Andrzej Kaczmarek

Intelligent Processing of Stuttered Speech

The process of counting stuttering events could be carried out more objectively through the automatic detection of stop-gaps, syllable repetitions and vowel prolongations. The alternative would be based on the subjective evaluations of speech fluency and may be dependent on a subjective evaluation method. Meanwhile, the automatic detection of intervocalic intervals, stop-gaps, voice onset time and vowel durations may depend on the speaker and the rules derived for a single speaker might be unreliable when trying to consider them as universal ones. This implies that learning algorithms having strong generalization capabilities could be applied to solve the problem. Nevertheless, such a system requires vectors of parameters, which characterize the distinctive features in a subjects speech patterns. In addition, an appropriate selection of the parameters and feature vectors while learning may augment the performance of an automatic detection system.The paper reports on automatic recognition of stuttered speech in normal and frequency altered feedback speech. It presents several methods of analyzing stuttered speech and describes attempts to establish those parameters that represent stuttering event. It also reports results of some experiments on automatic detection of speech disorder events that were based on both rough sets and artificial neural networks.

Creating a Reliable Music Discovery and Recommendation System

The aim of this chapter is to show problems related to creating a reliable music discovery system. The SYNAT database that contains audio files is used for the purpose of experiments. The files are divided into 22 classes corresponding to music genres with different cardinality. Of utmost importance for a reliable music recommendation system are the assignment of audio files to their appropriate genres and optimum parameterization for music-genre recognition. Hence, the starting point is audio file filtering, which can only be done automatically, but to a limited extent, when based on low-level signal processing features. Therefore, a variety of parameterization techniques are shortly reviewed in the context of their suitability to music retrieval from a large music database. In addition, some significant problems related to choosing an excerpt of audio file for an acoustic analysis and parameterization are pointed out. Then, experiments showing results of searching for songs that bear the greatest resemblance to the song in a given query are presented. In this way music recommendation system may be created that enables to retrieve songs that are similar to each other in terms of their low-level feature description and genre inclusion. The experiments performed also provide basis for more general observations and conclusions.

Music Recommendation Based on Multidimensional Description and Similarity Measures

This study aims to create an algorithm for assessing the degree to which songs belong to genres defined a priori. Such an algorithm is not aimed at providing unambiguous classification-labelling of songs, but at producing a multidimensional description encompassing all of the defined genres. The algorithm utilized data derived from the most relevant examples belonging to a particular genre of music. For this condition to be met, data must be appropriately selected. It is based on the fuzzy logic principles, which will be addressed further. The paper describes all steps of experiments along with examples of analyses and results obtained.