Abstract
Attempts to extend work on speech and natural language systems to the broader spoken language (SL) domain rapidly meet with bottlenecks due to temporal features of spoken language at different levels, and to the projection problem connected with Speaker and language Variation in spoken language, from speech style through dialectal to multilingual Variation. It is suggested that part of the Solution to the bottleneck problems is to consider typical SL problems like the ‘Prosodie Paradox’, connected with integrating the notion of time into linguistic descriptions. Four notions of time are distinguished, and a novel arrangement of linguistically motivated components for SL system architectures is suggested. Finally, consequences of this framework for the specification of a prosodie parser are discussed.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
