Publications-Theses

題名 人聲分類之研究
Analysis and Classification of Human Sounds
作者 蘇以暄
Su, Yi-Syuan
貢獻者 廖文宏
Liao, Wen-Hung
蘇以暄
Su, Yi-Syuan
關鍵詞 人聲分類
日期 2005
上傳時間 17-Sep-2009 14:09:26 (UTC+8)
摘要 本論文探討的內容主要關於人聲分類之研究。在第一個層次,我們將家庭環境中的聲音分為說話聲、人聲非說話聲以及環境音三種。為了達到此目標,我們尋找了許多特徵並找出合適的幾個作為參數。
在夜間睡眠研究的部份,我們希望可以將整晚的睡眠資料分為鼾聲與非鼾聲兩部份,針對鼾聲的部份再深入去探討是否有呼吸中止的情況產生。若受試者是在醫院或者專業睡眠實驗室收錄資料,則會有其他睡眠生理訊號可供分析。本論文試著找出鼾聲與振動、睡姿與睡眠階段的關係並有初步的成果。
In this thesis, we describe the classification of audio signals in a smart home environment and in all-night sleep studies. In a home environment, our objective is different from most audio scene analysis projects in that we are mainly concerned with the distinction of human and non-human sounds. Toward this goal, we identify appropriate features to be extracted from the audio files and discuss the rationale behind choosing a particular feature.
In all-night sleep recording, we describe the classification of audio signals recorded in all-night sleep studies. Our objective is to separate the episodes into snoring sounds and non-snoring sounds. We perform further analysis of the extracted snoring sounds to check if the testee has apnea. With polysomnogram data, we detect the relationship between snoring sounds and other sleep signals such as snoring vibration, sleep stages and body position.
參考文獻 【1】F. Dalmasso, R. Prota, “Snoring: analysis, measurement, clinical implications and applications”, Euro Respir J., 1996, pp. 146-159.
【2】 J. E. Osborne, E. Z. Osman, P. L. Hill, B. V. Lee, C. Sparkes, “A New Acoustic Method of Differentiating Palatal from Non-palatal Snoring”, Clin. Otolaryngol 24, Blackwell Science Ltd, 1999, pp 130-133.
【3】 Jean-Julien Aucouturier and F. Pachet, “Music similarity measures: What’s the use?”, Proc. Int. Symposium on Music Info. Retrieval. (ISMIR), Paris, France, 2002.
【4】Jané R, Solà-Soler J, Fiz JA, Morera J, “Automatic Detection of Snoring Signals: Validation with Simple Snores and OSAS Patients”, Proceedings of the 22nd Annual International Conference of the IEEE EMBS, IEEE EMBS, Chicago IL, July 23-28, 2000, pp. 3129-3131.
【5】K. Wilson K, R.A. Stoohs, T.F. Mulrooney, L.J. Johnson, C. Guilleminault, Z. Huang, “The Snoring Spectrogram: Acoustic Assessment of Snoring Sound Intensity in 1,139 Individuals Undergoing Polysomnography”, Chest, March 1, 1999, pp. 762 – 770.
【6】L. Lu, H.J. Zhang, Senior Member, IEEE, and H. Jiang, “Content Analysis for Audio Classification and Segmentation,” IEEE Transactions on Speech and Audio Processing, Vol. 10, October 2002, pp 504-516.
【7】M. F. McKinney and J. Breebaart, “Features for Audio and Music Classification,” ISMIR 2003, October 2003.
【8】N.C.Saunders, P. Tassone, G. Wood, A. Norris, M. Harries, B. Kotecha,”Is Acoustic Analysis of Snoring an Alternative to Sleep Nasendoscopy?”, Clin. Otolaryngol, 29, Blackwell Publishing Ltd, 2004, pp 242-246.
【9】R. Vertegaal, “Attentive User Interfaces,” Communications of the ACM, Vol. 46, NO. 3, March 2003.
【10】Z. Liu, J. Huang, Y. Wang, and T. Chen, “Audio Feature Extraction & Analysis for Scene Classification,” IEEE Signal Processing Society 1997 Workshop on Multimedia Signal Processing, June 1997.
