- ホーム
- > 洋書
- > ドイツ書
- > Mathematics, Sciences & Technology
- > Physics and Astronomy
- > mechanics & acoustics
Description
(Text)
Speech technology is a major and growing industry that enriches the lives oftechnologically-minded people in a number of ways. Many potential users are,however, excluded: Namely, all speakers who cannot easily, or even at all, producespeech. Silent-Speech Interfaces offer a way to communicate with a machine througha convenient speech recognition interface without the need for acoustic speech. Tothat end, the speech movements need to be captured and mapped to either text oracoustic speech. This dissertation proposes a new Silent-Speech Interface based on anewly developed measurement technology called Electro-Optical Stomatography anda novel parametric vocal tract model to facilitate real-time speech synthesis basedon the measured data. The hardware was used to conduct command word recognitionstudies reaching state-of-the-art intra- and inter-individual performance. Furthermore,a study on using the hardware to control the vocal tract model in a direct articulationto-speech synthesis loop was also completed. While the intelligibility of consonantsand connected speech was quite poor, the intelligibility of synthesized vowels washigh. Promising ways to improve the system are discussed in the outlook.
