Application of Speech Keyword Spotting in voice Control for Home Appliance
碩士 === 國立東華大學 === 資訊工程學系 === 96 === Filler-based keyword spotting method’s performance depends heavily on the efficacy of the built filler (garbage) model. Training an effective filler model is not a trivial task. Therefore, it is the goal of this study to propose a novel improved solution over the...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | en_US |
| Published: |
2008
|
| Online Access: | http://ndltd.ncl.edu.tw/handle/06571195347832216953 |
| Summary: | 碩士 === 國立東華大學 === 資訊工程學系 === 96 === Filler-based keyword spotting method’s performance depends heavily on the efficacy of the built filler (garbage) model. Training an effective filler model is not a trivial task. Therefore, it is the goal of this study to propose a novel improved solution over the filler-based keyword spotting methods. This thesis proposes a hierarchical keyword spotting (HKWS) method that replaces the keyword spotting process with a syllable-level spotting process followed by another word-level composition process. The first step of the syllable-level spotting is to pinpoint out all possible segments in the input speech signal. Afterwards, the second step to prune those syllable segments with lower scores through a syllable verification process. The word-level composition process is to concatenate the verified syllable segments into the target keyword under a predefined reasonable condition for concatenation.
The proposed approach achieves both the domain independence and vocabulary independence, and therefore is suitable for customization under different applications. Several experiments are also conducted to verify the effectiveness of the proposed HKWS method.
|
|---|