MA
Michael Auli
cs.CLcs.LGcs.SDeess.AScs.AIcs.CVapplicationscs.NEeess.IVlarge language models
On Valency
published · living versionsW_3p4mg6bx·v1 · currentpublished
Sequence Level Training with Recurrent Neural Networks
with Marc'Aurelio Ranzato, Sumit Chopra, Wojciech Zaremba
1 version
Preprints & journals
74 papers in the corpus · 2015–2025Omnilingual ASR: Open-Source Multilingual Speech Recognition for 1600+ Languages2511.09690v1 · Omnilingual ASR team: Gil Keren, Artyom Kozhevnikov, Yen Meng et al.2025 · 0 citationsarXiv
Effects of Speaker Count, Duration, and Accent Diversity on Zero-Shot Accent Robustness in Low-Resource ASR2506.04364v1 · Zheng-Xin Yong, Vineel Pratap, Michael Auli et al.2025 · 0 citationsarXiv
Improving Multilingual ASR in the Wild Using Simple N-best Re-ranking2409.18428v1 · Brian Yan, Vineel Pratap, Shinji Watanabe et al.2024 · 0 citationsarXiv
Scaling A Simple Approach to Zero-Shot Speech Recognition2407.17852v1 · Jinming Zhao, Vineel Pratap, Michael Auli2024 · 4 citationsarXiv
Large language models for science and medicine.38381530 · Telenti, Amalio, Auli, Michael, Hie, Brian L et al.2024 · 57 citationsEuropean journal of clinical investigation. 2024;54(6):e14183
AV-data2vec: Self-supervised Learning of Audio-Visual Speech Representations with Contextualized Target Representations2302.06419v2 · Jiachen Lian, Alexei Baevski, Wei-Ning Hsu et al.2023 · 27 citationsarXiv
DinoSR: Self-Distillation and Online Clustering for Self-supervised Speech Representation Learning2305.10005v2 · Alexander H. Liu, Heng-Jui Chang, Michael Auli et al.2023 · 9 citationsarXiv
Toward Joint Language Modeling for Speech Units and Text2310.08715v1 · Ju-Chieh Chou, Chung-Ming Chien, Wei-Ning Hsu et al.2023 · 10 citationsarXiv
Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language2212.07525v2 · Alexei Baevski, Arun Babu, Wei-Ning Hsu et al.2022 · 18 citationsarXiv
Measuring the Impact of Individual Domain Factors in Self-Supervised Pre-Training2203.00648v3 · Ramon Sanabria, Wei-Ning Hsu, Alexei Baevski et al.2022 · 6 citationsarXiv
Scaling Speech Technology to 1,000+ Languages2305.13516v1 · Vineel Pratap, Andros Tjandra, Bowen Shi et al.2023 · 116 citationsarXiv
Masked Autoencoders that Listen2207.06405v3 · Po-Yao Huang, Hu Xu, Juncheng Li et al.2022 · 103 citationsarXiv
data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language2202.03555v3 · Alexei Baevski, Wei-Ning Hsu, Qiantong Xu et al.2022 · 234 citationsarXiv
Simple and Effective Unsupervised Speech Translation2210.10191v1 · Changhan Wang, Hirofumi Inaguma, Peng-Jen Chen et al.2022 · 12 citationsarXiv
Wav2Vec-Aug: Improved self-supervised training with limited data2206.13654v1 · Anuroop Sriram, Michael Auli, Alexei Baevski2022 · 13 citationsarXiv
Towards End-to-end Unsupervised Speech Recognition2204.02492v2 · Alexander H. Liu, Wei-Ning Hsu, Michael Auli et al.2022 · 57 citationsarXiv
Unsupervised Speech Recognition2105.11084v3 · Alexei Baevski, Wei-Ning Hsu, Alexis Conneau et al.2021 · 21 citationsarXiv
On-demand compute reduction with stochastic wav2vec 2.02204.11934v1 · Apoorv Vyas, Wei-Ning Hsu, Michael Auli et al.2022 · 6 citationsarXiv
Simple and Effective Unsupervised Speech Synthesis2204.02524v3 · Alexander H. Liu, Cheng-I Jeff Lai, Wei-Ning Hsu et al.2022 · 11 citationsarXiv
XTREME-S: Evaluating Cross-lingual Speech Representations2203.10752v3 · Alexis Conneau, Ankur Bapna, Yu Zhang et al.2022 · 17 citationsarXiv
Unified Speech-Text Pre-training for Speech Translation and Recognition2204.05409v1 · Yun Tang, Hongyu Gong, Ning Dong et al.2022 · 66 citationsarXiv
XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale2111.09296v3 · Arun Babu, Changhan Wang, Andros Tjandra et al.2021 · 571 citationsarXiv
Improved Language Identification Through Cross-Lingual Self-Supervised Learning2107.04082v4 · Andros Tjandra, Diptanu Gon Choudhury, Frank Zhang et al.2021 · 38 citationsarXiv
Simple and Effective Zero-shot Cross-lingual Phoneme Recognition2109.11680v1 · Qiantong Xu, Alexei Baevski, Michael Auli2021 · 63 citationsarXiv
Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training2104.01027v2 · Wei-Ning Hsu, Anuroop Sriram, Alexei Baevski et al.2021 · 184 citationsarXiv
Reservoir Transformers2012.15045v2 · Sheng Shen, Alexei Baevski, Ari S. Morcos et al.2020 · 0 citationsarXiv
Large-Scale Self- and Semi-Supervised Learning for Speech Translation2104.06678v1 · Changhan Wang, Anne Wu, Juan Pino et al.2021 · 21 citationsarXiv
A Comparison of Approaches to Document-level Machine Translation2101.11040v1 · Zhiyi Ma, Sergey Edunov, Michael Auli2021 · 7 citationsarXiv
Multilingual Speech Translation with Efficient Finetuning of Pretrained Models2010.12829v4 · Xian Li, Changhan Wang, Yun Tang et al.2020 · 24 citationsarXiv
Unsupervised Cross-lingual Representation Learning for Speech Recognition2006.13979v2 · Alexis Conneau, Alexei Baevski, Ronan Collobert et al.2020 · 629 citationsarXiv
Language Models not just for Pre-training: Fast Online Neural Noisy Channel Modeling2011.07164v1 · Shruti Bhosale, Kyra Yee, Sergey Edunov et al.2020 · 3 citationsarXiv
A Comparison of Discrete Latent Variable Models for Speech Representation Learning2010.14230v1 · Henry Zhou, Alexei Baevski, Michael Auli2020 · 8 citationsarXiv
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations2006.11477v3 · Alexei Baevski, Henry Zhou, Abdelrahman Mohamed et al.2020 · 400 citationsarXiv
Self-training and Pre-training are Complementary for Speech Recognition2010.11430v1 · Qiantong Xu, Alexei Baevski, Tatiana Likhomanenko et al.2020 · 131 citationsarXiv
Beyond English-Centric Multilingual Machine Translation2010.11125v1 · Angela Fan, Shruti Bhosale, Holger Schwenk et al.2020 · 485 citationsarXiv
Self-training Improves Pre-training for Natural Language Understanding2010.02194v1 · Jingfei Du, Edouard Grave, Beliz Gunel et al.2020 · 138 citationsarXiv
On The Evaluation of Machine Translation Systems Trained With Back-Translation1908.05204v2 · Sergey Edunov, Myle Ott, Marc'Aurelio Ranzato et al.2019 · 89 citationsarXiv
The Source-Target Domain Mismatch Problem in Machine Translation1909.13151v2 · Jiajun Shen, Peng-Jen Chen, Matt Le et al.2019 · 6 citationsarXiv
Effectiveness of self-supervised pre-training for speech recognition1911.03912v3 · Alexei Baevski, Michael Auli, Abdelrahman Mohamed2019 · 99 citationsarXiv
Robust and On-the-fly Dataset Denoising for Image Classification2003.10647v2 · Jiaming Song, Lunjia Hu, Michael Auli et al.2020 · 12 citationsarXiv
vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations1910.05453v3 · Alexei Baevski, Steffen Schneider, Michael Auli2019 · 426 citationsarXiv
Depth-Adaptive Transformer1910.10073v4 · Maha Elbayad, Jiatao Gu, Edouard Grave et al.2019 · 59 citationsarXiv
Improving Conditioning in Context-Aware Sequence to Sequence Models1911.09728v1 · Xinyi Wang, Jason Weston, Michael Auli et al.2019 · 9 citationsarXiv
wav2vec: Unsupervised Pre-training for Speech Recognition1904.05862v4 · Steffen Schneider, Alexei Baevski, Ronan Collobert et al.2019 · 1,289 citationsarXiv
Simple and Effective Noisy Channel Modeling for Neural Machine Translation1908.05731v1 · Kyra Yee, Nathan Ng, Yann N. Dauphin et al.2019 · 53 citationsarXiv
GLOSS: Generative Latent Optimization of Sentence Representations1907.06385v1 · Sidak Pal Singh, Angela Fan, Michael Auli2019 · 2 citationsarXiv
ELI5: Long Form Question Answering1907.09190v1 · Angela Fan, Yacine Jernite, Ethan Perez et al.2019 · 332 citationsarXiv
Facebook FAIR's WMT19 News Translation Task Submission1907.06616v1 · Nathan Ng, Kyra Yee, Alexei Baevski et al.2019 · 326 citationsarXiv
Mixture Models for Diverse Machine Translation: Tricks of the Trade1902.07816v2 · Tianxiao Shen, Myle Ott, Michael Auli et al.2019 · 59 citationsarXiv
fairseq: A Fast, Extensible Toolkit for Sequence Modeling1904.01038v1 · Myle Ott, Sergey Edunov, Alexei Baevski et al.2019 · 2,681 citationsarXiv
Career total: 138 works. 74 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.