Multiexpert automatic speech recognition using acoustic and myoelectric signals
Multiexpert automatic speech recognition using acoustic and myoelectric signals
复制标题
DOI：
10.1109/tbme.2006.870224
复制
发表时间：
2006-04-01
影响因子：
4.6
通讯作者：
Lovely, DF
中科院分区：
文献类型：
--
作者：
Chan, ADC;Englehart, KB;Lovely, DF
传统的自动语音识别（ASR）系统的分类精度会显着下降，在声学噪声条件下。为了提高分类精度和增加系统的鲁棒性，实现了一个多专家ASR系统。在该系统中，声学语音信息补充有来自面部肌电信号（MES）的信息。采用一种新的专家组合方法，称为可扩展性方法，将声学ASR专家和MES ASR专家联合收割机组合。结合多个专家，这是基于证据理论的数学框架的可扩展性的方法进行了比较，Borda计数和分数为基础的方法combination.Acoustic和面部MES数据收集从5个科目，使用10个单词的词汇在18分贝的噪声范围。正如预期的那样，声学专家的性能随着声学噪声的增加而降低;声学ASR专家的分类准确率低至11.5%。加入MES ASR专家后，噪音的影响显著降低。在18 dB的噪声范围内，分类精度保持在78.8%以上，当使用可扩展性方法来联合收割机多个专家的意见。此外，在所有的噪声水平，以及最高的分类精度，除了在9分贝的噪声水平的可扩展性方法产生的分类精度高于任何个人的专家。使用Borda计数和分数为基础的多专家系统，分类精度提高相对于声学ASR专家，但分别低至51.5%和59.5%。
Classification accuracy of conventional automatic speech recognition (ASR) systems can decrease dramatically under acoustically noisy conditions. To improve classification accuracy and increase system robustness a multiexpert ASR system is implemented. In this system, acoustic speech information is supplemented with information from facial myoelectric signals (MES). A new method of combining experts, known as the plausibility method, is employed to combine an acoustic ASR expert and a MES ASR expert. The plausibility method of combining multiple experts, which is based on the mathematical framework of evidence theory, is compared to the Borda count and score-based methods of combination.Acoustic and facial MES data were collected from 5 subjects, using a 10-word vocabulary across an 18-dB range of acoustic noise. As expected the performance of an acoustic expert decreases with increasing acoustic noise; classification accuracies of the acoustic ASR expert are as low as 11.5%. The effect of noise is significantly reduced with the addition of the MES ASR expert. Classification accuracies remain above 78.8% across the 18-dB range of acoustic noise, when the plausibility method is used to combine the opinions of multiple experts. In addition, the plausibility method produced classification accuracies higher than any individual expert at all noise levels, as well as the highest classification accuracies, except at the 9-dB noise level. Using the Borda count and score-based multiexpert systems, classification accuracies are improved relative to the acoustic ASR expert but are as low as 51.5% and 59.5%, respectively.