Concepedia

Puyuan Peng

PP

7

Publications

224

Citations

7

H-Index

2022

Active since

Affiliations

The University of Texas at Austin(Current)

Puyuan Peng is an author at The University of Texas at Austin specializing in speech recognition, speech communication, and speech processing.

Top concepts

EngineeringSpeech ProcessingSpeech RecognitionSpeech CommunicationMachine LearningSpeech PerceptionLinguisticsDeep LearningComputer ScienceSelf-supervised Learning

Publications per year

2022–2024

7

Publications

7

MAE-AST: Masked Autoencoding Audio Spectrogram Transformer

Alan Baade, Puyuan Peng, David Harwath · Interspeech 2022 · 2022 · 76 citations

Engineering, Machine Learning, Speech Recognition +17

Word Discovery in Visually Grounded, Self-Supervised Speech Models

Puyuan Peng, David Harwath · Interspeech 2022 · 2022 · 34 citations

Language Grounding, Engineering, Machine Learning +22

Prompting the Hidden Talent of Web-Scale Speech Models for Zero-Shot Task Generalization

Puyuan Peng, Brian Yan, Shinji Watanabe et al. · 2023 · 34 citations

Natural Language Processing, Large Ai Model, Llm Fine-tuning +15

VoiceCraft: Zero-Shot Speech Editing and Text-to-Speech in the Wild

Puyuan Peng, Po-Yao Huang, Shang-Wen Li et al. · 2024 · 27 citations · Full text

Fast-Slow Transformer for Visually Grounding Speech

Puyuan Peng, David Harwath · ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · 2022 · 23 citations

Engineering, Visually Grounding Speech, Speech Recognition +17

Rows per page

1–5 of 7