V
Volker Strom
Researcher at University of Edinburgh
Publications - 24
Citations - 560
Volker Strom is an academic researcher from University of Edinburgh. The author has contributed to research in topics: Speech synthesis & Prosody. The author has an hindex of 10, co-authored 24 publications receiving 546 citations. Previous affiliations of Volker Strom include University of Bonn & AT&T Labs.
Papers
More filters
Proceedings ArticleDOI
Visual prosody: facial movements accompanying speech
TL;DR: This paper analyzed quantitatively head and facial movements that accompany speech and investigated how they relate to the text's prosodic structure, finding that the direction and strength of head movements vary from one speaker to another, yet their timing is typically well synchronized with the spoken text.
Detection of accents, phrase boundaries, and sentence modality in German
TL;DR: The authors used Gaussian distribution classifiers to detect accents, phrase boundaries, and sentence modality in spontaneous speech, yielding recognition rates of 78 percent for accents, 80 percent for phrase boundaries and 85 percent for sentence modalities.
Journal ArticleDOI
Modeling and interpolation of Austrian German and Viennese dialect in HMM-based speech synthesis
TL;DR: Good evaluation results show that listeners can perceive both continuous and categorical changes of dialect varieties by using phonological transformations employed as switching rules in the HMM interpolation.
Proceedings ArticleDOI
Modelling Prominence and Emphasis Improves Unit-Selection Synthesis
Volker Strom,Ani Nenkova,Robert A. J. Clark,Yolanda Vazquez-Alvarez,Jason Brenier,Simon King,Dan Jurafsky +6 more
TL;DR: The results of large scale perception experiments showing improvements in synthesising two distinct kinds of prominence: standard pitch-accent and strong emphatic accents are described and diffe rences in the effe cts of prominence between childdirected speech and news and fict ion genres are shown.
Proceedings Article
Corpus-based techniques in the AT&t nextgen synthesis system.
Ann K. Syrdal,Colin W. Wightman,Alistair Conkie,Yannis Stylianou,Marc C. Beutnagel,Juergen Schroeter,Volker Strom,Ki-Seung Lee,Matthew J. Makashay +8 more
TL;DR: Recent advances in automatic phonetic and prosodic labeling and a new faster harmonic plus noise model (HNM) and unit preselection implementations have improved TTS quality and speeded up both development time and runtime.