Publications
Embedding-matching ASR (2022~Present, Apple)
W. Jeon, "Timestamped Embedding-Matching Acoustic-to-Word CTC ASR", Preprint PDF arXiv
H. Yen and W. Jeon, "Improvements to Embedding-Matching Acoustic-to-Word ASR Using Multiple-Hypothesis Pronunciation-Based Embeddings", IEEE ICASSP 2023 PDF arXiv
Acoustic word embeddings for ASR (2020, Apple)
Confidence modeling (2019, Apple)
W. Jeon, M. Jordan, and M. Krishnamoorthy, "On modeling ASR word confidence", IEEE ICASSP 2020 PDF [Talk Video(MP4 file)] arXiv
Keyword (wakeup word) detection (2018, Apple)
W. Jeon, L. Liu, and H. Mason, "Voice trigger detection from LVCSR hypothesis lattices using bidirectional lattice recurrent neural networks", IEEE ICASSP 2019 PDF
Text-to-speech synthesis (2015, Apple)
W. Jeon, "Unit-selection text-to-speech synthesis using concatenation-sensitive neural networks", U.S. Patent 9,697,820 (filed Sep. 2015, granted July 2017)
Large-scale speaker identification (2011, Motorola)
W. Jeon and Y.-M. Cheng, “Efficient speaker search over large populations using kernelized locality-sensitive hashing,” IEEE ICASSP 2012 PDF
W. Jeon and C. Ma and D. Macho and Y.-M. Cheng, “Methods for creating and searching a database of speakers,” U.S. patent 8,442,823 (filed Oct. 2010, granted May 2013)
Speaker clustering (2010-2011, Motorola)
W. Jeon and C. Ma and D. Macho, “Statistical utterance comparison techniques for speaker clustering using factor analysis,” IEEE Transactions on Audio, Speech, and Language Processing, vol. 20, no. 9, pp. 2482-2491, Nov. 2012 PDF
W. Jeon and C. Ma and D. Macho, “An utterance comparison model for speaker clustering using factor analysis,” IEEE ICASSP 2011 PDF
Music information retrieval (2007-2009, Motorola)
W. Jeon and C. Ma, “Efficient search of music pitch contours using wavelet transforms and segmented dynamic time warping,” IEEE ICASSP 2011 PDF
W. Jeon and C. Ma and Y.-M. Cheng, “An efficient signal-matching approach to melody indexing and search using continuous pitch contours and wavelets,” International Society for Music Information Retrieval (ISMIR) Conference, Kobe, Japan, Oct 2009 PDF
W. Jeon and C. Ma, “Method and apparatus for best matching an audible query to a set of audible targets,” U.S. patent 8,049,093 (filed Dec. 2009, granted Nov. 2011)
W. Jeon and C. Ma and Y.-M. Cheng, “Efficient search of music pitch contours using multiscale wavelet transforms and segmented dynamic time warping,” working paper, Feb 2011 PDF
Auditory modeling (2002-2006, Georgia Tech)
W. Jeon and B.-H. Juang, “Speech analysis in a model of the central auditory system,” IEEE Transactions on Audio, Speech, and Language Processing, vol. 15, no. 6, pp. 1802-1817, Aug. 2007 PDF
W. Jeon and B.-H. Juang, “Separation of SNR via dimension expansion in a model of the central auditory system,” IEEE ICASSP 2006 PDF
W. Jeon and B.-H. Juang, “A category-dependent feature selection method for speech signals,” INTERSPEECH 2005 PDF
W. Jeon and B.-H. Juang, “A study of auditory modeling and processing for speech signals,” IEEE ICASSP 2005 PDF
W. Jeon and B.-H. Juang, “Auditory analysis for speech recognition based on physiological models” (abstract), Acoustical Society of America, 2004
W. Jeon and B.-H. Juang, “Automatic pattern recognition using category dependent feature selection,” U.S. patent 8,380,506 (filed Nov. 2007, granted Feb. 2013)
Other
C. Ma and W. Jeon, “Efficient speech indexing and search for embedded devices using uniterms,” IEEE ICASSP 2009 PDF
W. Jeon, “Speech analysis and cognition using category-dependent features in a model of the central auditory system,” Ph.D. thesis, Georgia Tech, 2006 LINK
W. Jeon, “Pitch detection of polyphonic music using constrained optimization,” M.S. thesis, Georgia Tech, 2002 PDF
W. Jeon, “Design of an inverted pendulum controller,” B.S. thesis, Seoul National University 1998