【11】劉勝義,「臨床睡眠檢查學」,合記出版社, 民國93年10月
【12】台灣睡眠醫學學會 http://www.tssm.org.tw/
描述 碩士
國立政治大學
資訊科學學系
93753004
94
資料來源 http://thesis.lib.nccu.edu.tw/record/#G0937530041
資料類型 thesis
dc.contributor.advisor 廖文宏zh_TW
dc.contributor.advisor Liao, Wen-Hungen_US
dc.contributor.author (Authors) 蘇以暄zh_TW
dc.contributor.author (Authors) Su, Yi-Syuanen_US
dc.creator (作者) 蘇以暄zh_TW
dc.creator (作者) Su, Yi-Syuanen_US
dc.date (日期) 2005en_US
dc.date.accessioned 17-Sep-2009 14:09:26 (UTC+8)-
dc.date.available 17-Sep-2009 14:09:26 (UTC+8)-
dc.date.issued (上傳時間) 17-Sep-2009 14:09:26 (UTC+8)-
dc.identifier (Other Identifiers) G0937530041en_US
dc.identifier.uri (URI) https://nccur.lib.nccu.edu.tw/handle/140.119/32731-
dc.description (描述) 碩士zh_TW
dc.description (描述) 國立政治大學zh_TW
dc.description (描述) 資訊科學學系zh_TW
dc.description (描述) 93753004zh_TW
dc.description (描述) 94zh_TW
dc.description.abstract (摘要) 本論文探討的內容主要關於人聲分類之研究。在第一個層次,我們將家庭環境中的聲音分為說話聲、人聲非說話聲以及環境音三種。為了達到此目標,我們尋找了許多特徵並找出合適的幾個作為參數。
在夜間睡眠研究的部份,我們希望可以將整晚的睡眠資料分為鼾聲與非鼾聲兩部份,針對鼾聲的部份再深入去探討是否有呼吸中止的情況產生。若受試者是在醫院或者專業睡眠實驗室收錄資料,則會有其他睡眠生理訊號可供分析。本論文試著找出鼾聲與振動、睡姿與睡眠階段的關係並有初步的成果。
zh_TW
dc.description.abstract (摘要) In this thesis, we describe the classification of audio signals in a smart home environment and in all-night sleep studies. In a home environment, our objective is different from most audio scene analysis projects in that we are mainly concerned with the distinction of human and non-human sounds. Toward this goal, we identify appropriate features to be extracted from the audio files and discuss the rationale behind choosing a particular feature.
In all-night sleep recording, we describe the classification of audio signals recorded in all-night sleep studies. Our objective is to separate the episodes into snoring sounds and non-snoring sounds. We perform further analysis of the extracted snoring sounds to check if the testee has apnea. With polysomnogram data, we detect the relationship between snoring sounds and other sleep signals such as snoring vibration, sleep stages and body position.
