Hello, World.
I am in the Speech Group at ICSI, as a Ph.D. student in Computer Science at Berkeley.
My research interest is in automatic speech recognition (ASR).

I'm currently working on my startup, Modista.com, applying computer vision to online shopping.

Email: arlo at the domain icsi.berkeley.edu
CV/Resume: PDF HTML

Current Projects

• Developing a speech recognition application for the Parallel Computing Laboratory.

Past Projects

• Developing Mandarin and Arabic ASR for the GALE project.
• Developing the English version of the SmartWeb recognizer.
• Searching broadcast news video for the TREC Video Retrieval Evaluation.
• Aligning video to imperfect transcripts of the Scottish Parliament (while at CSTR).
• Speech recognition of non-native speakers. (won an award)
• Pitch-based vocal tract length normalization.
• Graduate Student Instructor for CS188: Artificial Intelligence

Publications

M-Y. Hwang, G. Peng, M. Ostendorf, W. Wang, A. Faria, and A. Heidel
Building A Highly Accurate Mandarin Speech Recognizer with Language-Independent Technologies and Language-Dependent Modules
To appear in IEEE Transactions on Audio, Speech, and Language Processing. 2009.

D. Vergyri, A. Mandal, W. Wang, A. Stolcke, J. Zheng, M. Graciarena, D. Rybach, C. Gollan, R. Schlater, K. Kirchoff, A. Faria, and N. Morgan
Development of the SRI/Nightingale Arabic ASR System
Proc. of Interspeech. 2008.

J. Chong, Y. Yi, A. Faria, S. Rajagopalan, K. Keutzer
Data-Parallel Large Vocabulary Continuous Speech Recognition on Graphics Processors
Workshop on Emerging Applications and Many-core Architecture (EAMA). 2008.

A. Faria and N. Morgan.
Corrected Tandem Features for Acoustic Model Training.
Intl. Conf. Acoustics, Speech, Signal Processing (ICASSP). 2008.

A. Faria and N. Morgan.
When a Mismatch Can Be Good: Large vocabulary speech recognition trained with idealized Tandem features.
Proc. ACM Symposium on Applied Computing (SAC). 2008.

M-Y. Hwang, G. Peng, W. Wang, A. Faria, A. Heidel.
Building a Highly Accurate Mandarin Speech Recognizer
Proc. Automatic Speech Recognition and Understanding (ASRU). 2007.

S. Petrov, A. Faria, P. Michaillat, A. Berg, A. Stolcke, D. Klein, J. Malik.
Detecting Categories in News Video Using Acoustic, Speech, and Image Features
Proc. TREC Video Retrieval Workshop (TRECVID). 2006.

A. Faria
Accent Classification for Speech Recognition
Proc. Machine Learning and Multimodal Interaction (MLMI), LNCS 3869. 2005.

A. Faria and D. Gelbart
Efficient Pitch-based Estimation of VTLN Warp Factors
Proc. Eurospeech. 2005.

Course-related projects

• An Investigation of Tandem MLP Features for ASR (EE 225D: Spring 2007)
• MapReduce: Distributed Computing for Machine Learning (CS 262A: Fall 2006)
• HMMs for ASR (CS 188: Spring 2006)
• HMM-GMM Acoustic Models for Speech Recognition (CS 281A: Fall 2005)
• Estimation of Glottal Source Parameters from Diverse Signals (Ling 113: Spring 2004)
• Applied Phonetics: Portuguese Text-to-Speech (Ling 110: Spring 2003)