Quality control of automatic labelling using HMM-based synthesis

This paper presents a measure to verify the quality of automatically aligned phone labels. The measure is based on a similarity cost between automatically generated phonetic segments and phonetic segments generated by an HMMbased synthesiser. We investigate the effectiveness of the measure for identifying problems of three types: alignment errors, phone identity problems and noise insertion. Our experiments show that the measure is best at finding noise errors, followed by phone identity mismatches and serious misalignments.

• Type: Conference
• Year: 2009
• Where: ICASSP
• Authors: Sathish Pammi, Marcela Charfuelan, Marc Schröder
• Keywords: ICASSP 2009, Phone Identity, Phone Identity Problems, Phonetic Segments, Signal Processing