Open AccessProceedings Article
Modeling the prosody of hidden events for improved word recognition.
TLDR
A new approach to penalize word hypotheses that are inconsistent with prosodic features such as duration and pitch is investigated, and the language model is modified to represent hidden events such as sentence boundaries and various forms of disfluency.Citations
More filters
Proceedings Article
SRILM – An Extensible Language Modeling Toolkit
TL;DR: The functionality of the SRILM toolkit is summarized and its design and implementation is discussed, highlighting ease of rapid prototyping, reusability, and combinability of tools.
Proceedings ArticleDOI
Spontaneous speech: how people really talk and why engineers should care.
TL;DR: An overview of four fundamental properties of spontaneous speech that present challenges for spoken language applications because they violate assumptions often applied in automatic processing technology are described.
Automatic detection and classification of prosodic events
TL;DR: This thesis describes work on the automatic detection and classification of prosodic events – specifically, pitch accents and prosodic phrase boundaries, and presents three proof-of-concept applications showing that access to hypothesized prosodic event information can be used to improve the performance of downstream spoken language processing tasks.
Book ChapterDOI
Prosody Modeling for Automatic Speech Recognition and Understanding
TL;DR: A number of applications of the prosody framework are surveyed, and results for automatic sentence segmentation and disfluency detection, topic segmentation, dialog act labeling, and word recognition are given.
Direct Modeling of Prosody: An Overview of Applications in Automatic Speech Processing
E. Shriberg,Andreas Stolcke +1 more
TL;DR: This work describes a “direct modeling” approach to using prosody in various speech technology tasks that does not involve any hand-labeling or modeling of prosodic events such as pitch accents or boundary tones, and focuses on spontaneous speech from a variety of contexts.
References
More filters
Journal ArticleDOI
Classification and Regression Trees.
Proceedings ArticleDOI
SWITCHBOARD: telephone speech corpus for research and development
TL;DR: SWITCHBOARD as mentioned in this paper is a large multispeaker corpus of conversational speech and text which should be of interest to researchers in speaker authentication and large vocabulary speech recognition.
Journal ArticleDOI
A Maximum Likelihood Approach to Continuous Speech Recognition
TL;DR: This paper describes a number of statistical models for use in speech recognition, with special attention to determining the parameters for such models from sparse data, and describes two decoding methods appropriate for constrained artificial languages and one appropriate for more realistic decoding tasks.
Detection and Correction of Repairs in Human-Computer Dialog
TL;DR: In this article, the authors present criteria and techniques for automatically detecting the presence of a repair, its location, and making the appropriate correction, which involve integration of knowledge from several sources: pattern matching, syntactic and semantic analysis, and acoustics.
Proceedings ArticleDOI
Integrating multiple knowledge sources for detection and correction of repairs in human-computer dialog
TL;DR: The authors present criteria and techniques for automatically detecting the presence of a repair, its location, and making the appropriate correction, and preliminary results show that pattern matching is effective at detecting repairs without excessive overgeneration.