Robust speech/non-speech detection using LDA applied to MFCC for continuous speech recognition
Robust speech/non-speech detection using LDA applied to MFCC for continuous speech recognition
复制标题
使用 LDA 进行鲁棒语音/非语音检测，应用于 MFCC 进行连续语音识别
DOI：
--
复制
发表时间：
2001
期刊：
影响因子：
--
通讯作者：
L. Mauuary
中科院分区：
文献类型：
--
作者：
Arnaud Martin;Delphine Charlet;L. Mauuary
连续语音识别应用程序需要精确的检测，因为要识别的单词数量是未知的，并且词汇单词可能很短。语音/非语音检测必须对边界精度具有鲁棒性。在这项工作中，一个新的方法来评估检测算法的连续语音识别。将能量参数结合线性判别分析（LDA）的Mel倒谱系数（MFCC）语音/非语音检测算法与基于信噪比（SNR）的语音/非语音检测算法进行比较。LDA应用于MFCC语音/非语音检测，提高了在噪声环境中和连续语音识别应用中的识别性能。
Continuous speech recognition applications need precise detection because the number of words to recognize is unknown and vocabulary words can be short. The speech/non-speech detection must be robust to the boundary precision. In this work, a new approach to evaluate detection algorithm for continuous speech recognition is presented. The speech/non-speech detection using energy parameter combined with a Linear Discriminant Analysis (LDA) applied to Mel Frequency Cepstrum Coefficients (MFCC) is compared to the algorithm based on signal to noise ratio (SNR). The LDA applied to MFCC for speech/non-speech detection improves recognition performance in noisy environment and for continuous speech recognition applications.