Karn Watcharasupat

Karn Watcharasupat
Nanyang Technological University | ntu · School of Electrical and Electronic Engineering

Bachelor of Engineering
DSP × ML × AI for music and sounds. Research Engineer @ NTU Singapore. Incoming PhD @ Georgia Tech.

About

42
Publications
2,506
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
27
Citations
Introduction
Incoming PhD student at the Georgia Tech Center for Music Technology. Research Engineer at Nanyang Technological University, Singapore. Interdisciplinary audio ML/AI/DSP researcher with diverse domain experiences in array, spatial audio, music information retrieval, speech enhancement, and soundscapes. Also experienced in embedded systems, IoT, and cloud implementations.
Additional affiliations
August 2022 - present
Georgia Institute of Technology
Position
  • PhD Student
January 2021 - present
Georgia Institute of Technology
Position
  • Researcher
Description
  • Music Informatics Group
May 2020 - July 2020
AEvice Health
Position
  • Software Engineer
Education
January 2020 - May 2020
Georgia Institute of Technology
Field of study
  • Electrical and Computer Engineering
August 2018 - December 2021
Nanyang Technological University
Field of study
  • Electrical and Electronic Engineering

Publications

Publications (42)
Preprint
Full-text available
The selection of maskers and playback gain levels in a soundscape augmentation system is crucial to its effectiveness in improving the overall acoustic comfort of a given environment. Traditionally, the selection of appropriate maskers and gain levels has been informed by expert opinion, which may not representative of the target population, or by...
Article
Full-text available
Latte (for LATent Tensor Evaluation) is a Python library for evaluation of latent-based generative models in the fields of disentanglement learning and controllable generation. Latte is compatible with both PyTorch and TensorFlow/Keras, and provides both functional and modular APIs that can be easily extended to support other deep learning framewor...
Preprint
Full-text available
Translation of perceptual soundscape attributes from one language to another remains a challenging task that requires a high degree of fidelity in both psychoacoustic and psycholinguistic senses across the target population. Due to the inherently subjective nature of human perception, translating soundscape attributes using only small focus group d...
Presentation
Full-text available
Presentation on assessing the open-circuit voltage calibration procedure for headphone reproduction of acoustic environments. This presentation accompanies the paper: https://doi.org/10.48550/arXiv.2205.04728
Preprint
Full-text available
To increase the availability and adoption of the soundscape standard, a low-cost calibration procedure for reproduction of audio stimuli over headphones was proposed as part of the global ``Soundscape Attributes Translation Project'' (SATP) for validating ISO/TS~12913-2:2018 perceived affective quality (PAQ) attribute translations. A previous preli...
Preprint
Full-text available
Studies involving soundscape perception often exclude participants with hearing loss to prevent impaired perception from affecting experimental results. Participants are typically screened with pure tone audiometry, the "gold standard" for identifying and quantifying hearing loss at specific frequencies, and excluded if a study-dependent threshold...
Preprint
Full-text available
Studies involving soundscape perception often exclude participants with hearing loss to prevent impaired perception from affecting experimental results. Participants are typically screened with pure tone audiometry, the "gold standard" for identifying and quantifying hearing loss at specific frequencies, and excluded if a study-dependent threshold...
Preprint
Choosing optimal maskers for existing soundscapes to effect a desired perceptual change via soundscape augmentation is non-trivial due to extensive varieties of maskers and a dearth of benchmark datasets with which to compare and develop soundscape augmentation models. To address this problem, we make publicly available the ARAUS (Affective Respons...
Article
Full-text available
The ecological validity of soundscape studies usually rests on the choice of soundscapes that are representative of the perceptual space under investigation. For example, a soundscape pleasantness study might investigate locations with soundscapes ranging from “pleasant” to “annoying”. The choice of soundscapes is typically researcher led, but a pa...
Preprint
Full-text available
Convolutional recurrent networks (CRN) integrating a convolutional encoder-decoder (CED) structure and a recurrent structure have achieved promising performance for monaural speech enhancement. However, feature representation across frequency context is highly constrained due to limited receptive fields in the convolutions of CED. In this paper, we...
Preprint
Full-text available
