首页>
外国专利>
debate in several languages for speech recognition
debate in several languages for speech recognition
展开▼
机译:以多种语言进行辩论以进行语音识别
展开▼
页面导航
摘要
著录项
相似文献
摘要
There is provided a novel approach for generating multilingual text-to-phoneme mappings for use in multilingual speech recognition systems. The multilingual mappings are based on the weighted outputs from a neural network text-to-phoneme model, trained on data mixed from several languages. The multilingual mappings used together with a branched grammar decoding scheme is able to capture both inter- and intra-language pronunciation variations which is ideal for multilingual speaker independent speech recognition systems. A significant improvement in overall system performance is obtained for a multilingual speaker independent name dialling task when applying multilingual instead of language dependent text-to-phoneme mapping.
展开▼