| 2018 | ICASSP | Supervised Noise Reduction for Multichannel Keyword Spotting. | Yiteng Huang, Thad Hughes, Turaj Zakizadeh Shabestary, Taylor Applebaum |
| 2017 | ICASSP | Trainable frontend for robust and far-field keyword spotting. | Yuxuan Wang, Pascal Getreuer, Thad Hughes, Richard F. Lyon, Rif A. Saurous |
| 2017 | Interspeech | Generation of Large-Scale Simulated Utterances in Virtual Rooms to Train Deep-Neural Networks for Far-Field Speech Recognition in Google Home. | Chanwoo Kim, Ananya Misra, Kean K. Chin, Thad Hughes, Arun Narayanan, Tara N. Sainath, Michiel Bacchiani |
| 2013 | ICASSP | Recurrent neural networks for voice activity detection. | Thad Hughes, Keir Mierle |
| 2012 | ICASSP | Music models for music-speech separation. | Thad Hughes, Trausti T. Kristjansson |
| 2012 | Interspeech | Spectral Intersections for Non-Stationary Signal Separation. | Trausti T. Kristjansson, Thad Hughes |
| 2010 | Interspeech | Building transcribed speech corpora quickly and cheaply for many languages. | Thad Hughes, Kaisuke Nakajima, Linne Ha, Atul Vasu, Pedro J. Moreno, Mike LeBeau |
| 2009 | ICASSP | Revisiting graphemes with increasing amounts of data. | Yun-Hsuan Sung, Thad Hughes, Franoise Beaufays, Brian Strope |
| 2007 | EMNLP | Lexical Semantic Relatedness with Random Graph Walks. | Thad Hughes, Daniel Ramage |