Translation of perceptual descriptors such as the perceived affective quality attributes in the sound-scape standard (ISO/TS 12913-2:2018) is an inherently intricate task, especially if the target language is used in multiple countries. Despite geographical proximity and a shared language of Bahasa Melayu (Standard Malay), differences in culture an...
Preprint
Full-text available
The ecological validity of soundscape studies usually rests on a choice of soundscapes that are representative of the perceptual space under investigation. For example, a soundscape pleasantness study might investigate locations with soundscapes ranging from "pleasant" to "annoying". The choice of soundscapes is typically researcher-led, but a part...
Preprint
Full-text available
The introduction of ISO 12913-2:2018 has provided a framework for standardized data collection and reporting procedures for soundscape practitioners. A strong emphasis was placed on the use of calibrated head and torso simulators (HATS) for binaural audio capture to obtain an accurate subjective impression and acoustic measure of the soundscape und...
Conference Paper
Full-text available
Soundscape augmentation is an emerging approach for noise mitigation by introducing additional sounds known as "maskers" to increase acoustic comfort. Traditionally, the choice of maskers is often predicated on expert guidance or post-hoc analysis which can be time-consuming and sometimes arbitrary. Moreover, this often results in a static set of m...
Preprint
Full-text available
Soundscape augmentation is an emerging approach for noise mitigation by introducing additional sounds known as "maskers" to increase acoustic comfort. Traditionally, the choice of maskers is often predicated on expert guidance or post-hoc analysis which can be time-consuming and sometimes arbitrary. Moreover, this often results in a static set of m...
Conference Paper
Soundscape augmentation, which involves the addition of sounds known as "maskers" to a given soundscape, is a human-centric urban noise mitigation measure aimed at improving the overall sound-scape quality. However, the choice of maskers is often predicated on laborious processes and is inflexible to the time-varying nature of real-world soundscape...
Preprint
Full-text available
Latte (for LATent Tensor Evaluation) is a Python library for evaluation of latent-based generative models in the fields of disentanglement learning and controllable generation. Latte is compatible with both PyTorch and TensorFlow/Keras, and provides both functional and modular APIs that can be easily extended to support other deep learning framewor...
Technical Report
Full-text available
Controllability, despite being a much-desired property of a generative model, remains an ill-defined concept that is difficult to measure. In the context of neural music generation, a controllable system often implies an intuitive interaction between human agents and the neural model, allowing the relatively opaque neural model to be controlled by...
Conference Paper
Full-text available
Sound event localization and detection (SELD) is an emerging research topic that aims to unify the tasks of sound event detection and direction-of-arrival estimation. As a result, SELD inherits the challenges of both tasks, such as noise, reverberation, interference, polyphony, and non-stationarity of sound sources. Furthermore, SELD often faces an...
Preprint
Full-text available
Polyphonic sound event localization and detection (SELD) has many practical applications in acoustic sensing and monitoring. However, the development of real-time SELD has been limited by the demanding computational requirement of most recent SELD systems. In this work, we introduce SALSA-Lite, a fast and effective feature for polyphonic SELD using...
Conference Paper
Full-text available
We propose a dataset, AVASpeech-SMAD, to assist speech and music activity detection research. With frame-level music labels, the proposed dataset extends the existing AVASpeech dataset, which originally consists of 45 hours of audio and speech activity labels. To the best of our knowledge, the proposed AVASpeech-SMAD is the first open-source datase...
Conference Paper
Full-text available
Controllable music generation with deep generative models has become increasingly reliant on disentanglement learning techniques. However, current disentanglement metrics, such as mutual information gap (MIG), are often inadequate and misleading when used for evaluating latent representations in the presence of interdependent semantic attributes of...
Preprint
Full-text available
This paper introduces SINGA:PURA, a strongly labelled polyphonic urban sound dataset with spatiotemporal context. The data were collected via several recording units deployed across Singapore as a part of a wireless acoustic sensor network. These recordings were made as part of a project to identify and mitigate noise sources in Singapore, but also...
Preprint
Full-text available
We propose a dataset, AVASpeech-SMAD, to assist speech and music activity detection research. With frame-level music labels, the proposed dataset extends the existing AVASpeech dataset, which originally consists of 45 hours of audio and speech activity labels. To the best of our knowledge, the proposed AVASpeech-SMAD is the first open-source datase...
