位置：成果数据库 > 会议 > 会议详情页
A NEW METHOD FOR SAMPLE SELECTION IN ACTIVE LEARNING
  • 所属机构名称：北京邮电大学
  • 成果类型：会议
  • 相关项目：广播语音声学建模中的主动学习研究
同会议论文项目
广播语音声学建模中的主动学习研究
期刊论文 11 会议论文 21
同项目会议论文
Improved Algorithms of Music Information Retrieval based on Audio Fingerprint
Automatic Segmentation and Labeling Based On Boundary Type for Mandarin Chinese Speech
A Confusion Network Based Confidence Measure for Active Learning in Speech Recognition
Semi-supervised Learning for Automatic Audio Events Annotation Using TSVM
Improved Algorithms of Music Information Retrieval based on Audio Fingerprint
Speech Enhancement Using Modified Spectral Subtraction Based on Cepstral Smoothing
A New Method for Discriminative Model Combination in Speech Recognition
An Automatic Labeling System for Broadcast News Based on Recognition and Dynamic Programming
AN IMPROVED RECURSIVE ALGORITHM FOR AUTOMATIC ALIGNMENT OF COMPLEX LONG AUDIO
A mandarin speech recognition result evaluation algorithm on mixed words
语音识别可信度中的特征提取与特征选择问题研究
A New Algorithm for Mixture Splitting Based On DBC
基于LDA的词聚类语言模型
A New Method for MLE Training Based on Multi-model Weighting
A KLD Based Method for Initial Set Selection in Active learning
Novel Active Learning Sample Evaluation Method Based on Multi-level Confusion Networks
Automatic Segmentation and Labeling Based On Boundary Type for Mandarin Chinese Speech
A Confusion Network Based Confidence Measure for Active Learning in Speech Recognition
Semi-supervised Learning for Automatic Audio Events Annotation Using TSVM
A New Method for Model Selection in Speech Recognition