Dissertation > Excellent graduate degree dissertation topics show

Research on Active Learning and Semi-supervised Learning Methods in Speech Emotion Recognition

Author: ZhangXiaoPeng
Tutor: LiHaiFeng
School: Harbin Institute of Technology
Course: Computer technology
Keywords: Speech Emotion Recognition Active Learning Semi-supervisedlearning dimensional emotion graph regularized methods
CLC: TP391.1
Type: Master's thesis
Year: 2013
Downloads: 1
Quote: 0
Read: Download Dissertation

Abstract


Speech emotion recognition, especially large-scale emotion recognitionrequires a lot of emotional speech annotation. Numerous unlabeled naturalspeeches can be easily collected, while the annotation is high cost, especially forthe dimensional labeling. This paper studied active learning and semi-supervisedlearning in both discrete emotion model and dimensional emotion model. Activelearning focuses on how to choose the most informative data for humanannotation, while the semi-supervised learning focuses on how to label emotionalspeech automatically by itself. The goal is to achieve high performance at lowannotation cost.Aiming at how to choose the most informative emotional speech for humanannotation, thus effectively reducing the annotation costs, we studied activelearning method in speech emotion recognition. Under discrete emotion model,considering that the output probability is a measure of classification certainty, westudied least confidence, margin sampling and information entropy methodsbased on output probability. Moreover, we studied query by committee methodby constructing a committee of models to represent different regions of versionspace. Vote entropy and K-L divergence were applied to measure thedisagreement. Larger disagreement indicated more information. Underdimensional emotion model, output probabilities cannot be directly estimated inregression problems. In this paper, we studied least confidence method thatdiscretized the continuous annotation, and then approximately evaluated theinformativeness using a discrete classification model. Similarly, we also studiedquery by committee method by constructing a committee of regression model andestimated speech informativeness using output variance.Aiming at how to combine unlabeled data to improve learning performance,we studied semi-supervised learning method in speech emotion recognition.Under the discrete emotion model, considering that the high output probabilityspeech is the most certainty, we explored the self-learning method based onconfidence thresholds and the co-training method using different feature subset.Moreover, we used graph Laplacian to represent the similarity between two emotion data and propagate the label to surrounding vertex based on theirsimilarity, namely label propagation algorithm. Under dimensional emotionmodel, we explored the graph regularized method in speech emotion recognitionbased on manifold assumption. Considering squared loss of labeled data andmodel complexity norm in Hilbert space, we studied the LapRLS which usedLaplacian matrix defined on the manifold structure as a regularization term, andthe CoRLS which used two prediction functions’ disagreement based on twodifferent views as a regularization term.Finally, we studied the combination of active learning and semi-supervisedlearning methods under the discrete emotion model. The combination methodaugmented the training set by selecting least confidence speech for humanannotation and highest confidence speech annotated by the model.

Related Dissertations

  1. Research on Feature Selection and Construction in Emotion Speech Recognition,TP18
  2. Semi-supervised Learning and Active Learning of Sentiment Classification Coupled with Domain Knowledge,TP181
  3. Research on cross-language text categorization,TP391.1
  4. Manifold learning variance minimization,TP181
  5. Domain-specific Chinese term extraction,TP391.1
  6. Research of Query-by-committee Method of Active Learning,TP181
  7. The Research on Marine Literature Categorization and Labeling Minimization,TP391.1
  8. Research Based on an Active Relevance Feedback Mechanism in Content-Based Image Retrieval,TP391.3
  9. Research on Content-Based Image Retrieval,TP391.41
  10. Research on Intrusion Detection Based on Semi-supervised Learning,TP393.08
  11. The Web Pages Classification Method Based on Semi-supervised Support Vector Machine,TP393.092
  12. Svm-based Active Feedback in Image Retrieval Using Clustering,TP391.41
  13. Combining Semi-supervised and Active Learning for Image Retrieval,TP391.41
  14. Theory and Algorithms for Nearest Neighbor Method and Multiple-view Learning,TP181
  15. Research and Application on Graph Transduction,TP391.41
  16. Semi-supervised Active Learning for Relevance Feedback in Image Retrieval,TP391.41
  17. The application of a small amount of support vector machine classification labeled samples,TP18
  18. Obstacle detection for the wild semi-supervised Active Learning Research,TP181
  19. Machine Learning for Content Based Image Retrieval,TP391.3
  20. The Research of an Automatic Recommended Model of Reviewer for a Submission System,TP182
  21. Based on positive and unlabeled samples for semi-supervised classification,TP181

CLC: > Industrial Technology > Automation technology,computer technology > Computing technology,computer technology > Computer applications > Information processing (information processing) > Text Processing
© 2012 www.DissertationTopic.Net  Mobile