On the generalization of Shannon entropy for speech recognition
On the generalization of Shannon entropy for speech recognition
复制标题
香农熵在语音识别中的推广
DOI：
--
复制
发表时间：
2012
期刊：
影响因子：
--
通讯作者：
M. Liuni
中科院分区：
文献类型：
--
作者：
Nicolas Obin;M. Liuni
本文介绍了一种基于熵的频谱表示，作为音频信号噪声程度的度量，补充了音频和语音识别的标准mfc。所提出的表示是基于rsamunyi熵，这是香农熵的推广。在音频信号表示中，r<s:1>尼米熵的优点是既可以关注谐波内容（分布内的显著振幅），也可以关注噪声内容（振幅的均匀分布）。在多语言大型角色扮演视频游戏的真实场景中，在大规模的声音努力分类（低语-柔和/正常/大声喊叫）中，所提出的表示优于所有其他噪音度量——包括香农和维纳熵。在相对误差减少方面，改进幅度约为10%，对于嘈杂语音的识别尤其显著，例如低语/呼吸语音。这证实了噪声在语音识别中的作用，并将进一步扩展到语音质量分类，用于设计电子游戏中的自动语音分配系统。
This paper introduces an entropy-based spectral representation as a measure of the degree of noisiness in audio signals, complementary to the standard MFCCs for audio and speech recognition. The proposed representation is based on the Rényi entropy, which is a generalization of the Shannon entropy. In audio signal representation, Rényi entropy presents the advantage of focusing either on the harmonic content (prominent amplitude within a distribution) or on the noise content (equal distribution of amplitudes). The proposed representation outperforms all other noisiness measures - including Shannon and Wiener entropies - in a large-scale classification of vocal effort (whispered-soft/normal/loud-shouted) in the real scenario of multi-language massive role-playing video games. The improvement is around 10% in relative error reduction, and is particularly significant for the recognition of noisy speech - i.e., whispery/breathy speech. This confirms the role of noisiness for speech recognition, and will further be extended to the classification of voice quality for the design of an automatic voice casting system in video games.