I-Fan Chen (陳羿帆)
A Senior Applied Scientist in Amazon Artificial General Intelligent (AGI) org with
20+ years experience on speech research (ASR, speaker recognition/diarization) and natural language processing domains since 2004.
8+ years of the experience on large scale industrial solutions for production speech recognition systems (e.g., Alexa ASR) since 2016.
Research Areas and Interest:
Automatic Speech Recognition, Natural Language Processing, Machine Learning, Artificial General Intelligence, Multi-Modal AGI
Programming languages:
Python, C++, Java
Contact: ifanchen AT gmail DOT com
Education:
Doctor of Philosophy (PhD), Electrical Computer Engineering
Georgia Institute of Technology
May 2016
Publication List [Google Scholar Page]
2024
Pin-Jui Ku, I-Fan Chen, et. al., “Hot-fixing wake word recognition for end-to-end ASR via neural model reprogramming,” in Proc. ICASSP 2024.
2023
Pin-Jui Ku, Phani Sankar Nidadavolu, Brian King, Pegah Ghahremani, I-Fan Chen, “A preliminary study on associated learning for ASR,” in Proc. ASRU BAYESIAN 2023 Workshop
Yu Yu, Huck Yang, Jari Kolehmainen, Prashanth Gurunath Shivakumar, Yi Gu, Sungho Ryu, Roger Ren, Qi Luo, Aditya Gourav, I-Fan Chen, Yi Chieh Liu, Tuan Dinh, Ankur Gandhe, Denis Filimonov, Shalini Ghosh, Andreas Stolcke, Ariya Rastrow, Ivan Bulyko, “Low-rank adaptation of large language model rescoring for parameter-efficient speech recognition,” in Proc. 2023 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)
Hoang Anh Just, I-Fan Chen, et. al., ASR data selection from multiple sources: A practical approach on performance scaling, in NeurIPS 2023 Workshop on Efficient Natural Language and Speech Processing (ENLSP)
Anirudh Sundar, Gokce Keskin, Chander Chandak, I-Fan Chen, Pegah Ghahremani, Shalini Ghosh, “Prune then distill: Dataset distillation with importance sampling,” in Proc. ICASSP 2023.
2022
Chao-Han Huck Yang, I-Fan Chen, Andreas Stolcke, Sabato Marco Siniscalchi, Chin-Hui Lee, “An experimental study on private aggregation of teacher ensemble learning for end-to-end speech recognition,” in Proc. SLT 2022.
Pranav Dheram, Murugesan Ramakrishnan, Anirudh Raju, I-Fan Chen, Brian King, Katherine Powell, Melissa Saboowala, Karan Shetty, Andreas Stolcke, “Toward fairness in speech recognition: Discovery and mitigation of performance disparities,” in Proc. Interspeech 2022
Ting-Wei Wu, I-Fan Chen, Ankur Gandhe, “Learning to rank with BERT-based confidence models in ASR rescoring,” in Proc. Interspeech 2022.
2021
I-Fan Chen, Brian King, Jasha Droppo, “Investigation of Training Label Error Impact on RNN-T,” https://arxiv.org/abs/2112.00350
2019
Pranav Ladkat, Oleg Rybakov, Radhika Arava, Sree Hari Krishnan Parthasarathi, I-Fan Chen, Nikko Ström, “Two Tiered Distributed Training Algorithm for Acoustic Modeling,” in Proc. Interspeech 2019.
Yiming Wang, Xing Fan, I-Fan Chen, Yuzong Liu, Björn Hoffmeister, “End-to-end Anchored Speech Recognition,” in Proc. ICASSP 2019.
2017
Brian King, I-Fan Chen, Yonatan Vaizman, Yuzong Liu, Roland Maas, Sree Hari Krishnan Parthasarathi, Björn Hoffmeister, “Robust Speech Recognition Via Anchor Word Representations,” in Proc. Interspeech 2017.
