Louis C. W. Pols

Learn More
– Open source database – Hand-segmented Dutch speech – 8 speakers – 8 speaking styles – 50,000 words / 5 1/2 hours – Speech preparation: ~ 3 person-weeks per speaker – 1,000 hours of hand labeling – Asymptotic segmentation speed: 1 word / minute or 4 boundaries / minute – Median Absolute Difference: 6 ms between labelers 4 ms within labelers –(More)
In this paper we present several acoustical features, which are used as predictors for prominence. A set of 1244 sentences from 273 different speakers is selected from the Dutch Polyphone Corpus. Via listening experiments the subjective prominence markers are obtained. Several acoustical features concerning F 0 , energy and duration are derived and used as(More)
This paper presents research on integrating context-dependent durational knowledge into HMM-based speech recognition. The first part of the paper presents work on obtaining relations between the parameters of the context-free HMMs and their durational behaviour, in preparation for the context-dependent durational modelling presented in the second part.(More)
It is proposed that some of the variation in speech is the result of an effort to communicate efficiently. Speaking is considered efficient if the speech sound contains only the information needed to understand it. This efficiency is tested by means of a corpus of spontaneous and matched read speech, and syllable, word, and N-gram frequencies as measures of(More)
Speech is considered an efficient communication channel. This implies that the organization of utterances is such that more speaking effort is directed towards important parts than towards redundant parts. Based on a model of incremental word recognition, the importance of a segment is defined as its contribution to word-disambiguation. This importance is(More)