarbeitung u. Übertragung Electrical & Electronics Engineering Elektrotechnik u. Elektronik Spracherkennung

Stimmen zu »Techniques for Noise Robustness in Automatic Speech Recognition«

Details

Link teilen