Alert button
Picture for Alexis Conneau

Alexis Conneau

Alert button

Toward Joint Language Modeling for Speech Units and Text

Oct 12, 2023
Ju-Chieh Chou, Chung-Ming Chien, Wei-Ning Hsu, Karen Livescu, Arun Babu, Alexis Conneau, Alexei Baevski, Michael Auli

Figure 1 for Toward Joint Language Modeling for Speech Units and Text
Figure 2 for Toward Joint Language Modeling for Speech Units and Text
Figure 3 for Toward Joint Language Modeling for Speech Units and Text
Figure 4 for Toward Joint Language Modeling for Speech Units and Text
Viaarxiv icon

Scaling Speech Technology to 1,000+ Languages

May 22, 2023
Vineel Pratap, Andros Tjandra, Bowen Shi, Paden Tomasello, Arun Babu, Sayani Kundu, Ali Elkahky, Zhaoheng Ni, Apoorv Vyas, Maryam Fazel-Zarandi, Alexei Baevski, Yossi Adi, Xiaohui Zhang, Wei-Ning Hsu, Alexis Conneau, Michael Auli

Figure 1 for Scaling Speech Technology to 1,000+ Languages
Figure 2 for Scaling Speech Technology to 1,000+ Languages
Figure 3 for Scaling Speech Technology to 1,000+ Languages
Figure 4 for Scaling Speech Technology to 1,000+ Languages
Viaarxiv icon

Textually Pretrained Speech Language Models

May 22, 2023
Michael Hassid, Tal Remez, Tu Anh Nguyen, Itai Gat, Alexis Conneau, Felix Kreuk, Jade Copet, Alexandre Defossez, Gabriel Synnaeve, Emmanuel Dupoux, Roy Schwartz, Yossi Adi

Figure 1 for Textually Pretrained Speech Language Models
Figure 2 for Textually Pretrained Speech Language Models
Figure 3 for Textually Pretrained Speech Language Models
Figure 4 for Textually Pretrained Speech Language Models
Viaarxiv icon

Scaling Laws for Generative Mixed-Modal Language Models

Jan 10, 2023
Armen Aghajanyan, Lili Yu, Alexis Conneau, Wei-Ning Hsu, Karen Hambardzumyan, Susan Zhang, Stephen Roller, Naman Goyal, Omer Levy, Luke Zettlemoyer

Figure 1 for Scaling Laws for Generative Mixed-Modal Language Models
Figure 2 for Scaling Laws for Generative Mixed-Modal Language Models
Figure 3 for Scaling Laws for Generative Mixed-Modal Language Models
Figure 4 for Scaling Laws for Generative Mixed-Modal Language Models
Viaarxiv icon

FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech

May 25, 2022
Alexis Conneau, Min Ma, Simran Khanuja, Yu Zhang, Vera Axelrod, Siddharth Dalmia, Jason Riesa, Clara Rivera, Ankur Bapna

Figure 1 for FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech
Figure 2 for FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech
Figure 3 for FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech
Figure 4 for FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech
Viaarxiv icon

XTREME-S: Evaluating Cross-lingual Speech Representations

Apr 13, 2022
Alexis Conneau, Ankur Bapna, Yu Zhang, Min Ma, Patrick von Platen, Anton Lozhkov, Colin Cherry, Ye Jia, Clara Rivera, Mihir Kale, Daan Van Esch, Vera Axelrod, Simran Khanuja, Jonathan H. Clark, Orhan Firat, Michael Auli, Sebastian Ruder, Jason Riesa, Melvin Johnson

Figure 1 for XTREME-S: Evaluating Cross-lingual Speech Representations
Figure 2 for XTREME-S: Evaluating Cross-lingual Speech Representations
Figure 3 for XTREME-S: Evaluating Cross-lingual Speech Representations
Figure 4 for XTREME-S: Evaluating Cross-lingual Speech Representations
Viaarxiv icon

Leveraging unsupervised and weakly-supervised data to improve direct speech-to-speech translation

Mar 24, 2022
Ye Jia, Yifan Ding, Ankur Bapna, Colin Cherry, Yu Zhang, Alexis Conneau, Nobuyuki Morioka

Figure 1 for Leveraging unsupervised and weakly-supervised data to improve direct speech-to-speech translation
Figure 2 for Leveraging unsupervised and weakly-supervised data to improve direct speech-to-speech translation
Figure 3 for Leveraging unsupervised and weakly-supervised data to improve direct speech-to-speech translation
Figure 4 for Leveraging unsupervised and weakly-supervised data to improve direct speech-to-speech translation
Viaarxiv icon

mSLAM: Massively multilingual joint pre-training for speech and text

Feb 03, 2022
Ankur Bapna, Colin Cherry, Yu Zhang, Ye Jia, Melvin Johnson, Yong Cheng, Simran Khanuja, Jason Riesa, Alexis Conneau

Figure 1 for mSLAM: Massively multilingual joint pre-training for speech and text
Figure 2 for mSLAM: Massively multilingual joint pre-training for speech and text
Figure 3 for mSLAM: Massively multilingual joint pre-training for speech and text
Figure 4 for mSLAM: Massively multilingual joint pre-training for speech and text
Viaarxiv icon

XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale

Nov 19, 2021
Arun Babu, Changhan Wang, Andros Tjandra, Kushal Lakhotia, Qiantong Xu, Naman Goyal, Kritika Singh, Patrick von Platen, Yatharth Saraf, Juan Pino, Alexei Baevski, Alexis Conneau, Michael Auli

Figure 1 for XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale
Figure 2 for XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale
Figure 3 for XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale
Figure 4 for XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale
Viaarxiv icon