Work

Toward improved HMM-based speech synthesis using high-level syntactical features

Year: 2010

Type: conference-paper

Abstract: A major drawback of current Hidden Markov Model (HMM)-based speech synthesis is the monotony of the generated speech which is closely related to the monotony of the generated prosody.Complementary to model-oriented approaches that aim to increase the prosodic variability by reducing the "over-smoothing" effect, this paper presents a linguistic-oriented approach in which high-level linguistic features are extracted from text in order to improve prosody modeling.A linguistic processing chain based on linguistic preprocessing, morpho-syntactical labeling, and syntactical parsing is used to extract high-level syntactical features from an input text.Such linguistic features are then introduced into a HMM-based speech synthesis system to model prosodic variations (f0, duration, and spectral variations).Subjective evaluation reveals that the proposed approach significantly improve speech synthesis compared to a baseline model, event if such improvement depends on the observed linguistic phenomenon.

Source: Speech prosody

DOI: 10.21437/speechprosody.2010-119

Authors: Nicolas Obin, Pierre Lanchantin, Mathieu Avanzi, Anne Lacheret-Dujour, Xavier Rodet

Institutions: Institut de Recherche et Coordination Acoustique Musique, Université Paris Nanterre, Modèles Dynamiques Corpus, University of Neuchâtel

Language: English

Topic: Speech Recognition and Synthesis

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: bronze

Funders: National Science Foundation, Agence Nationale de la Recherche, Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung, Centre National de la Recherche Scientifique

Awards: A fresh look on the prosody/syntax interface, La structure interne des périodes, EXAFS and zeolites in heterogeneous catalysis