The Unofficious Joe Tepperman Web SIGHT

My name is Joseph Harris Tepperman and I was born late last century in Toronto. I do research on speech and am a maker of music, always hoping to make the distance between these two things not so very far.

This all happens in Los Angeles. LA's green is the green that, when it does, turns single-serving milk bottles opaque - the weeds, their spray painted through the inside spore webbing. What real coyotes there live our midst are a civilized lot, leaping out at LA River bicyclists like tan triangle basketballs trailing tails. And the sound of Spanish gives really such a simple joy - who could hate to traverse its few birdcall acres?

Those wanting oftener music updates (shows, etc.) should direct themselves here, thanks.

Most new of my newest (and only) speech-art installations

This foam Tower of Babel took little pieces of anything said to it and recombined them into new words. In the absence of external speech to draw on, it would just keep talking with whatever it had heard before, calling out new combinations of possible (but maybe nonexistent) English words to itself.

This was an argumentative hat rack that recognized words and talked back in collaged speech - similar to those automated telephone systems that bug everyone a lot. But most people ended up using it kind of like a magic 8-ball.

We did a phoneme-to-color mapping that allowed people to automatically "paint" these almost abstract expressionist things just with their voices. Based loosely on the Silent Way approach to second-language instruction.

Research publications, seriously

Journals

Joseph Tepperman, Sungbok Lee, Shrikanth Narayanan, and Abeer Alwan, "A Generative Student Model for Scoring Word Reading Skills," IEEE Transactions on Audio, Speech, and Language Processing, submitted October 2008.

Patti Price, Joseph Tepperman, Markus Iseli, Thao Duong, Matthew Black, Shizhen Wang, Christy Kim Boscardin, Margaret Heritage, P. David Pearson, Shrikanth Narayanan, and Abeer Alwan, Assessment of Emerging Reading Skills in Young Native Speakers and Language Learners. Speech Communication, in press, 2009.

Joseph Tepperman and Shrikanth Narayanan, Using Articulatory Representations to Detect Segmental Errors in Nonnative Pronunciation. IEEE Transactions on Audio, Speech, and Language Processing, 16(1):8-22, January 2008.

Conferences

Joseph Tepperman, Erik Bresch, Yoon-Chul Kim, Sungbok Lee, Louis Goldstein, and Shrikanth Narayanan, "An Articulatory Analysis of Phonological Transfer Using Real-Time MRI," to appear in Proceedings of Interspeech, Brighton, September 2009.

Joseph Tepperman, Louis Goldstein, Sungbok Lee, and Shrikanth Narayanan, "Automatically Rating Pronunciation Through Articulatory Phonology," to appear in Proceedings of Interspeech, Brighton, September 2009.

Emily Nava, Joseph Tepperman, Louis Goldstein, Maria Luisa Zubizarreta, and Shrikanth Narayanan, "Connecting Rhythm and Prominence in Automatic ESL Pronunciation Scoring," to appear in Proceedings of Interspeech, Brighton, September 2009.

Matthew Black, Joseph Tepperman, Sungbok Lee, and Shrikanth Narayanan, "Predicting Children's Reading Ability using Evaluator-Informed Features," to appear in Proceedings of Interspeech, Brighton, September 2009.

Matthew Black, Joseph Tepperman, Abe Kazemzadeh, Sungbok Lee, and Shrikanth Narayanan, Automatic Pronunciation Verification of English Letter-names for Early Literacy Assessment of Preliterate Children, in Proc. of ICASSP, Taipei, April 2009.

Joseph Tepperman, Matteo Gerosa, and Shrikanth Narayanan. A generative model for scoring children's reading comprehension. In Proc. of the Workshop on Child, Computer, and Interaction, Chania, Greece, October 2008.

Joseph Tepperman and Shrikanth Narayanan. Better Nonnative Intonation Scores Through Prosodic Theory. In Proceedings of InterSpeech ICSLP, Brisbane, Australia, September 2008.

Joseph Tepperman and Shrikanth Narayanan. Tree Grammars as Models of Prosodic Structure. In Proceedings of InterSpeech ICSLP, Brisbane, Australia, September 2008.

Matthew Black, Joseph Tepperman, Sungbok Lee, and Shrikanth Narayanan. Estimation of Children's Reading Ability by Fusion of automatic Pronunciation Verification and Fluency Detection. In Proceedings of InterSpeech ICSLP, Brisbane, Australia, September 2008.

Matthew Black, Joseph Tepperman, Abe Kazemzadeh, Sungbok Lee, and Shrikanth Narayanan. Pronunciation Verification of English Letter-Sounds in Preliterate Children. In Proceedings of InterSpeech ICSLP, Brisbane, Australia, September 2008.

