activity
20152024
most citedPay Less Attention with Lightweight and Dynamic Convolutions

318 citations · 1.2k across the 25 of their papers we have counts for

collaborators
Showing 2022Show all

5 papers · 1 filter

cs.CL20222 cited

Simple and Effective Unsupervised Speech Translation

Changhan Wang, Hirofumi Inaguma, Peng-Jen Chen +5

The amount of labeled data to train models for speech tasks is limited for most languages, however, the data scarcity is exacerbated for speech translation which requires labeled d…

cs.LG2022

On-demand compute reduction with stochastic wav2vec 2.0

Apoorv Vyas, Wei-Ning Hsu, Michael Auli +1

Squeeze and Efficient Wav2vec (SEW) is a recently proposed architecture that squeezes the input to the transformer encoder for compute efficient pre-training and inference with wav…

cs.SD20221 cited

Simple and Effective Unsupervised Speech Synthesis

Alexander H. Liu, Cheng-I Jeff Lai, Wei-Ning Hsu +3

We introduce the first unsupervised speech synthesis system based on a simple, yet effective recipe. The framework leverages recent work in unsupervised speech recognition as well…

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.CL2022

Unified Speech-Text Pre-training for Speech Translation and Recognition

Yun Tang, Hongyu Gong, Ning Dong +8

We describe a method to jointly pre-train speech and text in an encoder-decoder modeling framework for speech translation and recognition. The proposed method incorporates four sel…