CAJ | 학술논문

采用 HMM模型和 MFCC参数的语音识别器对普通话中声母音素的区分度不够理想,而在基于识别的计算机辅助发音教学系统中的辅音的识别具有特别重要的意义.考虑到相同发音位置不同发音方式的声母音素变化较快且高频信息较多,本文将小波分析的方法引入到提取梅尔频率倒谱参数(MFCC)的过程当中,来提高信号高频部分的时域分辨率,提出了基于小波分析的梅尔倒谱参数 MFCC_Wavelet.结合高低频不同分帧方式的 MFCC_Wavelet 参数与HMM模型的语音识别器,本文测试了 MFCC和 MFCC_Wavelet两种参数在4类发音中的区分性,实验结果表明,在相同发音位置不同发音方式、塞音与不塞音、送气音与不送气音及擦音与不擦音4类发音错误中,MFCC_Wavelet 的总体效果好于 MFCC.
채용 HMM모형화 MFCC삼수적어음식별기대보통화중성모음소적구분도불구이상,이재기우식별적계산궤보조발음교학계통중적보음적식별구유특별중요적의의.고필도상동발음위치불동발음방식적성모음소변화교쾌차고빈신식교다,본문장소파분석적방법인입도제취매이빈솔도보삼수(MFCC)적과정당중,래제고신호고빈부분적시역분변솔,제출료기우소파분석적매이도보삼수 MFCC_Wavelet.결합고저빈불동분정방식적 MFCC_Wavelet 삼수여HMM모형적어음식별기,본문측시료 MFCC화 MFCC_Wavelet량충삼수재4류발음중적구분성,실험결과표명,재상동발음위치불동발음방식、새음여불새음、송기음여불송기음급찰음여불찰음4류발음착오중,MFCC_Wavelet 적총체효과호우 MFCC.
Changing rapidly over time and with higher frequency,most consonants in Chinese Mandarin need shorter analysis frame length in automatic speech recognition (ASR).In contrast,longer frame suits vowels which are comparatively stable and with lower frequency distribution.A new speech feature MFCC-Wavelet is introduced here combining wavelet analysis with Mel frequency cepstrum coefficient (MFCC).It has higher time resolution in high frequency like wavelet analysis,and possesses Mel frequency resolution of MFCC satisfying both requirements of consonant and vowel recognition.Experiments showed better performance than MFCC to differentiate plosive/non-plosive,fricative/non-fricative and aspirated/non-aspirated phonemes in Chinese Mandarin recognition.These are important specifically in ASR-based computer-assisted pronunciation teaching (CAPT).