請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/81230完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 鄭士康(Shyh-Kang Jeng) | |
| dc.contributor.author | JIAHAO WANG | en |
| dc.contributor.author | 王佳豪 | zh_TW |
| dc.date.accessioned | 2022-11-24T03:37:31Z | - |
| dc.date.available | 2021-08-06 | |
| dc.date.available | 2022-11-24T03:37:31Z | - |
| dc.date.copyright | 2021-08-06 | |
| dc.date.issued | 2021 | |
| dc.date.submitted | 2021-07-29 | |
| dc.identifier.citation | 1. International, A.s.D., World Alzheimer report 2019: attitudes to dementia. 2019, Alzheimer’s Disease International London, UK. 2. Mirheidari, B., et al. Computational cognitive assessment: Investigating the use of an intelligent virtual agent for the detection of early signs of dementia. in ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 2019. IEEE. 3. Liang, J., Y. Cheng, and R. Chen, Highlights of Dementia. Journal of Internal Medicine 2014. 25(3): p. 151-157 (In Chinese). 4. Joshi, A., M. Kumar, and P.K. Das. Speaker diarization: A review. in 2016 International Conference on Signal Processing and Communication (ICSC). 2016. IEEE. 5. Wang, Q., et al. Speaker diarization with lstm. in 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 2018. IEEE. 6. Chen, S. and P. Gopalakrishnan. Speaker, environment and channel change detection and clustering via the bayesian information criterion. in Proc. DARPA broadcast news transcription and understanding workshop. 1998. Virginia, USA. 7. Hoffmann, I., et al., Temporal parameters of spontaneous speech in Alzheimer's disease. International journal of speech-language pathology, 2010. 12(1): p. 29-34. 8. Martinez-Sanchez, F., et al., Expressive prosodic patterns in individuals with Alzheimer's disease. Psicothema, 2012. 24(1): p. 16-21. 9. Henry, J.D., J.R. Crawford, and L.H. Phillips, Verbal fluency performance in dementia of the Alzheimer’s type: a meta-analysis. Neuropsychologia, 2004. 42(9): p. 1212-1222. 10. Anguera, X., et al., Speaker diarization: A review of recent research. 2012. 20(2): p. 356-370. 11. Siegler, M.A., et al. Automatic segmentation, classification and clustering of broadcast news audio. in Proc. DARPA speech recognition workshop. 1997. 12. Siami-Namini, S., N. Tavakoli, and A.S. Namin. The performance of LSTM and BiLSTM in forecasting time series. in 2019 IEEE International Conference on Big Data (Big Data). 2019. IEEE. 13. Yella, S.H., A. Stolcke, and M. Slaney. Artificial neural network features for speaker diarization. in 2014 IEEE Spoken Language Technology Workshop (SLT). 2014. IEEE. 14. Weiner, J., et al. Investigating the Effect of Audio Duration on Dementia Detection Using Acoustic Features. in INTERSPEECH. 2018. 15. Weiner, J. and T. Schultz. Selecting features for automatic screening for dementia based on speech. in International Conference on Speech and Computer. 2018. Springer. 16. Satt, A., et al. Evaluation of speech-based protocol for detection of early-stage dementia. in Interspeech. 2013. 17. Chen, Y.-H., Construction and Applications of Speech Corpus of Elders with Dementia (In Chinese). Master Thesis, 2020. 18. Gish, H. and M.J.I.s.p.m. Schmidt, Text-independent speaker identification. 1994. 11(4): p. 18-32. 19. McFee, B., et al. librosa: Audio and music signal analysis in python. in Proceedings of the 14th python in science conference. 2015. Citeseer. 20. Seddik, H., A. Rahmouni, and M. Sayadi. Text independent speaker recognition using the Mel frequency cepstral coefficients and a neural network classifier. in First International Symposium on Control, Communications and Signal Processing, 2004. 