Xiang Li

Affiliations:
  • IBM T.J. Watson Research Center, Human Language Technology Department, Yorktown Heights, NY, USA
  • Carnegie Mellon University, School of Computer Science, Pittsburgh, PA, USA


According to our database1, Xiang Li authored at least 11 papers between 2002 and 2007.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2007
How predictable is ASR confidence in dialog applications?
Proceedings of the 8th Annual Conference of the International Speech Communication Association, 2007

2006
Conversational help desk: vague callers and context switch.
Proceedings of the Ninth International Conference on Spoken Language Processing, 2006

Improved topic classification over maximum entropy model using k-norm based new objectives.
Proceedings of the Ninth International Conference on Spoken Language Processing, 2006

Efficient Speaker Detection via Target Dependent Data Reduction.
Proceedings of the 2006 IEEE International Conference on Multimedia and Expo, 2006

2005
Improving end-to-end performance of call classification through data confusion reduction and model tolerance enhancement.
Proceedings of the 9th European Conference on Speech Communication and Technology, 2005

2004
Parallel feature generation based on maximizing normalized acoustic likelihood.
Proceedings of the 8th International Conference on Spoken Language Processing, 2004

Discriminative training of compound-word based multinomial classifiers for speech routing.
Proceedings of the 8th International Conference on Spoken Language Processing, 2004

Feature generation based on maximum normalized acoustic likelihood for improved speech recognition.
Proceedings of the 2004 IEEE International Conference on Acoustics, 2004

2003
Feature generation based on maximum classification probability for improved speech recognition.
Proceedings of the 8th European Conference on Speech Communication and Technology, EUROSPEECH 2003, 2003

Training of stream weights for the decoding of speech using parallel feature streams.
Proceedings of the 2003 IEEE International Conference on Acoustics, 2003

2002
Combining search spaces of heterogeneous recognizers for improved speech recogniton.
Proceedings of the 7th International Conference on Spoken Language Processing, ICSLP2002, 2002


  Loading...