• Publications
  • Influence
HKUST/MTS: A Very Large Scale Mandarin Telephone Speech Corpus
The paper describes the design, collection, transcription and analysis of 200 hours of HKUST Mandarin Telephone Speech Corpus (HKUST/MTS), the largest and first of its kind for Mandarin conversational telephone speech, providing abundant and diversified samples for Mandarin speech recognition and other application-dependent tasks. Expand
CASS: a phonetically transcribed corpus of mandarin spontaneous speech
A collection of Chinese spoken language has been collected and phonetically annotated to capture spontaneous speech and language effects and will be used at the 2000 Johns Hopkins University Language Engineering Workshop by the project on Pronunciation Modeling of Mandarin Casual Speech. Expand
Multi-accent Chinese speech recognition
Pronunciation Modeling for Spontaneous Mandarin Speech Recognition
It is shown that partial changes are much less clear-cut than previously assumed and cannot be modelled by mere representation by alternate phone units and can be applied to any automatic speech recognition system based on subword units. Expand
Green light-emitting polyepinephrine-based fluorescent organic dots and its application in intracellular metal ions sensing.
It is discovered that Fe(2+), Fe(3+), and Cu(2+) can strongly quench the fluorescence of PEP-FODs through the nonradiative electron-transfer. Expand
State-dependent phonetic tied mixtures with pronunciation modeling for spontaneous speech recognition
  • Y. Liu, Pascale Fung
  • Computer Science
  • IEEE Transactions on Speech and Audio Processing
  • 21 June 2004
A state-dependent phonetic tied-mixture model with variable codebook size that incorporates a state-level pronunciation model for better discrimination of phonetic and acoustic confusions, while reducing model complexity is proposed. Expand
Asymmetric acoustic modeling of mixed language speech
This work proposes to improve speech recognition performance on speaker-independent, mixed language speech by asymmetric acoustic modeling using selective decision tree merging between a bilingual model and an accented embedded speech model that outperforms previous approaches. Expand
Spatial Disaggregation of Coarse Soil Moisture Data by Using High-Resolution Remotely Sensed Vegetation Products
A novel approach to spatially disaggregate coarse soil moisture (SM) by only using remotely sensed vegetation index is presented, and it is shown that the proposed approach can provide fine-resolution SM with reasonable spatial variability. Expand
Heuristic Approach for Optimizing Emergency Medical Services in Road Safety within Large Urban Networks
Emergency medical service (EMS) providers participating in vehicle crash-induced incident management aim to offer as wide and efficient coverage as possible to meet the demand for incident responsesExpand
Severe insulin resistance and moderate glomerulosclerosis in a minipig model induced by high-fat/ high-sucrose/ high-cholesterol diet.
It is concluded that feeding HFSCD to Chinese Bama minipigs for 5 months can induce humanoid type 2 diabetes and early-stage diabetic nephropathy, and accelerate extracellular matrix deposition and glomerulosclerosis. Expand