Model-based compensation of the additive noise for continuous speech recognition. experiments using the Aurora II database and tasks
Model-based compensation of the additive noise for continuous speech recognition. experiments using the Aurora II database and tasks
复制标题
用于连续语音识别的加性噪声的基于模型的补偿。
DOI：
10.21437/eurospeech.2001-78
复制
发表时间：
2001
期刊：
影响因子：
--
通讯作者：
A. Peinado
中科院分区：
文献类型：
--
作者：
J. C. Segura;Á. D. L. Torre;M. C. Benítez;A. Peinado
在本文中，我们采用基于模型的补偿方法来取消自动语音识别系统中加性噪声的效果。该方法是在统计框架中提出的，以便在观察到的嘈杂语音的情况下执行噪声效应的最佳补偿，该模型描述了在干净的参考环境中记录的语音的统计数据，并在嘈杂的识别环境中对噪声的估计估计。使用要识别的句子的第一帧估算噪声，并执行逐帧噪声补偿算法，以便补偿程序不限制实时语音识别系统，并且与基于分布式的新兴技术兼容语音识别。我们使用Aurora II数据库在噪声条件下进行了识别实验，以作为该数据库开发的识别任务作为标准参考。已经进行了实验，包括清洁和多条件训练方法。实验结果表明，当应用了基于模型的补偿方法时，识别性能的改善。
In this paper we apply a model-based compensation method to cancel the effect of the additive noise in Automatic Speech Recognition systems. The method is formulated in a statistical framework in order to perform the optimal compensation of the noise effect given the observed noisy speech, a model describing the statistics of the speech recorded in a clean reference environment and the estimation of the noise in the noisy recognition environment. The noise is estimated using the first frames of the sentence to be recognized and a frame-by-frame noise compensation algorithm is performed, so that the compensation procedure does not constrain real-time speech recognition systems and is compatible with emerging technologies based on distributed speech recognition. We have performed recognition experiments under noise conditions using the AURORA II database for the recognition tasks developed for this database as a standard reference. Experiments have been carried out including both, clean and multicondition training approaches. The experimental results show the improvements in the recognition performance when the proposed model-based compensation method is applied.