activity
20132022
most citedRobustFill: Neural Program Learning under Noisy I/O

107 citations · 137 across the 9 of their papers we have counts for

collaborators

18 papers

cs.CL2022

SUPERB @ SLT 2022: Challenge on Generalization and Efficiency of Self-Supervised Speech Representation Learning

Tzu-hsun Feng, Annie Dong, Ching-Feng Yeh +11

We present the SUPERB challenge at SLT 2022, which aims at learning self-supervised speech representation for better performance, generalization, and efficiency. The challenge buil…

cs.CL20223 cited

SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities

Hsiang-Sheng Tsai, Heng-Jui Chang, Wen-Chin Huang +14

Transfer learning has proven to be crucial in advancing the state of speech and natural language processing research in recent years. In speech, a model pre-trained by self-supervi…

cs.CL20224 cited

textless-lib: a Library for Textless Spoken Language Processing

Eugene Kharitonov, Jade Copet, Kushal Lakhotia +8

Textless spoken language processing research aims to extend the applicability of standard NLP toolset onto spoken language and languages with few or no textual resources. In this p…

cs.CV2022

Object Detection in Aerial Images: What Improves the Accuracy?

Hashmat Shadab Malik, Ikboljon Sobirov, Abdelrahman Mohamed

Object detection is a challenging and popular computer vision problem. The problem is even more challenging in aerial images due to significant variation in scale and viewpoint in…

cs.CL2021

SUPERB: Speech processing Universal PERformance Benchmark

Shu-wen Yang, Po-Han Chi, Yung-Sung Chuang +17

Self-supervised learning (SSL) has proven vital for advancing research in natural language processing (NLP) and computer vision (CV). The paradigm pretrains a shared model on large…

cs.SD2021

Speech Resynthesis from Discrete Disentangled Self-Supervised Representations

Adam Polyak, Yossi Adi, Jade Copet +5

We propose using self-supervised discrete representations for the task of speech resynthesis. To generate disentangled representation, we separately extract low-bitrate representat…