Preprint
Full-text available
Controllable music generation with deep generative models has become increasingly reliant on disentanglement learning techniques. However, current disentanglement metrics, such as mutual information gap (MIG), are often inadequate and misleading when used for evaluating latent representations in the presence of interdependent semantic attributes of...
Preprint
Full-text available
Echo and noise suppression is an integral part of a full-duplex communication system. Many recent acoustic echo cancellation (AEC) systems rely on a separate adaptive filtering module for linear echo suppression and a neural module for residual echo suppression. However, not only do adaptive filtering modules require convergence and remain suscepti...
Preprint
Full-text available
Sound event localization and detection (SELD) consists of two subtasks, which are sound event detection and direction-of-arrival estimation. While sound event detection mainly relies on time-frequency patterns to distinguish different sound classes, direction-of-arrival estimation uses amplitude and/or phase differences between microphones to estim...
Conference Paper
Full-text available
This paper introduces SINGA:PURA, a strongly labelled polyphonic urban sound dataset with spatiotemporal context. The data were collected via several recording units deployed across Singapore as a part of a wireless acoustic sensor network. These recordings were made as part of a project to identify and mitigate noise sources in Singapore, but also...
Conference Paper
Full-text available
Studies involving subjective evaluation require feedback from human participants to assess the performance of a system or an environment. A participant is typically presented with a set of metrics to be observed and they present their assessment accordingly. Investigator-led in-situ soundscape evaluation in ISO 12913-2 collects perceptual responses...
Conference Paper
Full-text available
Acoustic parameters obtained from calibrated acoustic equipment are part of the minimum sound-scape reporting requirements as stated in Annex A of ISO 12913-2. To dynamically monitor the acoustic environment of a large area, a large network of acoustic sensors could be deployed, albeit at significant cost. Micro-Electro-Mechanical Systems (MEMS) mi...
Preprint
Full-text available
Sound event localization and detection (SELD) is an emerging research topic that aims to unify the tasks of sound event detection and direction-of-arrival estimation. As a result, SELD inherits the challenges of both tasks, such as noise, reverberation, interference, polyphony, and non-stationarity of sound sources. Furthermore, SELD often faces an...
Preprint
Full-text available
The Sørensen-Dice Coefficient has recently seen rising popularity as a loss function (also known as Dice loss) due to its robustness in tasks where the number of negative samples significantly exceeds that of positive samples, such as semantic segmentation, natural language processing, and sound event detection. Conventional training of polyphonic...
Technical Report
Full-text available
Sound event localization and detection consists of two subtasks which are sound event detection and direction-of-arrival estimation. While sound event detection mainly relies on time-frequency patterns to distinguish different sound classes, direction-of-arrival estimation uses magnitude or phase differences between microphones to estimate source d...
Preprint
Full-text available
Sound event localization and detection consists of two subtasks which are sound event detection and direction-of-arrival estimation. While sound event detection mainly relies on time-frequency patterns to distinguish different sound classes, direction-of-arrival estimation uses magnitude or phase differences between microphones to estimate source d...
Conference Paper
In blind source separation of speech signals, the inherent imbalance in the source spectrum poses a challenge for methods that rely on single-source dominance for the estimation of the mixing matrix. We propose an algorithm based on the directional sparse filtering (DSF) framework that utilizes the Lehmer mean with learnable weights to adaptively a...
Preprint
Full-text available
In blind source separation of speech signals, the inherent imbalance in the source spectrum poses a challenge for methods that rely on single-source dominance for the estimation of the mixing matrix. We propose an algorithm based on the directional sparse filtering (DSF) framework that utilizes the Lehmer mean with learnable weights to adaptively a...
Preprint
Full-text available
In the field of music information retrieval, the task of simultaneously identifying the presence or absence of multiple musical instruments in a polyphonic recording remains a hard problem. Previous works have seen some success in improving instrument classification by applying temporal attention in a multi-instance multi-label setting, while anoth...

Network

Cited By