Parrot Speech

My photographParrot Speech project deals with an implementation of a system that helps to analyze vocalization of gray parrots. The system extract acoustic features from a real recorded phonic samples. The samples are processed using various speech signal processing methods and finally analyzed by self-organizing neural networks.

Publications

  • Skripal P.: The analysis of vocal communication in Parrots. At: Czech Technical University in Prague, 2006 BibTex, PDF

    Phonic expression has always been the primary mean of communication not only for human beings, but also for animals. It constitutes an essential element of their mutual communication. Latest studies of songbirds' social behavior make it apparent that there are many parallels between the evolution of birds' natural vocalization and that of human speech. Besides imitation of words (those of human beings) by itself, it is their natural phonic expression that is of an overriding importance. This way of expression can potentially contain even linguistic structures and thus reflect some of the linguistic expression general features - that of a speech. We can identify this phenomenon also in case of parrots, which are generally known for their highly developed ability of imitation. "Parrot natural speech" phenomenon is thus related not only to profound philosophical implications, but is closely connected to natural sciences and humanities such as ethology and linguistics, too. Outside of this humanities and scientific context can this issue be also viewed upon from the specifically technical point of view. In order to study this phenomenon in depth, one needs to classify parrot phonic expression, which on its lowest level requires for its functioning a system that would be able to analyze the acoustic signal. With help of computing would such a system be able to classify the phonic expression into individual characteristic categories. From the above mentioned phenomenon's point of view it seems that the most interesting approach is their linguistic rating similar to the one being widely used in systems for human speech recognition. The categories themselves can obtain their meaning on several levels. Topic of this final thesis is in addition to the parrot vocalization analyses itself the proposal for implementation of a system that would use its analytical aspect for the need of phonetics expression classification. In this analytical part we shall further on deal with cepstral and statistical analyses of the real phonic samples and will propose a method for an extraction of the appropriate acoustic signal features. The second final part of the thesis is focused on detailed analyses of the self-organizing neural network and its application during the process of the acquired features classification. Implementation of the above mentioned classification system and its testing with real data constitutes an integral part of this study.

  • Skripal P.: The analysis of vocal communication in Parrots. In: Proceedings ACM Student Research Competition 2006, CZ ACM, 2006. ISBN BibTex, PDF

    The topic of the thesis is the analysis of the acoustic communication and vocalization in parrots. In the experimental part of this work, we are dealing with cepstral and statistical analyses of real phonic samples and we will introduce a method for the extraction of appropriate acoustic signal features. The document describes a proposal for implementation of a system that would use the analytical outcomes of our work for the need of phonetics expression classification. We focus on detailed analyses of the self-organizing neural network and its application during the process of the acquired features classification. An overview of implementation of the above-mentioned classification system and of its use with real data constitutes an integral part of this study. Finally in this paper, we will discuss the possibilities of application of the Parrot Speech Toolbox and briefly present some crucial results as the outcomes of the whole work.