AIConfPaper
← Search

Peter Wu

9 accepted papers

2025

Humans Hallucinate Too: Language Models Identify and Correct Subjective Annotation Errors With Label-in-a-Haystack Prompts

Georgios Chochlakis, Peter Wu, Tikka Arjun Singh Bedi, Marcus Ma, Kristina Lerman, Shrikanth Narayanan
EMNLP 2025

Modeling complex subjective tasks in Natural Language Processing, such as recognizing emotion and morality, is considerably challenging due to significant variation in human annotations. This variation often reflects reasonable differences in semantic interpretations rather than mere noise, necessit

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2024

Towards an Interpretable Representation of Speaker Identity via Perceptual Voice Qualities

Robin Netzorg, Bohan Yu, Andrea Guzman, Peter Wu, Luna McNulty, Gopala Krishna Anumanchipalli
ICASSP 2024accepted

Unlike other data modalities such as text and vision, speech does not lend itself to easy interpretation. While lay people can understand how to describe an image or sentence via perception, non-expert descriptions of speech often end at high-level demographic information, such as gender or age. In…

Cited by 0Source ↗Scholar ↗
2023

A Fast and Accurate Pitch Estimation Algorithm Based on the Pseudo Wigner-Ville Distribution

Yisi Liu, Peter Wu, Alan W. Black, Gopala Krishna Anumanchipalli
ICASSP 2023accepted

Estimation of fundamental frequency (F0) in voiced segments of speech signals, also known as pitch tracking, plays a crucial role in pitch synchronous speech analysis, speech synthesis, and speech manipulation. In this paper, we capitalize on the high time and frequency resolution of the pseudo Wign…

Cited by 0Source ↗Scholar ↗
2023

Articulation GAN: Unsupervised Modeling of Articulatory Learning

Gasper Begus, Alan Zhou, Peter Wu, Gopala Krishna Anumanchipalli
ICASSP 2023accepted

Generative deep neural networks are widely used for speech synthesis, but most existing models directly generate waveforms or spectral outputs. Humans, however, produce speech by controlling articulators, which results in the production of speech sounds through physical properties of sound propagati…

Cited by 0Source ↗Scholar ↗
2023

Evidence of Vocal Tract Articulation in Self-Supervised Learning of Speech

Cheol Jun Cho, Peter Wu, Abdelrahman Mohamed, Gopala Krishna Anumanchipalli
ICASSP 2023accepted

Recent self-supervised learning (SSL) models have proven to learn rich representations of speech, which can readily be utilized by diverse downstream tasks. To understand such utilities, various analyses have been done for speech SSL models to reveal which and how information is encoded in the learn…

Cited by 0Source ↗Scholar ↗
2023

Speaker-Independent Acoustic-to-Articulatory Speech Inversion

Peter Wu, Li-Wei Chen, Cheol Jun Cho, Shinji Watanabe, Louis Goldstein, Alan W. Black +1
ICASSP 2023accepted

To build speech processing methods that can handle speech as naturally as humans, researchers have explored multiple ways of building an invertible mapping from speech to an interpretable space. The articulatory space is a promising inversion target, since this space captures the mechanics of speech…

Cited by 39Source ↗Scholar ↗
2022

PACS: A Dataset for Physical Audiovisual Commonsense Reasoning

Samuel Yu, Peter Wu, Paul Pu Liang, Ruslan Salakhutdinov, Louis-Philippe Morency
ECCV 2022poster

"In order for AI to be safely deployed in real-world scenarios such as hospitals, schools, and the workplace, it must be able to robustly reason about the physical world. Fundamental to this reasoning is physical common sense: understanding the physical properties and affordances of available object…

Cited by 19Source ↗PDF ↗code ↗Scholar ↗
2022

Training Strategies for Automatic Song Writing: A Unified Framework Perspective

Tao Qian, Jiatong Shi, Shuai Guo, Peter Wu, Qin Jin
ICASSP 2022accepted

Automatic song writing (ASW) typically involves four tasks: lyric-to-lyric generation, melody-to-melody generation, lyric-to-melody generation, and melody-to-lyric generation. Previous works have mainly focused on individual tasks without considering the correlation between them, and thus a unified…

Cited by 0Source ↗Scholar ↗
2021

MultiBench: Multiscale Benchmarks for Multimodal Representation Learning

Paul Pu Liang, Yiwei Lyu, Xiang Fan, Zetian Wu, Yun Cheng, Jason Wu +6
NeurIPS 2021poster

Learning multimodal representations involves integrating information from multiple heterogeneous sources of data. It is a challenging yet crucial area with numerous real-world applications in multimedia, affective computing, robotics, finance, human-computer interaction, and healthcare. Unfortunatel…

Cited by 186Source ↗Scholar ↗