I am a research scientist at the Johns Hopkins affiliated Human Language Technology Center of Excellence (HLTCOE). I am broadly interested in speech technologies, but I have primarily worked on multilingual and cross-lingual acoustic modeling for low-resource language ASR and topic identification. Recently, I have been increasingly interested in Machine Translation. I finished my PhD at Johns Hopkins University in 2021 advised by Sanjeev Khudanpur. I have worked on end-to-end speech recognition ESPnet and Fairseq and I am an occasional contributer to Kaldi. Before starting at Johns Hopkins I used to work on machine learning applications in atmospheric science. Outside of work, I spend most of my time making music and with my family.
Towards Zero-Shot Code-Switched Speech Recognition
Brian Yan, Matthew Wiesner, Ondřej Kleich, Preethi Jyothi, Shinji Watanabe, Accepted at ICASSP 2023
Building Keyword Search Systems from End-To-End ASR Systems
Ruizhe Huang, Matthew Wiesner, Leibny Paola García-Perera, Dan Povey, Jan Trmal, Sanjeev Khudanpur, Accepted at ICASSP 2023
JHU IWSLT 2022 Dialect Speech Translation System Description
Jinyi Yang, Amir Hussein, Matthew Wiesner, Sanjeev Khudanpur, IWSLT 2022
Injecting Text and Cross-Lingual Supervision in Few-shot Learning from Self-supervised Models
Matthew Wiesner, Desh Raj, Sanjeev Khudanpur, ICASSP 2022
Training Hybrid Models on Noisy Transliterated Transcripts for Code-Switched Speech Recognition
Matthew Wiesner, Mousmita Sarma, Ashish Arora, Desh Raj, Dongji Gao, Ruizhe Huang, Supreet Preet, Moris Johnson, Zikra Iqbal, Nagendra Goel, Jan Trmal, Paola García, Sanjeev Khudanpur, Interspeech 2021
The Multilingual TEDx Corpus for Speech Recognition and Translation
Elizabeth Salesky, Matthew Wiesner, Jacob Bremerman, Roldano Cattoni, Matteo Negri, Marco Turchi, Douglas W. Oard, Matt Post, Interspeech 2021
A Corpus for Large-Scale Phonetic Typology
Elizabeth Salesky, Eleanor Chodroff, Tiago Pimentel, Matthew Wiesner, Ryan Cotterell, Alan W Black, Jason Eisner, ACL 2020
Zero-Shot Pronunciation Lexicons for Cross-Language Acoustic Model Transfer Settings
Matthew Wiesner, Oliver Adams, David Yarowsky, Jan Trmal Sanjeev Khudanpur, ASRU 2019
Pretraining by Backtranslation for End-to-end ASR in Low-Resource Settings
Matthew Wiesner, Adithya Renduchintala, Shinji Watanabe, Chunxi Liu, Najim Dehak, Sanjeev Khudanpur, INTERSPEECH 2019
Analysis of Multilingual Sequence-to-Sequence speech recognition systems
Martin Karafiát, Murali Karthick Baskar, Shinji Watanabe, Takaaki Hori, Matthew Wiesner, Jan "Honza'' Černocký, INTERSPEECH 2019
Massively Multilingual Adversarial Speech Recognition
Oliver Adams, Matthew Wiesner, Shinji Watanabe, David Yarowsky, NAACL 2018
Multilingual sequence-to-sequence speech recognition:architecture, transfer learning, and language modeling
Jaejin Cho, Murali Karthick Baskar, Ruizhi Li, Matthew Wiesner, Sri Harish Mallidi, Nelson Yalta,Martin Karafiat, Shinji Watanabe, Takaaki Hori, SLT 2018
Low-Resource Centextual Topic Identification on Speech
Chunxi Liu, Matthew Wiesner, Shinji Watanabe, Craig Harman, Jan Trmal, Najim Dehak, Sanjeev Khudanpur, SLT 2018.
Automatic Speech Recognition and Topic Identification for Almost-Zero-Resource Languages
Matthew Wiesner, Chunxi Liu, Lucas Ondel, Craig Harman, Vimal Manohar, Jan Trmal, Zhongqiang Huang, Najim Dehak, Sanjeev Khudanpur, INTERSPEECH 2018.
Multi-Modal Data Augmentation for End-to-end ASR Best Student Paper!
Adithya Renduchintala, Shuoyang Ding, Matthew Wiesner and Shinji Watanabe, INTERSPEECH 2018.
ESPnet: End-to-End Speech Processing Toolkit
Shinji Watanabe, Takaaki Hori, Shigeki Karita, Tomoki Hayashi, Jiro Nishitoba, Yuya Unno, Nelson Enrique Yalta Soplin, Jahn Heymann, Matthew Wiesner, Nanxin Chen, Adithya Renduchintala, Tsubasa Ochiai, INTERSPEECH 2018.
Topic Identification for Speech without ASR Nominated for Best Student Paper
Chunxi Liu, Jan Trmal, Matthew Wiesner, Craig Harman, Sanjeev Khudanpur, INTERSPEECH 2017.
The Kaldi OpenKWS System: Improving Low Resource Keyword Search
Jan Trmal, Matthew Wiesner, Vijayaditya Peddinti, Xiaohui Zhang, Pegah Ghahremani, Yiming Wang, Vimal Manohar, Hainan Xi, Daniel Povey, Sanjeev Khudanpur, INTERSPEECH 2017.
Automated Detection of Radar Severe Weather Signatures
Matthew Wiesner, Joseph Hardin, V. Chandrasekaran, American Meteorological Society 2014.
Ph.D. in Electrical Engineering (Oct 2021)
Johns Hopkins University, MD, USA
Masters in Electrical Engineering (May 2016)
Johns Hopkins University, MD, USA
B.Eng Electrical Engineering / Minor in Arabic Language (Dec 2013)
McGill University, QC, CA
nnet_pytorch: A pytorch replacement for nnet3 in Kaldi
Jotto: The Code Breaking Game
B3 Clustering Metric
Music