广播新闻语音的关键词检测系统  

Keyword spotting system for broadcast news

作　　者：张鹏远[1] 邵健[1] 赵庆卫[1] 颜永红[1] 

机构地区：[1]中国科学院声学所中科信利实验室,北京100080

出　　处：《通信学报》2007年第12期131-135,共5页Journal on Communications

基　　金：国家重点基础研究发展计划("973"计划)基金资助项目(2004CB318106);国家自然科学基金资助项目(10574140;60535030);国家高技术研究发展计划("863"计划)基金资助项目(2006AA010102;2006AA01Z195)~~

摘　　要：提出了一种两阶段的关键词检测策略,关键词表可即时配置、即时使用。与以往不同的是,解码是在整个声学空间上进行的,而不仅仅是关键词所构成的声学空间。首先,利用维特比解码得到最优候选的音素序列。然后,通过关键词列表,可以产生候选的关键词。最后,采用了基于声学模型的置信度与基于网格的置信度相结合的方法来降低虚警。实验证明,新的框架下关键词检测的性能得到了显著的提高。A two-step keyword spotting strategy was presented. This strategy allowed to change keyword list conveniently. Different from the previous systems, search space was generated based on all Chinese syllables, not specifically for keywords. Phoneme recognition was performed without any lexical constraints. With 1-best phoneme sequence and keyword list, which generated keyword hypotheses. At last, two confidence measures were introduced adopted in the system： one based on acoustic model and the other based on phoneme lattice. For a decoded speech frame aligned to an HMM state, the acoustic confidence was calculated. The lattice confidence made use of phoneme lattices generated by a phoneme recognizer. These two confidence measures were combined using a weighting factor to obtain a hybrid confidence as they had different dynamic scales. Experiments show that the proposed algorithms significantly improve the system oerformance on the broadcast news task.

关 键 词：关键词检测 音节识别器 置信度计算 

分 类 号：TP391.42[自动化与计算机技术—计算机应用技术]