Publications

Embedding-matching ASR (2022~Present, Apple)


Acoustic word embeddings for ASR (2020, Apple)


Confidence modeling (2019, Apple)


Keyword (wakeup word) detection  (2018, Apple)


Text-to-speech synthesis (2015, Apple)


Large-scale speaker identification (2011, Motorola)


Speaker clustering (2010-2011, Motorola)


Music information retrieval (2007-2009, Motorola)


Auditory modeling (2002-2006, Georgia Tech)


Other