Dissertation > Excellent graduate degree dissertation topics show

The Study of the Articulatory Mechanism of Emotional Speech

Author: ZhengLu
Tutor: WangHong
School: Shandong Normal University
Course: Computer Software and Theory
Keywords: Emotional Speech The electromagnetic sound Miriam (EMA) Principal Component Analysis Vowel sounds
CLC: TP391.41
Type: Master's thesis
Year: 2011
Downloads: 50
Quote: 0
Read: Download Dissertation

Abstract


The difference in emotional speech synthesis research in the past, most of the proceeding from the speech signal, analysis of the acoustic parameters and thus the speech synthesis. At present, English, Japanese, German, Swedish and other emotional voice more Chinese emotional speech research also belong to just the initial stage. Although the expression of emotions with the world commonality, but the performance of the common emotional language of tonal languages ??and accents, their intonation patterns are very different. The study found many phoneticians English rhythm will affect pronunciation. With the perfection of speech synthesis technology, voice rhythm more and more attention, however, when mixed with emotion, rhythm and other information in Mandarin, it is quite difficult to study pronunciation mechanism. This paper by electromagnetic sounder instrument (EMA) recorded a female pronunciation neutral emotional data, pronunciation pronunciation data obtained by electromagnetic sounder instrument. We mainly analyze the standard of Putonghua vowels [aiuyeo] different tone in the narrow focus of pronunciation data, analysis of each vowel in a narrow focus mode tone tuning for each vowel acoustics in under a different tone Baseband parameters F0, formant data F1, F2, and F3 were analyzed. The paper first introduces the research of emotional speech pronunciation, Mandarin emotional speech pronunciation mechanism is not a lot. Secondly, the use of the electromagnetic sounder instrument equipment physiological pronunciation data collection, as well as data preprocessing, proposed to extract vowel target Target algorithm and its implementation. Next, each vowel pronunciation data and acoustic data in the physiological having Significance analysis of statistical analysis, and on the relationship between the two compared. Subsequently using principal component analysis method and the spatial distribution of the pronunciation of the vowel analysis. Using matlab to achieve the spatial distribution of vowel sounds, trying to explain the multidimensional variable under the influence of the spatial distribution of the various vowels. For each vowel found in the the physiological tuning data under different tone: the tone will affect the pronunciation and tone of each vowel tuning is not the same. The study found that each vowel When in tone3, baseband lowest value (F0), each vowel is not exactly the same data in the the three formants mode under different tones of acoustic data. Physiological pronunciation and acoustic data have some relevance. Found by principal component analysis, multidimensional variable factor can be a factor of two principal components, and the front and rear of the Factor1 behalf of pronunciation, Factor2 represents tuning the level and the tongue shape. Finally, the EMA recorded data into a visual model interface.

Related Dissertations

  1. Application of Improved Principal Component Analysis Algorithm in Course Construction,G642.4
  2. Mechanism of Preattentive Processing of Emotional Prosody Among Patients with Panic Disorder: A Mismatch Negativity Study,R749.7
  3. Research of Diagnosing Cucumber Diseases Based on Hyperspectral Imaging,S436.421
  4. The Impact of Tourism on Typical Vegetation in Luya Mountain Nature Reserve, Shanxi Province,S759.9
  5. Macaca mulatta palm morphological study of pattern ridge count,Q954
  6. Zhaoguan Lower Coal Group water inrush prediction and control techniques,TD745
  7. Research on Cultural Industrial Competitiveness of Chong Qing,F224
  8. The Research of Prairie Road Light Environment Effects on Physiological Indicators of Drivers,U491.254
  9. Research on Feature Extraction, Selection and Classification Algorithms for Pulmonary CAD,TP391.41
  10. Research Onamethod for Human Face Recognition Based on MMTD,TP391.41
  11. Competitiveness’ Evaluation and Development Strategy of the Tourism Industry in Huanggang City,F592.7
  12. Research on Rural Information Promoting Urban-rural Integration in Jiangsu Southern Area,F127;F224
  13. The Design of Information System of Power Equipment Current-carrying Faults Diagnosis,TP311.52
  14. The Research of E-government System Performance Evaluation Index System in Linyi City Based on the Principal Component Analysis,G206
  15. Face recognition algorithm based on feature fusion research,TP391.41
  16. Visual underwater target detection and recognition,TP391.41
  17. Decision fusion based on multi- model air separation process fault detection and prediction,TQ116.11
  18. EEG -based emotion recognition,TP391.4
  19. Study on F Company’s Marine Cable Distribution Mode,F426.474
  20. Data Driven Rolling Bearing Fault Diagnosis Research,TH165.3
  21. Image semantic annotation of blocks - a global feature extraction method,TP391.41

CLC: > Industrial Technology > Automation technology,computer technology > Computing technology,computer technology > Computer applications > Information processing (information processing) > Pattern Recognition and devices > Image recognition device
© 2012 www.DissertationTopic.Net  Mobile