學術產出-國科會研究計畫

文章檢視/開啟

書目匯出

Google ScholarTM

政大圖書館

引文資訊

TAIR相關學術產出

題名 睡眠研究中鼾聲之聲學分析
其他題名 Acoustic Analysis of Snoring Sounds in Sleep Studies
作者 廖文宏;楊建銘
貢獻者 政治大學資訊科學系
行政院國家科學委員會
關鍵詞 睡眠研究; 鼾聲分析; 阻塞型睡眠呼吸中止症
Audio classification; snoring analysis; OSA
日期 2006
上傳時間 12-十一月-2012 11:01:42 (UTC+8)
摘要 鼾聲的成因,是由於呼吸道受阻隔,導致呼吸時出現強烈震盪,產生噪音,乃影響睡眠品質的重要因素,然而睡眠研究中的標準方法:多頻道睡眠生理記錄,對於聲波訊號之搜集與分析並無統一的標準,因此有關鼾聲以及阻塞型睡眠呼吸中止症之診斷或評估,仍需依賴專業人員綜合各項相關生理指標,進行人工之判讀,缺乏簡便、可攜與自動化之監控與分析工具。準此,本研究將利用音訊處理相關技術,發展鼾聲之發音模型,探討鼾聲之基本聲學特性,訂定收音之標準程序,並研發自動化分類之工具,對整晚錄音所得之結果,自動擷取與鼾聲相關之段落,並比較不同時間之鼾聲型態。具體而言,本研究計畫將包含三大階段: (1)鼾聲的基本聲學分析(2)一般環境中之人聲分類(3)睡眠時期的鼾聲監測。關於鼾聲分類的目標,短期而言將就信號分析的結果尋求明確的指標,藉以判斷鼾聲的嚴重性以及是否有阻塞型睡眠呼吸中止症的機率;中長期而言將與相關醫療院所合作,試圖從鼾聲之聲學特性推測其成因與可能發生阻塞的位置,以協助訂定診斷與治療的方針。
In this research, 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 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. Finally, we have also developed algorithms to automatically process video captured during sleep in an attempt to reveal the relationship between posture and the characteristics of snoring sounds.
關聯 基礎研究
學術補助
研究期間:9508~ 9607
研究經費:551仟元
資料類型 report
dc.contributor 政治大學資訊科學系en_US
dc.contributor 行政院國家科學委員會en_US
dc.creator (作者) 廖文宏;楊建銘zh_TW
dc.date (日期) 2006en_US
dc.date.accessioned 12-十一月-2012 11:01:42 (UTC+8)-
dc.date.available 12-十一月-2012 11:01:42 (UTC+8)-
dc.date.issued (上傳時間) 12-十一月-2012 11:01:42 (UTC+8)-
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/55373-
dc.description.abstract (摘要) 鼾聲的成因,是由於呼吸道受阻隔,導致呼吸時出現強烈震盪,產生噪音,乃影響睡眠品質的重要因素,然而睡眠研究中的標準方法:多頻道睡眠生理記錄,對於聲波訊號之搜集與分析並無統一的標準,因此有關鼾聲以及阻塞型睡眠呼吸中止症之診斷或評估,仍需依賴專業人員綜合各項相關生理指標,進行人工之判讀,缺乏簡便、可攜與自動化之監控與分析工具。準此,本研究將利用音訊處理相關技術,發展鼾聲之發音模型,探討鼾聲之基本聲學特性,訂定收音之標準程序,並研發自動化分類之工具,對整晚錄音所得之結果,自動擷取與鼾聲相關之段落,並比較不同時間之鼾聲型態。具體而言,本研究計畫將包含三大階段: (1)鼾聲的基本聲學分析(2)一般環境中之人聲分類(3)睡眠時期的鼾聲監測。關於鼾聲分類的目標,短期而言將就信號分析的結果尋求明確的指標,藉以判斷鼾聲的嚴重性以及是否有阻塞型睡眠呼吸中止症的機率;中長期而言將與相關醫療院所合作,試圖從鼾聲之聲學特性推測其成因與可能發生阻塞的位置,以協助訂定診斷與治療的方針。en_US
dc.description.abstract (摘要) In this research, 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 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. Finally, we have also developed algorithms to automatically process video captured during sleep in an attempt to reveal the relationship between posture and the characteristics of snoring sounds.
-
dc.language.iso en_US-
dc.relation (關聯) 基礎研究en_US
dc.relation (關聯) 學術補助en_US
dc.relation (關聯) 研究期間:9508~ 9607en_US
dc.relation (關聯) 研究經費:551仟元en_US
dc.subject (關鍵詞) 睡眠研究; 鼾聲分析; 阻塞型睡眠呼吸中止症en_US
dc.subject (關鍵詞) Audio classification; snoring analysis; OSA-
dc.title (題名) 睡眠研究中鼾聲之聲學分析zh_TW
dc.title.alternative (其他題名) Acoustic Analysis of Snoring Sounds in Sleep Studiesen_US
dc.type (資料類型) reporten