Symposium on Machine Learning in Speech and Language Processing (MLSLP)

September 14, 2012
Portland, Oregon, USA


8:10-8:50Mark GalesLog-Linear Models for Speech Recognition (talk slides)
8:50-9:30Shai Ben-DavidTheoretical Analysis of Domain Adaptation -- Current State of the Art (talk slides)
9:30-10:10Brian RoarkHallucinating System Outputs for Discriminative Language Modeling (talk slides)
10:30-11:10Dirk Van CompernolleLarge Vocabulary Template Based Speech Recognition (talk slides)
11:10-11:50Erik McDermottAn Integrated Framework for ``Margin'' Based Sequential Discriminative Training over Lattices Based on Differenced Maximum Mutual Information (dMMI) (talk slides)
11:50-12:30Inderjit DhillonSparse Inverse Covariance Matrix Estimation Using Quadratic Approximation (talk slides)
1:40-2:20Hoifung PoonUnsupervised Semantic Parsing (talk slides)
2:20-3:00Georg HeigoldExemplar-Based Speech Recognition in a Rescoring Approach (talk slides)
3:00-4:30Poster Session
Andrea DeMarco and Stephen CoxIterative Classification Of Regional British Accents In I-Vector Space
Hitoshi Nishikawa, Toshiro Makino, and Yoshihiro MatsuoDomain Adaptation with Augmented Space Method for Multi-Domain Contact Center Dialogue Summarization
Marc Delcroix, Atsunori Ogawa, Tomohiro Nakatani, and Atsushi NakamuraDynamic Variance Adaptation using differenced Maximum Mutual Information
Udhyakumar Nallasamy, Florian Metze, Tanja SchultzSemi-Supervised Learning for Speech Recognition in the Context of Accent Adaptation
Anindya Roy, Mathew Magimai-Doss, and Sebastien MarcelBoosting Localized Binary Features for Speech Recognition
Rohit Prabhavalkar, Joseph Keshet, Karen Livescu, and Eric Fosler-LussierDiscriminative Spoken Term Detection with Limited Data
Bin Zhang and Mari OstendorfSemi-Supervised Learning for Text Classification using Feature Affinity Regularization
Emre Yilmaz, Dirk Van Compernolle, and Hugo Van hammeCombining exemplar-based matching and exemplar-based sparse representations of speech
Raman Arora and Karen LivescuKernel CCA for multi-view learning of acoustic features using articulatory measurements
4:30-5:10Hal Daumé IIITransfer Learning in Language (talk slides)
5:10-5:50Li DengLearning Deep Architectures Using Kernel Modules (talk slides)