2015
Tze Siong Lau, I-Fan Chen, Chin-Hui Lee, "Tunable Keyword-Aware Language Modeling and Context Dependent Fillers for LVCSR-based Spoken Keyword Search," in Proc. Interspeech, 2015. [PDF]
I-Fan Chen, Chongjia Ni, Boon Pang Lim, Nancy F. Chen, and Chin-Hui Lee, "A Keyword-Aware Language Modeling to Spoken Keyword Search," in Journal of Signal Processing Systems, 2015, DOI: 10.1007/s11265-015-0998-0 . [PDF1]
I-Fan Chen, Chongjia Ni, Boon Pang Lim, Nancy F. Chen, and Chin-Hui Lee, "A KEYWORD-AWARE GRAMMAR FRAMEWORK FOR LVCSR-BASED SPOKEN KEYWORD SEARCH," in Proc. ICASSP, 2015. [PDF1] [Slide]
Nancy Chen, Chongjia Ni, I-Fan Chen, Sunil Sivadas, Van Tung Pham, Haihua Xu, Xiong Xiao, Tze Siong Lau, Sujun Leow, Boon Pang Lim, Cheung-Chi Leung, Lei Wang, Chin-Hui Lee, Alvina Goh, Eng Siong Chng, Bin Ma, Haizhou Li, "LOW-RESOURCE KEYWORD SEARCH STRATEGIES FOR TAMIL," in Proc. ICASSP, 2015. [PDF1]
2014
Van Tung Pham, Nancy F. Chen, Sunil Sivadas, Haihua Xu, I-Fan Chen, Chongjia Ni, Eng Siong Chng, Haizhou Li, "SYSTEM AND KEYWORD DEPENDENT FUSION FOR SPOKEN TERM DETECTION," in Proc. IEEE SLT, 2014.
I-Fan Chen, Nancy F. Chen, and Chin-Hui Lee, "A Keyword-Boosted sMBR Criterion to Enhance Keyword Search Performance in Deep Neural Network Based Acoustic Modeling," in Proc. Interspeech, 2014. [PDF1] [PDF2] [Slides]
Zhen Huang, Jinyu Li, Sabato Marco Siniscalchi, I-Fan Chen, Chao Weng, and Chin-Hui Lee, "Feature Space Maximum A Posteriori Linear Regression for Adaptation of Deep Neural Networks," in Proc. Interspeech, 2014. [PDF]
I-Fan Chen, Chongjia Ni, Boon Pang Lim, Nancy F. Chen, and Chin-Hui Lee, "A Novel Keyword+LVCSR-Filler Based Grammar Network Representation for Spoken Keyword Search," in Proc. ISCSLP, 2014. [PDF1] [PDF2] [Slides] [nominee of best student award]
I-Fan Chen, Sabato Marco Siniscalchi, and Chin-Hui Lee, "ATTRIBUTE BASED LATTICE RESCORING IN SPONTANEOUS SPEECH RECOGNITION," in Proc. ICASSP, 2014. [PDF1][PDF2]
Publications before 2014
2013
I-Fan Chen, S. M. Marco, S. Moon, D. Shin, M.-W. Koo, M. Chung, and C.-H. Lee, "An Experimental Study on Structural-MAP Approaches to Implementing Very Large Vocabulary Speech Recognition Systems for Real-World Tasks," in APSIPA2013. [PDF1] [PDF2]
I-Fan Chen and C.-H. Lee, "A Hybrid HMM/DNN Approach to Keyword Spotting of Short," in Proc. Interspeech, 2013. [PDF1] [PDF2]
I-Fan Chen and C.-H. Lee, "A Resource-Dependent Approach to Word Modeling for Keyword Spotting, " in Proc. Interspeech, 2013. [PDF1] [PDF2]
2012
I-Fan Chen and C.-H. Lee, "A Study on Using Word-Level HMMs to Improve ASR Performance over State-of-the-Art Phone-Level Acoustic Modeling for LVCSR," in Proc. Interspeech, 2012. [PDF1] [PDF2]
2010
I-Fan Chen, S.-S. Cheng, and H.-M. Wang, "Phonetic subspace mixture model for speaker diarization," in Proc. Interspeech, 2010. [PDF1] [PDF2]
S.-S. Cheng, I.-F. Chen, and H.-M. Wang, "Bayesian Speaker Recognition Using Gaussian Mixture Model and Laplace Approximation," in Proc. Interspeech, 2010. [PDF1] [PDF2]
2009
I-Fan Chen and H.-M. Wang, "Articulatory feature asynchrony analysis and compensation in detection-based ASR," in Proc. Interspeech, 2009. [PDF1] [PDF2]
2008
I-Fan Chen and H.-M. Wang, "An Investigation of Phonological Feature Systems Used In Detection-Based ASR," in Proc. ISCSLP'08, 2008. [PDF1] [PDF2]
2006