Automatic rhythm modeling for language identification
Automatic rhythm modeling for language identification
复制标题
用于语言识别的自动节奏建模
DOI：
10.21437/eurospeech.2001-594
复制
发表时间：
2001
期刊：
影响因子：
--
通讯作者：
F. Pellegrino
中科院分区：
文献类型：
--
作者：
Jérôme Farinas;F. Pellegrino
本文提出了一种基于韵律建模的自动语言识别方法。除了语音学和音韵学之外，节奏实际上是语言识别中最有希望考虑的特征之一，但它的建模仍然是一个重要的问题。本文提出了一种节奏提取算法。对5种欧洲语言的读语音进行了实验。他们表明，显着的特征可以自动提取和有效地从原始信号建模：高斯混合建模的提取的特征的结果在81%的正确的语言识别的5种语言，使用20秒的持续时间的话语。
This paper deals with an approach to Automatic Language Identification based on rhythmic modeling. Beside phonetics and phonotactics, rhythm is actually one of the most pro mising features to be considered for language identification, but significant problems are unresolved for its modeling. In this paper, an algorithm of rhythm extraction is described. Experiments are performed on read speech for 5 European languages. They show that salient features may be automatically extracted and efficiently modeled from the raw signal: a Gaussian mixture modeling of the extracted features results in a 81 % percent of correct language identification for the 5 languages, using 20 s duration utterances.
影响因子：
56.9
作者：
Ramus, F;Hauser, MD;Mehler, J
通讯作者：
Mehler, J