“Speech Technology Group”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
Welcome to Speech Recognition team in CSLT, RIIT, Tsinghua University.
 
(相同用户的5个中间修订版本未显示)
第5行: 第5行:
 
'''1. Speech recognition'''
 
'''1. Speech recognition'''
  
We are interested in large vocubulary speech recognition, particularly on the modern topics such as noise robust ASR, deep belief network, covariance modeling etc.
+
We are interested in large vocubulary speech recognition, particularly on the modern topics such as noise robust ASR, deep learning. The research also
 +
extendes to speech analysis and spoken document retreival.  
  
'''2. Speech analysis'''
+
'''2. Language processing'''
 
+
Our research focuses on speech signal analysis, such as sparse coding, non-negative matrix factorization, speech signal separation, noise cancelation etc.
+
 
+
'''3. Spoken document retrieval'''
+
 
+
We focus on key word spotting, spoken term detection, spoken document retrieval, FST-based indexing.
+
 
+
'''4. Language processing'''
+
  
 
The focus is semantic embedding, sequential modeling, translation, question answering and dialog system.
 
The focus is semantic embedding, sequential modeling, translation, question answering and dialog system.
  
'''5. Financial processing'''
+
'''3. Financial processing'''
  
 
We also are interested in machine methods for financial data technical analysis, including prediction for financial data, stock portfolio, risk potting.
 
We also are interested in machine methods for financial data technical analysis, including prediction for financial data, stock portfolio, risk potting.
第30行: 第23行:
 
[[People]]
 
[[People]]
  
[[Porjects]]
+
[[Porjects|Team Space]]
  
 
[[Work progress]]
 
[[Work progress]]
  
[[Time tables]]
 
  
 
----
 
----
第43行: 第35行:
 
----
 
----
  
[[asr-rules|Regulations]]
+
[[asr-group-admin|Group Admin]]

2015年7月10日 (五) 06:06的最后版本

Welcome to Speech Recognition team in CSLT, RIIT, Tsinghua University.

Research focus:

1. Speech recognition

We are interested in large vocubulary speech recognition, particularly on the modern topics such as noise robust ASR, deep learning. The research also extendes to speech analysis and spoken document retreival.

2. Language processing

The focus is semantic embedding, sequential modeling, translation, question answering and dialog system.

3. Financial processing

We also are interested in machine methods for financial data technical analysis, including prediction for financial data, stock portfolio, risk potting.




People

Team Space

Work progress



News

Readings


Group Admin