Continuous Speech Database Acquisition of Various Dialects from Maharashtra Region

The development of a speech dataset in the Marathwada dialect of the Marathi language, which is spoken across the Maharashtra state is described in this paper. The study describes the creation of a continuous sentences speech dataset in Marathi for different dialects, as well as a continuous speech database for various dialects in various Maharashtra areas. The newly developed voice database will be useful to all Marathi language scholars. Any different variety of a language spoken by a group of people is referred to as a dialect. Dialect refers to variances in a language's speaking patterns. Due to the speakers' regional and cultural disparities, individuals' exposure to native languages impacts their accents and choice of words through conversation. Marathi seems to be an Indo- Aryan linguistic pronounced primarily by the Marathi community throughout Maharashtra, India. It is the state language of Maharashtra. The spoken form of Marathi varies by area. These changes have a significant impact on the utterance architecture of phonology. Such changes have a significant impact on the utterance architecture of phonology. Four separate Marathi dialects, including Marathwada area (Marathi), Khandesh (Ahirani), Vidarbha region (Varhadi), and Kokan Region (malvani), were studied in this paper for their effect on phonetic duration through spoken phrases.