Konkatenatīvas latviešu valodas runas sintēzes sistēmas izveide
Loading...
Date
Authors
Advisor
Journal Title
Journal ISSN
Volume Title
Publisher
Latvijas Universitāte
Language
N/A
Abstract
Bakalaura darbā ir aprakstīta autora izstrādāta konkatenatīvas latviešu valodas runas sintēzes sistēma. Bakalaura darba ietvaros tika izstrādāta sistēmas arhitektūra un runas sintēzes bibliotēka, kas nodrošina nepieciešamo funkcionalitāti, lai sistēmu būtu iespējams integrēt ārējos risinājumos.
Darbā tiek aprakstīti procesi, kā no teksta latviešu valodā tiek iegūts audio fails, kas satur sākotnējā teksta akustisko reprezentāciju, respektīvi, runu. Darbā tiek arī apskatīti principi, kā no atsevišķiem audio fragmentiem tiek izveidots nepieciešamais audio fails, fragmentus ar dažādām metodēm kombinējot kopā.
The Bachelor paper describes a concatenative Latvian language speech synthesis system developed by the author. Within the framework of the Bachelor paper the architecture of the system and the speech synthesis library, that provides the necessary functionality, so that the system can be integrated into external systems, was developed. In the paper there are examined processes of how an audio file, is gained from a text in Latvian, where the resulting audio file contains the acoustic representation of the text, respectively, the speech. In the paper the author looks at principles of how an audio file is combined together from smaller audio fragments using different concatenation methods.
The Bachelor paper describes a concatenative Latvian language speech synthesis system developed by the author. Within the framework of the Bachelor paper the architecture of the system and the speech synthesis library, that provides the necessary functionality, so that the system can be integrated into external systems, was developed. In the paper there are examined processes of how an audio file, is gained from a text in Latvian, where the resulting audio file contains the acoustic representation of the text, respectively, the speech. In the paper the author looks at principles of how an audio file is combined together from smaller audio fragments using different concatenation methods.