|
|
1 |
Using Duration Information in Cantonese Connected-Digit Recognition
|
Zhu, Yu、Lee, Tan
|
Explicit Duration Modeling
、
Hidden Markov Models
、
Cantonese
、
Connected-Digit Recognition
、
Duration Features
、
THCI Core
|
|  |
|
|
2 |
Modeling Cantonese Pronunciation Variations for Large-Vocabulary Continuous Speech Recognition
|
Lee, Tan、Kam, Patgi、Soong, Frank K.
|
Automatic Speech Recognition
、
Cantonese
、
Pronunciation Variation
、
THCI Core
|
| |
|
|
3 |
A Maximum Entropy Approach for Semantic Language Modeling
|
Chueh, Chuang-hua、Wang, Hsin-min、Chien, Jen-tzung
|
Language Modeling
、
Maximum Entropy
、
Latent Semantic Analysis
、
Speech Recognition
、
THCI Core
|
| |
|
|
4 |
Robust Target Speaker Tracking in Broadcast TV Streams
|
Bai, Junmei、Jiang, Hongchen、Zhang, Shilei、Zhang, Shuwu、Xu, Bo
|
Speaker Tracking
、
Audio Segmentation
、
Entropy
、
GMM
、
THCI Core
|
| |
|
|
5 |
A Fast Framework for the Constrained Mean Trajectory Segment Model by Avoidance of Redundant Computation on Segment
|
Tang, Yun、Liu, Wenju、Zhang, Yiyan、Xu, Bo
|
Speech Recognition
、
Mandarin Digit String Recognition
、
Segment Model
、
THCI Core
|
| |
|
|
6 |
Voice Activity Detection Based on Auto-Correlation Function Using Wavelet Transform and Teager Energy Operator
|
Wu, Bing-fei、Wang, Kun-ching
|
Voice Activity Detection
、
Teager Energya
、
Wavelet
、
Auto-Correlation
、
THCI Core
|
| |
