Search Results for author: Ho-Hsiang Wu

Found 7 papers, 4 papers with code

Learning Audio Concepts from Counterfactual Natural Language

1 code implementation10 Jan 2024 Ali Vosoughi, Luca Bondi, Ho-Hsiang Wu, Chenliang Xu

Conventional audio classification relied on predefined classes, lacking the ability to learn from free-form text.

Audio captioning Audio Classification +2

A Study on Robustness to Perturbations for Representations of Environmental Sound

no code implementations20 Mar 2022 Sangeeta Srivastava, Ho-Hsiang Wu, Joao Rulff, Magdalena Fuentes, Mark Cartwright, Claudio Silva, Anish Arora, Juan Pablo Bello

To accomplish this, we imitate channel effects by injecting perturbations to the audio signal and measure the shift in the new (perturbed) embeddings with three distance measures, making the evaluation domain-dependent but not task-dependent.

FAD Transfer Learning

Wav2CLIP: Learning Robust Audio Representations From CLIP

1 code implementation21 Oct 2021 Ho-Hsiang Wu, Prem Seetharaman, Kundan Kumar, Juan Pablo Bello

We propose Wav2CLIP, a robust audio representation learning method by distilling from Contrastive Language-Image Pre-training (CLIP).

Cross-Modal Retrieval Image Generation +3

Exploring modality-agnostic representations for music classification

1 code implementation2 Jun 2021 Ho-Hsiang Wu, Magdalena Fuentes, Juan P. Bello

We train music instrument classifiers that can take both images or sounds as input, and perform comparably to sound-only or image-only classifiers.

Classification Cross-Modal Retrieval +4

SONYC-UST-V2: An Urban Sound Tagging Dataset with Spatiotemporal Context

no code implementations11 Sep 2020 Mark Cartwright, Jason Cramer, Ana Elisa Mendez Mendez, Yu Wang, Ho-Hsiang Wu, Vincent Lostanlen, Magdalena Fuentes, Graham Dove, Charlie Mydlarz, Justin Salamon, Oded Nov, Juan Pablo Bello

In this article, we describe our data collection procedure and propose evaluation metrics for multilabel classification of urban sound tags.

CodeSearchNet Challenge: Evaluating the State of Semantic Code Search

14 code implementations20 Sep 2019 Hamel Husain, Ho-Hsiang Wu, Tiferet Gazit, Miltiadis Allamanis, Marc Brockschmidt

To enable evaluation of progress on code search, we are releasing the CodeSearchNet Corpus and are presenting the CodeSearchNet Challenge, which consists of 99 natural language queries with about 4k expert relevance annotations of likely results from CodeSearchNet Corpus.

Code Search Information Retrieval +2

Cannot find the paper you are looking for? You can Submit a new open access paper.