Alexei Baevski

Character — United States

Computer Science · Physical Sciences

28h-index8.9kcitations65works0.02yr avg
OpenAlex↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Speech Recognition and Synthesis(47), Natural Language Processing Techniques(35), Topic Modeling(25), Music and Audio Processing(24), Speech and Audio Processing(9)

Publications65 total

Av-Data2Vec: Self-Supervised Learning of Audio-Visual Speech Representations with Contextualized Target Representations
2023· 20 cited
Toward Joint Language Modeling for Speech Units and Text
arXiv (Cornell University)·2023· 2 citedOpen Access
Measuring the Impact of Domain Factors in Self-Supervised Pre-Training
2023· 3 cited
Scaling Speech Technology to 1,000+ Languages
arXiv (Cornell University)·2023· 115 citedOpen Access
OVRL-V2: A simple state-of-art baseline for ImageNav and ObjectNav
arXiv (Cornell University)·2023· 14 citedOpen Access
AV-data2vec: Self-supervised Learning of Audio-Visual Speech Representations with Contextualized Target Representations
arXiv (Cornell University)·2023· 1 citedOpen Access
Towards End-to-End Unsupervised Speech Recognition
2022 IEEE Spoken Language Technology Workshop (SLT)·2023· 51 cited
Toward Joint Language Modeling for Speech Units and Text
2023· 7 citedOpen Access
Introducing Semantics into Speech Encoders
2023· 2 citedOpen Access
Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language
arXiv (Cornell University)·2022· 19 citedOpen Access
Introducing Semantics into Speech Encoders
arXiv (Cornell University)·2022Open Access
Simple and Effective Zero-shot Cross-lingual Phoneme Recognition
Interspeech 2022·2022· 51 cited
XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale
Interspeech 2022·2022· 457 cited
On-demand compute reduction with stochastic wav2vec 2.0
Interspeech 2022·2022· 6 cited
Wav2Vec-Aug: Improved self-supervised training with limited data
Interspeech 2022·2022· 10 cited
Simple and Effective Unsupervised Speech Synthesis
Interspeech 2022·2022· 11 cited
Masked Autoencoders that Listen
arXiv (Cornell University)·2022· 109 citedOpen Access
Wav2Vec-Aug: Improved self-supervised training with limited data
arXiv (Cornell University)·2022· 3 citedOpen Access
Improved Language Identification Through Cross-Lingual Self-Supervised Learning
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)·2022· 36 cited
Offline Visual Representation Learning for Embodied Navigation
arXiv (Cornell University)·2022· 24 citedOpen Access
page 1 of 4Next →

Frequent Co-authors

Michael Auli(43), Alexis Conneau(13), Wei-Ning Hsu(12), Qiantong Xu(8), Changhan Wang(7), Juan Pino(7), Sergey Edunov(6), Abdelrahman Mohamed(5), Ronan Collobert(5), Andros Tjandra(4), Arun Babu(4), Myle Ott(3), Angela Fan(3), Nathan Ng(3), Kushal Lakhotia(3), Yatharth Saraf(3), Steffen Schneider(3), Tatiana Likhomanenko(3), Paden Tomasello(3), Gabriel Synnaeve(3)