专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

2. 发明申请

WO2014145960A2 METHOD AND SYSTEM FOR GENERATING ADVANCED FEATURE DISCRIMINATION VECTORS FOR USE IN SPEECH RECOGNITION 审中-公开
标题翻译：用于生成语音识别中使用的高级特征歧视向量的方法和系统
公开(公告)号：WO2014145960A2
公开(公告)日：2014-09-18
申请号：PCT/US2014030819
申请日：2014-03-17
申请人： SHORT KEVIN M , HONE BRIAN
发明人： SHORT KEVIN M , HONE BRIAN
IPC分类号： G10L17/02
CPC分类号： G10L15/02 , G10L25/03 , G10L25/18 , G10L25/21 , G10L25/24 , G10L25/93 , G10L2015/025
摘要： A method of renormalizing high-resolution oscillator peaks, extracted from windowed samples of an audio signal, is disclosed. Feature vectors are generated for which variations in both fundamental frequency and time duration of speech are substantially mitigated. The feature vectors may be aligned within a common coordinate space, free of those variations in frequency and time duration that occurs between speakers, and even over speech by a single speaker, to facilitate a simple and accurate determination of matches between those AFDVs generated from a sample of the audio signal and corpus AFDVs generated for known speech at the phoneme and sub-phoneme level. The renormalized feature vectors can be combined with traditional feature vectors such as MFCCs, or they can be used exclusively to identify voiced, semi-voiced and unvoiced sounds.
摘要翻译：公开了一种从音频信号的窗口采样中提取的高分辨率振荡器峰值的重新归一化方法。生成基本频率和语音持续时间的变化的特征向量被大大减轻。特征向量可以在公共坐标空间内对齐，没有在扬声器之间发生的频率和持续时间的这些变化，甚至在单个扬声器的语音之间的对准，以便于简单和准确地确定从一个扬声器产生的那些AFDV之间的匹配在音素和子音素级别为已知语音生成的音频信号和语料库AFDV的样本。重归一化特征向量可以与诸如MFCC的传统特征向量组合，或者它们可以专门用于识别有声，半声和无声的声音。

IPRDB

热门服务

关于我们

友情链接

联系方式