Comparison of intensity-based methods for automatic speech rate computation

Automatic computation of speech rate is a necessary task in wide range applications that require this prosodic feature, which manual transcription and time alignments are not available. Several tools have been developed to end, but enough research has conducted yet see what extent they scalable other languages.
 In the present work, we take two off-the- shelf designed for automatic already tested Dutch English (v1, relies on intensity peaks preceded by an dip find syllable nuclei v3, surrounded dips) apply them read spontaneous Spanish speech. Then, test offers best performance. The results obtained with precision normalized mean squared error metrics showed v3 performs better than v1. However, recall measurement shows performance v1, suggests more fine-grained analysis sensitivity specificity needed select option depending application dealing with.