Name: Sheng Li
Type: User
Company: National Institute of Information and Communications Technology (NICT)
Bio: Ph.D. (Kyoto Univ.)
Researcher,
National Institute of Information and Communications Technology (NICT),
E-mail: sheng dot li at ieee dot org
Location: Kyoto, Japan
Blog: https://scholar.google.com/citations?hl=en&user=zHAhs0IAAAAJ
Sheng Li's Projects
最全中华古诗词数据库, 唐宋两朝近一万四千古诗人, 接近5.5万首唐诗加26万宋诗. 两宋时期1564位词人,21050首词。
CINO: Pre-trained Language Models for Chinese Minority (少数民族语言预训练模型)
非常全的文言文(古文)-现代文平行语料
Computational Network Toolkit (CNTK)
This is the implementation of paper CONSISTENT TRAINING AND DECODING FOR END-TO-END SPEECH RECOGNITIONUSING LATTICE-FREE MMI submitted to ICASSP2022
Making Espnet easier to use
The official repository of the Eesen project
GSoC'16 RedHen Labs
Improving ASR by Joint Training with Translation
Open-Source Large Vocabulary Continuous Speech Recognition Engine
This is now the official location of the Kaldi project.
Khmer Language Model using ULMFiT
Separate Khmer words from given sentences.
NICT-Tib1: A public speech corpus of Lhasa dialect for benchmarking Tibetan language speech recognition systems developed by NICT
More than 43+ collections of Thai Natural Language Processing libraries. Update daily.
A playbook for systematically maximizing the performance of deep learning models.
VoxLingua107 recipe for SpeechBrain
Fast parallel CTC.