Mark Cartwright
YOU?
Author Swipe
View article: Expressive Range Characterization of Open Text-to-Audio Models
Expressive Range Characterization of Open Text-to-Audio Models Open
Text-to-audio models are a type of generative model that produces audio output in response to a given textual prompt. Although level generators and the properties of the functional content that they create (e.g., playability) dominate most…
View article: De Novo Design of Miniprotein Inhibitors of Bacterial Adhesins
De Novo Design of Miniprotein Inhibitors of Bacterial Adhesins Open
View article: Expressive Range Characterization of Open Text-to-Audio Models
Expressive Range Characterization of Open Text-to-Audio Models Open
Text-to-audio models are a type of generative model that produces audio output in response to a given textual prompt. Although level generators and the properties of the functional content that they create (e.g., playability) dominate most…
View article: <i>De Novo</i> Design of Miniprotein Inhibitors of Bacterial Adhesins
<i>De Novo</i> Design of Miniprotein Inhibitors of Bacterial Adhesins Open
The rise of multidrug-resistant bacterial infections necessitates the discovery of novel antimicrobial strategies. Here, we show that protein design provides a generalizable means of generating new antimicrobials by neutralizing the functi…
View article: “Choices? That's the dream”: challenges and opportunities in non-speech information closed-captioning
“Choices? That's the dream”: challenges and opportunities in non-speech information closed-captioning Open
Introduction Access to non-speech information (NSI) in video content is essential to creating accessible and engaging video content, particularly for D/deaf and Hard-of-Hearing (DHH) audiences. In this paper we present an overview of the c…
View article: EmotionCaps: Enhancing Audio Captioning Through Emotion-Augmented Data Generation
EmotionCaps: Enhancing Audio Captioning Through Emotion-Augmented Data Generation Open
Recent progress in audio-language modeling, such as automated audio captioning, has benefited from training on synthetic data generated with the aid of large-language models. However, such approaches for environmental sound captioning have…
View article: Open-Set Tagging Dataset (OST)
Open-Set Tagging Dataset (OST) Open
Open-set Tagging (OST) is a synthetic dataset of 1s clips used to evaluate source-centric representation learning models in the paper Compositional Audio Representation Learning. Due to the size of the dataset, we only share the source fil…
View article: Compositional Audio Representation Learning
Compositional Audio Representation Learning Open
Human auditory perception is compositional in nature -- we identify auditory streams from auditory scenes with multiple sound events. However, such auditory scenes are typically represented using clip-level representations that do not dise…
View article: Audio Engineering by People Who Are deaf and Hard of Hearing: Balancing Confidence and Limitations
Audio Engineering by People Who Are deaf and Hard of Hearing: Balancing Confidence and Limitations Open
With technological advancements, audio engineering has evolved from a domain exclusive to professionals to one open to amateurs. However, research is limited on the accessibility of audio engineering, particularly for deaf, Deaf, and hard …
View article: Unspoken Sound: Identifying Trends in Non-Speech Audio Captioning on YouTube
Unspoken Sound: Identifying Trends in Non-Speech Audio Captioning on YouTube Open
High-quality closed captioning of both speech and non-speech elements (e.g., music, sound effects, manner of speaking, and speaker identification) is essential for the accessibility of video content, especially for d/Deaf and hard-of-heari…
View article: Multi-label Open-set Audio Classification
Multi-label Open-set Audio Classification Open
Current audio classification models have small class vocabularies relative to the large number of sound event classes of interest in the real world. Thus, they provide a limited view of the world that may miss important yet unexpected or u…
View article: Open-Set Tagging Dataset (OST)
Open-Set Tagging Dataset (OST) Open
OST is a synthetic dataset of 1s clips to study multi-label open-set audio classification. The scripts generate an Open-Set Soundscapes dataset (OSS) of 10s soundscapes generated using Scaper. If you are not going to use this dataset, you …
View article: WASPAA 2023 Organizing Committee
WASPAA 2023 Organizing Committee Open
View article: A General Framework for Learning Procedural Audio Models of Environmental Sounds
A General Framework for Learning Procedural Audio Models of Environmental Sounds Open
