Modelling Lexical Stress

Human listeners use lexical stress for word segmentation and disambiguation. We look into using lexical stress for speech recognition by examining a Dutch-language corpus. We propose that different spectral features are needed for different phonemes and that, besides vowels, consonants should be taken into account.

• Type: Conference
• Year: 2005
• Where: TSD
• Authors: Rogier C. van Dalen, Pascal Wiggers, Léon J. M. Rothkrantz
• Keywords: Different Spectral Features, Lexical Stress, Signal Processing, TSD 2005, Word Segmentation