Lyrics Recognition from a Singing Voice Based on Finite State Automaton for Music Information Retrieval
Lyrics Recognition from a Singing Voice Based on Finite State Automaton for Music Information Retrieval
复制标题
基于有限状态自动机的歌声歌词识别及音乐信息检索
DOI：
--
复制
发表时间：
2005
期刊：
影响因子：
--
通讯作者：
S. Makino
中科院分区：
文献类型：
--
作者：
Toru Hosoya;Motoyuki Suzuki;Akinori Ito;S. Makino
近来，已经开发了几种音乐信息检索（MIR）系统，其通过用户的歌唱声音来检索音乐片段。所有这些系统都只使用旋律信息进行检索。虽然歌词信息对于检索是有用的，但是很少有人尝试利用用户输入中的歌词。为了开发使用歌词和旋律信息的MIR系统，需要歌词识别。从歌声中识别歌词是通过与语音识别类似的技术来实现的。歌词识别与一般语音识别的区别在于，输入的歌词是数据库中歌曲歌词的一部分。为了最大限度地利用语言约束，我们描述了识别语法使用有限状态自动机（FSA），只接受数据库中的歌词。此外，我们进行了一个“唱歌的声音适应”使用扬声器适应技术。在我们的实验结果中，约86%的检索准确率。
Recently, several music information retrieval (MIR) systems have been developed which retrieve musical pieces by the user’s singing voice. All of these systems use only the melody information for retrieval. Although the lyrics information is useful for retrieval, there have been few attempts to exploit lyrics in the user’s input. In order to develop a MIR system that uses lyrics and melody information, lyrics recognition is needed. Lyrics recognition from a singing voice is achieved by similar technology to that of speech recognition. The difference between lyrics recognition and general speech recognition is that the input lyrics are a part of the lyrics of songs in a database. To exploit linguistic constraints maximally, we described the recognition grammar using a finite state automaton (FSA) that accepts only lyrics in the database. In addition, we carried out a “singing voice adaptation” using a speaker adaptation technique. In our experimental results, about 86% retrieval accuracy was obtained.
影响因子：
4.3
作者：
LEGGETTER, CJ;WOODLAND, PC
通讯作者：
WOODLAND, PC