en_US
dc.description.tableofcontents CHAPTER 1 Introdoction 1
1.1 Overview and backrounds 2
1.2 Related work 6
1.2.1 Human sounds classification in a smart home environment 6
1.2.2 Classification of audio signals in all-night sleep studies 7
CHAPTER 2 Human sounds classification 11
2.1 Audio feature analysis 11
2.1.1 Fundamental frequency 11
2.1.2 Zero-crossing rate 12
2.1.3 Autocorrelaiton 13
2.1.4 Spectral centroid 15
2.1.5 Entropy 15
2.1.6 Formant frequency 17
2.2 Hierarchical audio classification 17
CHAPTER 3 Audio signal classification in all-night sleep studies 20
3.1 Acoustics of snoring 20
3.2 Snoring sounds segmentation 23
3.3 Sounds classification 24
3.4 Grouping of snoring episodes 25
3.4.1 KL-divergence 26
3.4.2 The entropy of spectrogram 28
CHAPTER 4 Experimental results 29
4.1 Classification of human sounds in a smart home environment 29
4.2 Classification of audio signals in all-night sleep recording 30
CHAPTER 5 Pysiological signals and snoring sounds 33
5.1 Snoring vibration 33
5.2 Sleep stages 43
5.3 Body position 60
CHAPTER 6 Conclusions 68
References 70
zh_TW
dc.format.extent 81211 bytes-
dc.format.extent 102420 bytes-
dc.format.extent 124915 bytes-
dc.format.extent 203440 bytes-
dc.format.extent 1200320 bytes-
dc.format.extent 2673666 bytes-
dc.format.extent 90010 bytes-
dc.format.extent 1702488 bytes-
dc.format.extent 72742 bytes-
dc.format.extent 134863 bytes-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.language.iso en_US-
dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0937530041en_US
dc.subject (關鍵詞) 人聲分類zh_TW
dc.title (題名) 人聲分類之研究zh_TW
dc.title (題名) Analysis and Classification of Human Soundsen_US
dc.type (資料類型) thesisen
dc.relation.reference (參考文獻) 【1】F. Dalmasso, R. Prota, “Snoring: analysis, measurement, clinical implications and applications”, Euro Respir J., 1996, pp. 146-159.zh_TW
dc.relation.reference (參考文獻) 【2】 J. E. Osborne, E. Z. Osman, P. L. Hill, B. V. Lee, C. Sparkes, “A New Acoustic Method of Differentiating Palatal from Non-palatal Snoring”, Clin. Otolaryngol 24, Blackwell Science Ltd, 1999, pp 130-133.zh_TW
dc.relation.reference (參考文獻) 【3】 Jean-Julien Aucouturier and F. Pachet, “Music similarity measures: What’s the use?”, Proc. Int. Symposium on Music Info. Retrieval. (ISMIR), Paris, France, 2002.zh_TW
dc.relation.reference (參考文獻) 【4】Jané R, Solà-Soler J, Fiz JA, Morera J, “Automatic Detection of Snoring Signals: Validation with Simple Snores and OSAS Patients”, Proceedings of the 22nd Annual International Conference of the IEEE EMBS, IEEE EMBS, Chicago IL, July 23-28, 2000, pp. 3129-3131.zh_TW
dc.relation.reference (參考文獻) 【5】K. Wilson K, R.A. Stoohs, T.F. Mulrooney, L.J. Johnson, C. Guilleminault, Z. Huang, “The Snoring Spectrogram: Acoustic Assessment of Snoring Sound Intensity in 1,139 Individuals Undergoing Polysomnography”, Chest, March 1, 1999, pp. 762 – 770.zh_TW
dc.relation.reference (參考文獻) 【6】L. Lu, H.J. Zhang, Senior Member, IEEE, and H. Jiang, “Content Analysis for Audio Classification and Segmentation,” IEEE Transactions on Speech and Audio Processing, Vol. 10, October 2002, pp 504-516.zh_TW
dc.relation.reference (參考文獻) 【7】M. F. McKinney and J. Breebaart, “Features for Audio and Music Classification,” ISMIR 2003, October 2003.zh_TW
dc.relation.reference (參考文獻) 【8】N.C.Saunders, P. Tassone, G. Wood, A. Norris, M. Harries, B. Kotecha,”Is Acoustic Analysis of Snoring an Alternative to Sleep Nasendoscopy?”, Clin. Otolaryngol, 29, Blackwell Publishing Ltd, 2004, pp 242-246.zh_TW
dc.relation.reference (參考文獻) 【9】R. Vertegaal, “Attentive User Interfaces,” Communications of the ACM, Vol. 46, NO. 3, March 2003.zh_TW
dc.relation.reference (參考文獻) 【10】Z. Liu, J. Huang, Y. Wang, and T. Chen, “Audio Feature Extraction & Analysis for Scene Classification,” IEEE Signal Processing Society 1997 Workshop on Multimedia Signal Processing, June 1997.zh_TW
dc.relation.reference (參考文獻) 【11】劉勝義,「臨床睡眠檢查學」,合記出版社, 民國93年10月zh_TW
dc.relation.reference (參考文獻) 【12】台灣睡眠醫學學會 http://www.tssm.org.tw/zh_TW