Using missing feature theory to actively select features for robust speech recognition with interruptions, filtering and noise KN-37
Using missing feature theory to actively select features for robust speech recognition with interruptions, filtering and noise KN-37
复制标题
使用缺失特征理论主动选择特征，实现具有中断、过滤和噪声的鲁棒语音识别 KN-37
DOI：
--
复制
发表时间：
1997
期刊：
影响因子：
--
通讯作者：
B. Carlson
中科院分区：
文献类型：
--
作者：
R. Lippmann;B. Carlson
用安静的宽带语音训练的语音识别器在高通、低通和陷波滤波、噪声和语音输入中断的情况下会急剧退化。提出了一种补偿这些退化的新的简单方法，该方法使用梅尔滤波器组（MFB）幅度作为输入特征和缺失特征理论来动态修改隐马尔可夫模型识别器中执行的概率计算。当提供由于过滤或掩蔽而丢失的特征的身份时，大型独立于说话者的数字识别任务的识别准确度通常会从 50% 以下上升到 95% 以上。这些有希望的结果表明未来需要不断估计 MFB 频段内的 SNR，以实现语音识别器的动态自适应。训练产生的
Speech recognizers trained with quiet wide-band speech degrade dramatically with high-pass, low-pass, and notch filtering, with noise, and with interruptions of the speech input. A new and simple approach to compensate for these degradations is presented which uses mel-filter-bank (MFB) magnitudes as input features and missing feature theory to dynamically modify the probability computations performed in Hidden Markov Model recognizers. When the identity of features missing due to filtering or masking is provided, recognition accuracy on a large talker-independent digit recognition task often rises from below 50% to above 95%. These promising results suggest future work to continuously estimate SNR's within MFB bands for dynamic adaptation of speech recognizers. produced by training