Awesome Speech Audio

Papers Topics Trending Leaderboards Authors Datasets Learn Ask AI Map Tools Packs News Videos

BrowsePapersThe full index, filterable and sortable.TopicsThe same papers grouped by subject tag.TrendingWhat moved this week, and by how much.AuthorsWho publishes here, and who they publish with.MapThe collection laid out by embedding similarity.

CompareLeaderboardsBenchmark tables, with the paper behind each number.DatasetsThe datasets these papers train and evaluate on.ToolsCode and libraries released alongside the papers.

ReadLearnOrdered routes from background reading to current work.Ask AIAsk a question and get answers cited to these papers.VideosThe most-watched talks and lectures in this field.PacksShort curated sets built around one question.

FollowNewsPress and coverage tied back to the papers.BlogsAuthor and lab write-ups of their own work.NewsletterEmail digest of what changed, on a schedule.Research RadarPaste an abstract, get matches across every collection.

YoursSavedPapers you bookmarked in this browser.

← authors · overview

Loading author…

Stay Updated

E-Mail Digest Research Radar

Submit a paper · Privacy · Terms

© 2026 Awesome Papers.

Antonio Torralba — most-cited papers & profile · Speech Audio

← authors · overview

Antonio Torralba

93 papers · 31 citations · 126 h-index

Citigroup · Dominica State College · IIT@MIT · MIT Computer Science and Artificial Intelligence Laboratory · Massachusetts Institute of Technology

Google Scholar ↗Semantic Scholar ↗OpenAlex ↗

Most-cited papers

SoundNet: Learning Sound Representations from Unlabeled Video
2016
Jointly Discovering Visual Objects and Spoken Words from Raw Sensory Input
2018
The Sound of Pixels
2018
The Sound of Motions
2019
Self-Supervised Audio-Visual Co-Segmentation
2019
Music Gesture for Visual Sound Separation
2020
AVLnet: Learning Audio-Visual Language Representations from Instructional Videos
2020
Foley Music: Learning to Generate Music from Videos
2020
Learning Neural Acoustic Fields
2022
Physics-Driven Diffusion Models for Impact Sound Synthesis from Videos
2023
Improving Factuality and Reasoning in Language Models through Multiagent Debate
2023

Top co-authors

Chuang Gan · 7 Hang Zhao · 4 Joshua B. Tenenbaum · 4 Andrew Rouditchenko · 3 Carl Vondrick · 2 David Harwath · 2 Deng Huang · 2 Josh McDermott · 2 Yilun Du · 2 Adri\`a Recasens · 1 and James Glass · 1 Andrew Luo · 1

Topics

Multimodal Audio Audio Understanding Music Generation cs.CV cs.LG cs.SD eess.AS Speech Recognition Audio Generation cs.RO