Andrew Rosenberg

I am currently an Assistant Professor of Computer Science at Queens College (CUNY). I completed my Ph.D. at Columbia University in 2009.

My research concerns Natural Language Processing, Spoken Language Processing, Prosody/Intonation and Machine Learning.

Teaching

Spring 2010 : Queens College - Machine Learning

Spring 2010 : CUNY Graduate Center - Machine Learning [webpage to come, see Queens College page]

Fall 2009 : Algorithms I - CSCI700

Publications

Andrew Rosenberg. 2009. Automatic Detection and Classification of Prosodic Events. Ph.D. Thesis. Columbia University
Andrew Rosenberg and Julia Hirschberg. 2009. Detecting Pitch Accent at the Word, Syllable and Vowel Level HLT/NAACL
Andrew Rosenberg and Julia Hirschberg. 2008. Charisma Perception from Text and Speech Speech Communication. 2008 [ScienceDirect]
Sameer Maskey, Andrew Rosenberg and Julia Hirschberg. 2008. Intonational Phrases for Speech Summarization INTERSPEECH '08
Andrew Rosenberg and Julia Hirschberg. 2007. Detecting Pitch Accent Using Pitch-corrected Energy-based Predictors. INTERSPEECH '07
Fadi Biadsy, Julia Hirschberg, Wisam Dakka, and Andrew Rosenberg. 2007. Comparing American and Palestinian Perceptions of Charisma Using Acoustic-Prosodic and Lexical Analysis. INTERSPEECH '07
Andrew Rosenberg, Mehrbod Sharifi and Julia Hirschberg. 2007. Varying Input Segmentation for Story Boundary Detection in English, Arabic and Mandarin Broadcast News. INTERSPEECH '07
Andrew Rosenberg and Julia Hirschberg. 2007. V-Measure: A conditional entropy-based external cluster evaluation measure. EMNLP '07
Andrew Rosenberg and Julia Hirschberg. 2006. On the Correlation of Energy and Pitch Accent in Read English Speech. INTERSPEECH '06
Andrew Rosenberg and Julia Hirschberg. 2006. Story Segmentation of Broadcast News in English, Mandarin and Arabic. HLT/NAACL '06
Andrew Rosenberg and Julia Hirschberg. 2005. Acoustic/Prosodic and Lexical Correlates of Charismatic Speech. EUROSPEECH'05
Andrew Rosenberg and Ed Binkowski. 2004. Augmenting the Kappa Statistic to Determine Interannotator Reliability for Multiply Labeled Data Points. HLT/NAACL '04

Current Research Projects

AuToBI

Based on my dissertation, "Automatic Detection and Classification of Prosodic Events", I will incrementally release a system to generate hypothesized ToBI tones over the next few months. I am currently working to bringing the disparate components together to a single software package.

Most Recent Update (11-04-2010): IntensityExtractor.java - a java implementation of Praat's intensity extraction algorithm Sound_to_Intensity...

Analysis of Non-native Intonation

Intonation is typically the last aspect of spoken language acquired by non-native speakers. In this work, we examine the influence of Mandarin Chinese speakers' native language on their perception and production of intonation in American English.

Collaborators: Julia Hirschberg

V-Measure: Cluster Evaluation Measure

Evaluating the success of clustering algorithms is not a trivial task. In 2007, I proposed a conditional entropy-based measure called V-measure at EMNLP. This measure is described in V-Measure: A conditional entropy-based external cluster evaluation measure. The name comes from its similarity in calculation to F-measure, and its goal of evaluating cluster validity.

V-measure is the evaluation measure for the unsupervised evaluation of the SemEval 2010 Word Sense Induction and Disambiguation Task

Distributed here a java package that implements V-Measure as well as a number of other cluster evaluation measures. Feel free to email with bug reports and feature requests
ClusterEvaluator.jar
ClusterEvaluator source code
Javadoc for ClusterEvaluator.

Other