Speech recognition based on Itakura-Saito divergence and dynamics/sparseness constraints from mixed sound of speech and music by non-negative matrix factorization
Speech recognition based on Itakura-Saito divergence and dynamics/sparseness constraints from mixed sound of speech and music by non-negative matrix factorization
复制标题
DOI：
10.21437/interspeech.2014-160
复制
发表时间：
2014
期刊：
影响因子：
--
通讯作者：
Naoaki Hashimoto;Shoichi Nakano;Kazumasa Yamamoto;S. Nakagawa
中科院分区：
文献类型：
--
作者：
Naoaki Hashimoto;Shoichi Nakano;Kazumasa Yamamoto;S. Nakagawa
我们考虑了一种基于非负矩阵分解（NMF）的混合声音语音识别方法，该方法仅去除音乐，该混合声音由语音和音乐组成。我们使用Itakura-Saito散度代替Kullback-Leibler散度来比较代价函数，以及权重矩阵的动态和稀疏约束，以改善语音识别。对于使用匹配条件模型的孤立词识别，我们将单词错误率相对于没有删除音乐的情况降低了52：1%（平均从69.3%降低到85.3%）。索引术语：语音识别，混合声音，音乐去除，矢量量化，非负矩阵分解
We considered a speech recognition method for mixed sound, which is composed of both speech and music, that only removes music based on non-negative matrix factorization (NMF). We used Itakura-Saito divergence instead of Kullback-Leibler divergence to compare the cost function, and the dynamics and sparseness constraints of a weight matrix to improve speech recognition. For isolated word recognition using the matched condition model, we reduced the word error rate of 52:1% relative from the case that didn’t remove music (on average, from 69.3% to 85.3%). Index Terms: speech recognition, mixed sound, music removal, vector quantization, non-negative matrix factorization