Fall 2014 SST and Prosody Joint Reading Group
- Tuesday November 4, 4:30-5:30, BI 2369:
MCMC for Machine Learning,
Yang Zhang, 11/4/2014, 4:30-5:30pm, BI 2369 - Tuesday October 28, 4:30-5:30, BI 2369:
Regularized Estimation of GMMs for SVM-Based Speaker Recognition,
Kaizhi Qian, 10/28/2014, 4:30-5:30pm, BI 2369 - Tuesday October 21, 4:30-5:30, BI 2369:
Restricted Boltzmann Machines,
Amit Das, 10/21/2014, 4:30-5:30pm, BI 2369 - Tuesday October 14, 4:30-5:30, BI 2369:
Linking bottom-up intonation stylization to discourse structure
Talk by Tim Mahrt, discussing a paper by Uwe D. Reichel - Tuesday October 7, 4:30-5:30, BI 2369:
Automatic Pronunciation Error Identification based on TOEFL Junior Corpus
Talk by Xuesong Yang - Tuesday September 23, 4:30-5:30, BI 2369:
Shallow and Deep Learning for Audio and Natural Language Processing
Talk by Po-Sen Huang - Tuesday September 16, 4:30-5:30, BI 2369:
Learning Task-specific Lexical Embeddings
Presented by Sujeeth Bharadwaj - Tuesday September 9, 4:30-5:30, BI 2369:
N-best Entropy based Data Selection for Acoustic Modeling
Presented by Preethi Jyothi - Tuesday September 2, 4:30-5:30, BI 2369:
Long Audio Alignment
Presented by Mark Hasegawa-Johnson (Joint work with Mohamed Elmahdy & Eiman Mustafawi) - Tuesday August 26, 4:30-5:30, BI 2369:
Talk by Harsh Vardhan Sharma