Fast NMF based approach and improved VQ based approach for speech recognition from mixed sound
Fast NMF based approach and improved VQ based approach for speech recognition from mixed sound
复制标题
DOI：
--
复制
发表时间：
2012-12
期刊：
影响因子：
--
通讯作者：
Shoichi Nakano;Kazumasa Yamamoto;S. Nakagawa
中科院分区：
文献类型：
--
作者：
Shoichi Nakano;Kazumasa Yamamoto;S. Nakagawa
我们已经考虑了一种语音识别方法的混合声音，包括语音和音乐，只删除基于矢量量化（VQ）和非负矩阵分解（NMF）的音乐。本文描述了基于NMF的快速音乐消除算法，并利用矢量量化方法进行了改进。对于孤立词的识别，使用干净的语音模型，字错误减少率的46%的改善相比，没有删除音乐的情况下。此外，在10 dB下获得了接近干净语音识别的高识别率。对于多条件的情况下，我们提出的方法减少了50%的错误率相比，多条件模型。
We have considered a speech recognition method for mixed sound, consisting of speech and music, that removes only the music based on vector quantization (VQ) and non-negative matrix factorization (NMF). This paper describe fast calculation technique of music removal based on NMF and improvement using a VQ method. For isolated word recognition using the clean speech model, an improvement of 46% word error reduction rate was obtained compared with the case of not removing music. Furthermore, a high recognition rate, close to clean speech recognition was obtained at 10 dB. For the case of the multi-conditions, our proposed method reduced the error rate of 50% compared with the multi-conditions model.