Exploring Music Contents
Exploring Music Contents
复制标题
探索音乐内容
DOI：
10.1007/978-3-642-23126-1_10
复制
发表时间：
2011
期刊：
影响因子：
--
通讯作者：
Barthet M
中科院分区：
文献类型：
--
作者：
Barthet M
我们提出了两个语音/音乐的歧视方法，使用音色模型和测量他们的表现上3小时长的数据库广播播客从BBC。在第一种方法中，使用中值滤波对用自动音色识别（ATR）模型获得的机器估计分类进行后处理。分类系统（LSF/K-means）使用两个不同的分类级别进行训练，一个是高级（语音，音乐），另一个是低级（男性和女性语音，古典，爵士，摇滚和流行）。第二种方法结合自动结构分割和音色识别（ASS/ATR）。ASS使用HMM和软K均值算法评估特征分布（MFCC，RMS）之间的相似性。这两种方法进行了评估，在语义（相对正确的重叠RCO），和时间（边界检索F-措施）的水平。ASS/ATR方法获得了最好的结果（平均RCO为94.5%，边界F-测量为50.1%）。这些性能相比，得到了有利的基于SVM的技术提供了一个很好的基准的最先进的。
We propose two speech/music discrimination methods using timbre models and measure their performances on a 3 hour long database of radio podcasts from the BBC. In the first method, the machine estimated classifications obtained with an automatic timbre recognition (ATR) model are post-processed using median filtering. The classification system (LSF/K-means) was trained using two different taxonomic levels, a high-level one (speech, music), and a lower-level one (male and female speech, classical, jazz, rock & pop). The second method combines automatic structural segmentation and timbre recognition (ASS/ATR). The ASS evaluates the similarity between feature distributions (MFCC, RMS) using HMM and soft K-means algorithms. Both methods were evaluated at a semantic (relative correct overlap RCO), and temporal (boundary retrieval F-measure) levels. The ASS/ATR method obtained the best results (average RCO of 94.5% and boundary F-measure of 50.1%). These performances were favourably compared with that obtained by a SVM-based technique providing a good benchmark of the state of the art.