位置：成果数据库 > 会议 > 会议详情页
Phone modeling and combining discriminative training for Mandarin-English bilingual speech recogniti
  • 所属机构名称：清华大学
  • 会议名称：2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010
  • 成果类型：会议
  • 会场：Dallas, TX, United states
  • 相关项目：基于内容的跨语言语音检索方法研究
作者： Qian, Yanmin|Liu, Jia|
同会议论文项目
基于内容的跨语言语音检索方法研究
期刊论文 39 会议论文 21 专利 1
同项目会议论文
A study of lattice-based spoken term detection for Chinese spontaneous speech
Combining Chinese spoken term detection systems via side-information conditioned linear logistic reg
Variant time-frequency cepstral features for speaker recognition
A fast query by humming system based on notes
A Modified Subband Post-filtering Approach for MVDR Beamformer
Channel compensation technology in differential GSV-SVM speaker verification system
Addressing the out-of-vocabulary problem for large-scale Chinese spoken term detection
Acoustic modeling based on Chinese phonetics knowledge
Fusing multiple systems into a compact lattice index for chinese spoken term detection
A novel speech recognition system-on-chip
Fractional fourier transform based auditory feature for language identification
A novel embedded speaker verification on system on chip
Robust speaker recognition in cross-channel condition
Feature selection based on mutual information for language recognition
Perturbation analysis of Mel-frequency cepstrum coefficients
A CMLLR supervector kernel for SVM language recognition
Objective assessment of speech quality by combining Bark- and Mel-scale frequency
Multi-feature combination for speaker recognition
An improved method for voice conversion based on Gaussian mixture model
Multiple Background Models for Speaker Verification