该文提出了一种基于能量分布和共振峰结构的汉语鼻音检测方法,该方法首先基于Seneff听觉谱提取了一组描述音段能量分布和共振峰结构的特征参数,然后采用支持向量机模型进行检测和分类,得到候选的鼻音,最后根据音段持续时间、前端韵母能量、高低频能量差、中低频能量比等特征对候选的鼻音进行后处理,去除插入错误,提高鼻音检测的准确率。实验结果表明,干净语音鼻音检测准确率可以达到90.4%,信噪比10dB的语音鼻音检测准确率可达到84.4%以上。
Abstract
A Chinese nasal detection method based on energy distribute and formant structure characteristics is presented. According to this method, the energy distribute and formant structure features are first acquired by Seneffs auditory spectrum, then SVM classifier is combined to realize candidate nasal detection. Finally, post processing is conducted to remove the insertion errors in accordance with parameters of segment duration, front vowel energy, energy difference of high and low frequency, energy ratio of middle and low frequency, etc. The experimental results show that the accuracy is 90.4% for clean speech, above 84.4% for noisy speech with the SNR of 10dB.
Key wordsnasal detection; energy distribute; formant structure; Seneff auditory model
关键词
鼻音检测 /
能量分布 /
共振峰结构 /
Seneff听觉模型
{{custom_keyword}} /
Key words
nasal detection /
energy distribute /
formant structure /
Seneff auditory model
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Chin-Hui.Lee. From knowledge-ignorant to knowledge-rich modeling: A new speech research paradigm for next generation automatic speech recognition[C]//Proceedings of ICSLP Keynote speech, 2004.
[2] S. R. Mahadeva Prasanna, B.V. Sandeep Reddy, P. Krishnamoorthy. Vowel onset point detection using source, spectral peaks and modulation spectrum energies[J]. IEEE Transactions on Audio, Speech and Language Processing,2009,17(4):556-565.
[3] Almpanidis G., Kotti M., Kotropoulos C.. Robust Detection of Phone Boundaries Using Model Selection Criteria With Few Observations[J]. IEEE Transactions on Audio, Speech, and Language Processing, 2009,17(2):287-298.
[4] K.Y. Leung, M. Siu. Speech Recognition Using Combined Acoustic and Articulatory Information with Retraining of Acoustic Model Parameters[C]//Proceedings of ICSLP 2002,3: 2117-2120.
[5] M.Hasegawa-Johnson, J.Baker, S.Borys, et.al. Landmark-based speech recognition:Report of the 2004 Johns Hopkins summer workshop[C]//Proceedings of ICASSP,2005: 213-216.
[6] J. Morris, E. Fosler-Lussier. Further experiments with detector-based conditional random fields in phonetic recognition[C]//Proceedings of ICASSP, April, 2007.
[7] Carla Lopes, Fernando Perdigo.A Hierarchical Broad-class Classification to Enhance Phoneme Recognition[C]//Proceedings of European Signal Processing Conference, 2009,1760-1764.
[8] Limin Du, Kenneth Noble Stevens. Automatic Detection of Landmark for Nasal Consonants from Speech Waveform[C]//Proceedings of ICSLP 2006.
[9] Sarah E. Borys. An SVM Front-end Landmark Speech Recognition System[M]. University of Illinois, 2008.
[10] Stephanie Seneff. A joint synchrony/mean-rate model of auditory speech processing [J]. Journal of Phonetics, 1988,16: 55-76.
[11] Stephanie Seneff. Pitch and Spectral Analysis of Speech Based on an Auditory Synchrony Model[M]. Cambridge, Massachusetts Institute of Technology,1985.
[12] Ahmed M. Abdelatty Ali. Auditory-Based Speech Processing Based on the Average Localized Synchrony Detection [C]//Proceedings of Acoustic Speech and Signal Processing (ICASSP), 2000,3:1623-1626.
[13] Ahmed M. Abdelatty Ali, Jan Van der Spiegel, Paul Mueller. Robust Auditory-Based Speech Processing Using the Average Localized Synchrony Detection[J]. IEEE Transaction on Signal and Audio Processing, 2001, 10:279-292.
[14] 语音与语言学词典[M]. 上海: 上海辞书出版社,1981.
[15] Steve Young.The HTK Book(for HTK Version 3.4) [M].Cambridge University Engineering Department,2006: 289.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家高技术研究发展(863)计划资助项目(2006AA01Z146),国家自然科学基金资助项目(60872142)
{{custom_fund}}
PDF(2636 KB)