2004. IEEE. 21. Shome, N., S.A. Barlaskar, and R. Laskar. Significance of frame size and frame shift on vowel on set point detection. in 2016 IEEE International Conference on Recent Trends in Electronics, Information Communication Technology (RTEICT). 2016. IEEE. 22. Cui, Z., et al., Deep bidirectional and unidirectional LSTM recurrent neural network for network-wide traffic speed prediction. 2018. 23. Yin, R., H. Bredin, and C. Barras. Speaker change detection in broadcast tv using bidirectional long short-term memory networks. in Interspeech 2017. 2017. ISCA. 24. Bredin, H. Tristounet: triplet loss for speaker turn embedding. in 2017 IEEE international conference on acoustics, speech and signal processing (ICASSP). 2017. IEEE. 25. Karam, M., F.A. Russo, and D.I.J.I.T.o.H. Fels, Designing the model human cochlea: An ambient crossmodal audio-tactile display. 2009. 2(3): p. 160-169. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/81230 | - |
| dc.description.abstract | 我們希望設計出一種現代化的護理機器人，其需要能夠具備護理失智症患者的能力，其中一項挑戰是，實現護理機器人與失智症患者之間的對話，而這需要對護理機器人進行語言理解及表達能力的訓練。與此同時，實現這些訓練需要具備大量具有高度分割準確率的失智症患者之語音片段。我們通過實驗發現，失智症患者的語音識別及語音內容的轉折點檢測比正常人要復雜得多。因此，在本文中，我們首次提出設計雙向長短期記憶人工神經網路，進行失智症患者的說話人模型之設計，並通過對時間序列數據進行建模，從根本上解決失智症患者語音內容的轉折點檢測之難題。 本文研究結果表明，一些傳統中著名的關於語音內容轉折點檢測的方法，例如貝葉斯信息量準則，其不能有效地處理目標是失智症患者這樣的特殊情況。我們確認，現階段我們所提出的模型在處理失智症患者語音內容轉折點檢測方面的準確率為28.60％，比傳統中著名的貝葉斯信息量準則模型的準確率高出16.10％。 | zh_TW |
| dc.description.provenance | Made available in DSpace on 2022-11-24T03:37:31Z (GMT). No. of bitstreams: 1 U0001-2907202104281500.pdf: 1817003 bytes, checksum: 6cadab197e94d7cd7d54c24bd2f87559 (MD5) Previous issue date: 2021 | en |
| dc.description.tableofcontents | ACKNOWLEDGEMENTS 2 中文摘要 4 ABSTRACT 5 ABBREVIATIONS 7 CONTENTS 9 FIGURE CONTENTS 10 TABLE CONTENTS 12 1. INTRODUCTION 13 2. RELATED WORK 20 3. BACKGROUNDS 24 4. DATASETS 27 5. METHODS 30 5.1 FEATURE EXTRACTION AND SELECTION 30 5.2 NEURAL NETWORK ARCHITECTURE 33 5.3 LABELING TRAINING DATA 35 6. EVALUATION METRICS OF PURITY AND COVERAGE 36 7. EVALUATION METRICS OF SEGMENTATION ACCURACY 39 8. THE CHALLENGE OF SPEAKER CHANGE DETECTION IN DEMENTIA 43 8.1 FURTHER PROCESSING SEGMENTATION RESULTS 44 9. CONCLUSION 48 10. FUTURE WORK 50 BIBLIOGRAPHY 51 APPENDIX 56 | |
| dc.language.iso | en | |
| dc.subject | 失智症 | zh_TW |
| dc.subject | 語音內容轉折點檢測 | zh_TW |
| dc.subject | 貝葉斯信息量準則 | zh_TW |
| dc.subject | 雙向長短期記憶人工神經網路 | zh_TW |
| dc.subject | Bayesian Information Criterion | en |
| dc.subject | Dementia speaker | en |
| dc.subject | Speaker change detection | en |
| dc.subject | Bidirectional Long Short-Term Memory networks | en |
| dc.title | 利用雙向長短期記憶人工神經網路的失智症患者語音分割 | zh_TW |
| dc.title | Speaker Change Detection for Patients with Dementia Using Bidirectional Long Short-Term Memory Networks | en |
| dc.date.schoolyear | 109-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 林怡君(Hsin-Tsai Liu),謝宏昀(Chih-Yang Tseng) | |
| dc.subject.keyword | 失智症,語音內容轉折點檢測,雙向長短期記憶人工神經網路,貝葉斯信息量準則, | zh_TW |
| dc.subject.keyword | Speaker change detection,Dementia speaker,Bayesian Information Criterion,Bidirectional Long Short-Term Memory networks, | en |
| dc.relation.page | 60 | |
| dc.identifier.doi | 10.6342/NTU202101878 | |
| dc.rights.note | 同意授權(限校園內公開) | |
| dc.date.accepted | 2021-07-30 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 電信工程學研究所 | zh_TW |
| 顯示於系所單位： | 電信工程學研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-2907202104281500.pdf 授權僅限NTU校內IP使用（校園外請利用VPN校外連線服務） | 1.77 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。