Introducing the SEA_AP: an Enhanced Tool for Automatic Prosodic Analysis

Introducing the SEA_AP: an Enhanced Tool for Automatic Prosodic Analysis Marta Martínez*, Rocío Varela*, Carmen García-Mateo*, Elisa Fernández Rei**, Adela Martínez Calvo*** *AtlantTIC Research Center, Escola de Enxeñaría de Telecomunicación Universidade de Vigo, Campus As Lagoas Marcosende 36310 Vigo (Spain) **Instituto da Lingua Galega, Universidade de Santiago de Compostela, Praza da Universidade, 4, 15782 Santiago de Compostela (Spain) ***Servizo de Consultoría Estadística, Dep. de Estatística e Investigación Operativa, Universidade de Santiago de Compostela, Facultade de Matemáticas, 15782 Santiago de Compostela (Spain) E-mail: carmen.garcia@uvigo.es, mmartinez@gts.uvigo.es, rvarela@gts.uvigo.es, elisa.fernandez@usc.es, adela.martinez@usc.es Abstract SEA_AP (Segmentador e Etiquetador Automático para Análise Prosódica, Automatic Segmentation and Labelling for Prosodic Analysis) toolkit is an application that performs audio segmentation and labelling to create a TextGrid file which will be used to launch a prosodic analysis using Praat. In this paper, we want to describe the improved functionality of the tool achieved by adding a dialectometric analysis module using R scripts. The dialectometric analysis includes computing correlations among F0 curves and it obtains prosodic distances among the different variables of interest (location, speaker, structure, etc.). The dialectometric analysis requires large databases in order to be adequately computed, and automatic segmentation and labelling can create them thanks to a procedure less costly than the manual alternative. Thus, the integration of these tools into the SEA_AP allows to propose a distribution of geoprosodic areas by means of a quantitative method, which completes the traditional dialectological point of view. The current version of the SEA_AP toolkit is capable of analysing Galician, Spanish and Brazilian Portuguese data, and hence the distances between several prosodic linguistic varieties can be measured at present. Keywords: Speech segmentation, labelling, prosody, dialectometry 1. Introduction Research activities produce an important amount of resources and tools which are usually unfocused and fragmented, since they are developed by different groups all over the world and implement partial solutions. It is also common that different research areas can help one another to reach better results based on the resources they share. As an example, in CORILGA project (García-Mateo et al., 2014), linguistics and speech processing had reached improvements for both research areas. Eventually, this situation turns into the need of unifying the material in compact code packages provided with user interfaces which will make the research progress also useful for the other specialization areas. Taking into account this situation, the SEA_AP toolkit (Segmentador e Etiquetador Automático para Análise Prosódica) (Martínez et al., 2015) was developed. This software is an automatic segmentation and labelling tool which includes prosodic analysis scripts. In its first release (Martínez et al., 2015), it was prepared to get audio and transcription files as input and generate automatic timestamps which were used to create automatically a Praat TextGrid (Boersma & Weenik, 2013) to perform prosodic analysis. Besides, the tool seeks to integrate some tools used by linguists in dialectological oriented projects such as the AMPER project (Contini et al., 2002: 227-230; Martínez et al., 2003-2015). One of the most important points of the prosodic analysis is the study of …

Content truncated to 500 words