activity
20182022
most citedmSLAM: Massively multilingual joint pre-training for speech and text

59 citations · 137 across the 5 of their papers we have counts for

collaborators

9 papers

cs.CL202215 cited

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

Alexis Conneau, Min Ma, Simran Khanuja +6

We introduce FLEURS, the Few-shot Learning Evaluation of Universal Representations of Speech benchmark. FLEURS is an n-way parallel speech dataset in 102 languages built on top of…

cs.CL20221 cited

XTREME-S: Evaluating Cross-lingual Speech Representations

Alexis Conneau, Ankur Bapna, Yu Zhang +16

We introduce XTREME-S, a new benchmark to evaluate universal cross-lingual speech representations in many languages. XTREME-S covers four task families: speech recognition, classif…

cs.CL202259 cited

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

Ankur Bapna, Colin Cherry, Yu Zhang +6

We present mSLAM, a multilingual Speech and LAnguage Model that learns cross-lingual cross-modal representations of speech and text by pre-training jointly on large amounts of unla…

cs.CL202150 cited

SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training

Ankur Bapna, Yu-an Chung, Nan Wu +7

Unsupervised pre-training is now the predominant approach for both text and speech understanding. Self-attention models pre-trained on large amounts of unannotated data have been h…

cs.CL2020

Improving Multilingual Models with Language-Clustered Vocabularies

Hyung Won Chung, Dan Garrette, Kiat Chuan Tan +1

State-of-the-art multilingual models depend on vocabularies that cover all of the languages the model will expect to see at inference time, but the standard methods for generating…

cs.LG202012 cited

Finding Fast Transformers: One-Shot Neural Architecture Search by Component Composition

Henry Tsai, Jayden Ooi, Chun-Sung Ferng +2

Transformer-based models have achieved stateof-the-art results in many tasks in natural language processing. However, such models are usually slow at inference time, making deploym…