Abeer Alwan, Yijian Bai, Matt Black, Larry Casey, Matteo Gerosa, Margaret Heritage, Markus Iseli, Barbara Jones, Abe Kazemzadeh, Sungbok Lee, Shrikanth Narayanan, Patti Price, Joseph Tepperman, and Shizhen Wang. A system for technology based assessment of language and literacy in young children: the role of multiple information sources. In Proceedings of IEEE International Workshop on Multimedia Signal Processing, Chania, Greece, October 2007.

Joseph Tepperman, Abe Kazemzadeh, and Shrikanth Narayanan. A Text-free Approach to Assessing Nonnative Intonation. In Proceedings of InterSpeech ICSLP, Antwerp, Belgium, August 2007.

Joseph Tepperman, Matthew Black, Patti Price, Sungbok Lee, Abe Kazemzadeh, Matteo Gerosa, Margaret Heritage, Abeer Alwan, and Shrikanth Narayanan. A Bayesian Network Classifier for Word-level Reading Assessment. In Proceedings of InterSpeech ICSLP, Antwerp, Belgium, August 2007.

Matthew Black, Joseph Tepperman, Sungbok Lee, Patti Price, and Shrikanth Narayanan. Automatic Detection and Classification of Disfluent Reading Miscues in Young Children's Speech for the Purpose of Assessment. In Proceedings of InterSpeech ICSLP, Antwerp, Belgium, August 2007.

Joseph Tepperman, Jorge Silva, Abe Kazemzadeh, Hong You, Sungbok Lee, Abeer Alwan, and Shrikanth Narayanan. Pronunciation verification of children’s speech for automatic literacy assessment. In Proceedings of InterSpeech ICSLP, Pittsburgh, PA, September 2006.

Abe Kazemzadeh, Joseph Tepperman, Jorge Silva, Hong You, Sungbok Lee, Abeer Alwan, and Shrikanth Narayanan. Automatic detection of voice onset time contrasts for use in pronunciation assessment. In Proceedings of InterSpeech ICSLP, Pittsburgh, PA, September 2006.

Joseph Tepperman, David Traum, and Shrikanth Narayanan. Yeah right: Sarcasm recognition for spoken dialogue systems. In Proceedings of InterSpeech ICSLP, Pittsburgh, PA, September 2006.

Joseph Tepperman, Jorge Silva, Abhinav Sethy, and Shrikanth Narayanan. Robust recognition and assessment of non-native speech variability. In Proceedings of International Conference on Intelligent Systems And Computing: Theory And Applications, Ayia Napa, Cyprus, July 2006. Invited paper.

Joseph Tepperman and Shrikanth Narayanan. Hidden-articulator markov models for pronunciation evaluation. In Proceedings of ASRU, San Juan, Puerto Rico, November 2005.

Joseph Tepperman and Shrikanth Narayanan. Automatic syllable stress detection using prosodic features for pronunciation evaluation of language learners. In Proceedings of ICASSP, Philadelphia, PA, March 2005.

Abstracts

Joseph Tepperman, Erik Bresch, Yoon-Chul Kim, Louis Goldstein, Dani Byrd, Krishna Nayak, and Shrikanth Narayanan. "Articulatory analysis of foreign-accented speech using real-time MRI." J. Acoust. Soc. Am., 125(4):2753, 2009.

Shrikanth Narayanan, Abe Kazemzadeh, Matthew Black, Joseph Tepperman, Sungbok Lee, and Abeer Alwan. "Letter sound and letter name recognition for automated literacy assessment of young children." J. Acoust. Soc. Am., 123(5):3327, 2008.

Joseph Tepperman and Shrikanth Narayanan. "Spoken Name Pronunciation Evaluation." J. Acoust. Soc. Am., 116:2480, 2004.

A Very Selective Discography

As a leader

Mooey Moobau - All Murmur of Our Mothers' Waters. Ebola Music, 2008

The Domestication of Animals - The Domestication of Animals Plays the Screams of Drowning Ants, Bites of the Box-packed Dogs. Ebola Music, 2008

GST Mugwump - GST Mugwump and Friends Play the Music of Snidge. Superpickle, 2002

The Nourishment - Not Tonight, Honey - I've Got... The Nourishment. Brave New Weird, 2001

GST Mugwump - While I Was Me 1996-1998. Superpickle, 1999

As a guest

Bodies of Water - A Certain Feeling. Secretly Canadian, 2008

Cat Hair Ensemble - East of Western. 2008

Listing Ship - Hull Full of Oil and Bone. True Classical, 2008

Bodies of Water - Ears Will Pop and Eyes Will Blink. Thousand Tongues, 2007

Dorian Wood - Bolka. 2007

Ego Plum and the Ebola Music Orchestra - The Rat King. Ebola Music, 2007

Leopold - The Wreck of Hope. Total Annihilation, 2004.

The Industrial Jazz Group - City of Angles. Innova, 2002