| Summary: | In the contemporary world of techniques, voice technologies, such as speech recognition, synthesis of speech signals, and their combined versions, acquire more and more significance. If we had a good synthesizer, we could use it widely. An example could be the reading of electronic books in voice, etc. Speech synthesizers of older generation were quite primitive. A modern synthesis machine is not only able to read the text evenly, but to convey the emotionality as well. Speech synthesizer can raise a tone, dictate a question, and synthesize a voice of a desired timbre and speed. These features considerably enrich the speech synthesized.
The articulatory speech synthesizer is based on a model of the physiology of the human speech production process. Articulatory synthesis usually consists of two separate components – articulatory model and acoustic model. In the articulatory model, the vocal tract is divided into numerous small sections and the corresponding cross – sectional areas are used as parameters to represent the vocal tract characteristics. In the acoustic model, each cross–sectional area is approximated by an electrical analog transmission line. To simulate the movement of the vocal tract, the area functions change time.
The aim of the research paper is to analyze the consistent pattern of the vocal tract, generating the sound of Lithuanian language. The tasks are these: to look at the history of speech synthesis; to look at the architecture of speech; to overlook... [to full text]
|
|---|
