0

Karn N. Watcharasupat

Papers
16

Cite

Notes

Only stored in your browser.

Attribution

Affiliations & profile
Semantic Scholar
Attribution policy →
16papers

Authored papers

16

A Stem-Agnostic Single-Decoder System for Music Source Separation Beyond Four Stems

arXiv 2024

2024

Facing the Music: Tackling Singing Voice Separation in Cinematic Audio Source Separation

arXiv 2024

2024

A Generalized Bandsplit Neural Network for Cinematic Audio Source Separation

arXiv 2023

2023

Quantifying Spatial Audio Quality Impairment

arXiv 2023

2023

Crossing the Linguistic Causeway: Ethnonational Differences on Soundscape Attributes in Bahasa Melayu

arXiv 2023

2023

ARAUS: A Large-Scale Dataset and Baseline Models of Affective Responses to Augmented Urban Soundscapes

arXiv 2022

2022

Crossing the Linguistic Causeway: A Binational Approach for Translating Soundscape Attributes to Bahasa Melayu

arXiv 2022

2022

Assessment of a cost-effective headphone calibration procedure for soundscape evaluations

arXiv 2022

2022

Singapore Soundscape Site Selection Survey (S5): Identification of Characteristic Soundscapes of Singapore via Weighted k-means Clustering

arXiv 2022

2022

Do uHear? Validation of uHear App for Preliminary Screening of Hearing Ability in Soundscape Studies

arXiv 2022

2022

SALSA: Spatial Cue-Augmented Log-Spectrogram Features for Polyphonic Sound Event Localization and Detection

arXiv 2021

2021

Latte: Cross-framework Python Package for Evaluation of Latent-Based Generative Models

arXiv 2021

2021

A Strongly-Labelled Polyphonic Dataset of Urban Sounds with Spatiotemporal Context

arXiv 2021

2021

AVASpeech-SMAD: A Strongly Labelled Speech and Music Activity Detection Dataset with Label Co-Occurrence

arXiv 2021

2021

SALSA-Lite: A Fast and Effective Feature for Polyphonic Sound Event Localization and Detection with Microphone Arrays

arXiv 2021

2021

Evaluation of Latent Space Disentanglement in the Presence of Interdependent Attributes

arXiv 2021

2021

Affiliations

No known affiliations.

Frequent co-authors

10

from 16 papers