位置：成果数据库 > 会议 > 会议详情页
Temporal kernel neural network language model
  • 所属机构名称：清华大学
  • 会议名称：IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013
  • 时间：2013.5.5
  • 成果类型：会议
  • 相关项目：面向海量语音信息处理的垃圾过滤和数据选择方法研究
作者： Shi Y Z|Zhang W Q|Cai M|Liu J|
同会议论文项目
面向海量语音信息处理的垃圾过滤和数据选择方法研究
期刊论文 30 会议论文 21 专利 3
同项目会议论文
GPU accelerated GMM supervectors for speaker and language recognition
Complementary combination in i-vector level for language recognition
Automatic pitch accent detection using auto-context with acoustic features
Log-likelihood kernels based on adapted GMMs for speaker verification
Orthogonal space combination for text-independent speaker recognition
Robust audio fingerprinting based on local spectral luminance maxima scheme
Speaker Adaptation Based on Speaker-Dependent Eigenphone Estimation
Parallel absolute-relative feature based phonotactic language recognition
THUEE system for the Albayzin 2012 language recognition evaluation
Improving deep neural network acoustic models using unlabeled data
I-matrix for text-independent speaker recognition
Deep maxout neural networks for speech recognition
Selection of negative pool for PR-SVM in language recognition
THU-EE system fusion for the NIST 2012 speaker recognition evaluation
State-level data borrowing for low-resource speech recognition based on subspace GMMs
Compact acoustic modeling based on acoustic manifold using a mixture of factor analyzers
A dynamic gap dimension reduction approach for high order n-gram phonotactic language recognition
Discriminant local information distance preserving projection for text-independent speaker recogniti
Combining Lattice-Based Language Dependent and Independent Approaches for Out-of-Language Detection
Improve low-resource non-native mispronunciation detection with native speech by articulatory-based