This paper introduces the Procedural (audio) Variational autoEncoder (ProVE) framework as a general approach to learning Procedural Audio PA models of environmental sounds with an improvement to the realism of the synthesis while maintaini…
View article: SONYC-FSD-SED
SONYC-FSD-SED Open
Created by Yu Wang, Mark Cartwright, and Juan Pablo Bello Publication If using this data in academic work, please cite the following paper, which presented this dataset: Y. Wang, M. Cartwright, and J. P. B…
View article: SONYC-FSD-SED
SONYC-FSD-SED Open
Created by Yu Wang, Mark Cartwright, and Juan Pablo Bello Publication If using this data in academic work, please cite the following paper, which presented this dataset: Y. Wang, M. Cartwright, and J. P. B…
View article: Enhancers of Host Immune Tolerance to Bacterial Infection Discovered Using Linked Computational and Experimental Approaches (Adv. Sci. 26/2022)
Enhancers of Host Immune Tolerance to Bacterial Infection Discovered Using Linked Computational and Experimental Approaches (Adv. Sci. 26/2022) Open
Drug Repurposing Linked computational and experimental approaches identified that Xenopus laevis embryos can naturally tolerate certain bacteria by modulating their metal ion binding and hypoxia gene networks to maintain health despite hig…
View article: Enhancers of Host Immune Tolerance to Bacterial Infection Discovered Using Linked Computational and Experimental Approaches
Enhancers of Host Immune Tolerance to Bacterial Infection Discovered Using Linked Computational and Experimental Approaches Open
Current therapeutic strategies against bacterial infections focus on reduction of pathogen load using antibiotics; however, stimulation of host tolerance to infection in the presence of pathogens might offer an alternative approach. Comput…
View article: Urban Rhapsody: Large‐scale exploration of urban soundscapes
Urban Rhapsody: Large‐scale exploration of urban soundscapes Open
Noise is one of the primary quality‐of‐life issues in urban environments. In addition to annoyance, noise negatively impacts public health and educational performance. While low‐cost sensors can be deployed to monitor ambient noise levels …
View article: A Study on Robustness to Perturbations for Representations of Environmental Sound
A Study on Robustness to Perturbations for Representations of Environmental Sound Open
Audio applications involving environmental sound analysis increasingly use general-purpose audio representations, also known as embeddings, for transfer learning. Recently, Holistic Evaluation of Audio Representations (HEAR) evaluated twen…
View article: MONYC: Music of New York City Dataset
MONYC: Music of New York City Dataset Open
International audience
View article: Who calls the shots? Rethinking Few-Shot Learning for Audio
Who calls the shots? Rethinking Few-Shot Learning for Audio Open
Few-shot learning aims to train models that can recognize novel classes given just a handful of labeled examples, known as the support set. While the field has seen notable advances in recent years, they have often focused on multi-class i…
View article: Synthetic noisy urban soundscapes: a dataset of synthetic soundscapes with real urban backgrounds
Synthetic noisy urban soundscapes: a dataset of synthetic soundscapes with real urban backgrounds Open
Publication If you use this data in your work, please cite the following paper, which introduced this dataset: [1] Pishdadian, F., Wichern, G., & Le Roux, J. (2020). Finding strength in weakness: Learning to separate sound…
View article: Synthetic noisy urban soundscapes: a dataset of synthetic soundscapes with real urban backgrounds
Synthetic noisy urban soundscapes: a dataset of synthetic soundscapes with real urban backgrounds Open
Publication If you use this data in your work, please cite the following paper, which introduced this dataset: [1] Pishdadian, F., Wichern, G., & Le Roux, J. (2020). Finding strength in weakness: Learning to separate sound…
View article: FSD-MIX-CLIPS
FSD-MIX-CLIPS Open
Created by Yu Wang, Nicholas J. Bryan, Justin Salamon, Mark Cartwright, and Juan Pablo Bello Publication If using this data in academic work, please cite the following paper, which presented this dataset: …
View article: FSD-MIX-CLIPS
FSD-MIX-CLIPS Open
Created by Yu Wang, Nicholas J. Bryan, Justin Salamon, Mark Cartwright, and Juan Pablo Bello Publication If using this data in academic work, please cite the following paper, which presented this dataset: …
View article: SONYC-Backgrounds: a collection of urban background recordings from an acoustic sensor network
SONYC-Backgrounds: a collection of urban background recordings from an acoustic sensor network Open
Created by Aurora Cramer (1, 2), Mark Cartwright (3), Fatemeh Pishdadian (4), Juan Pablo Bello (1,2,5,6) 1. Music and Audio Research Lab, New York University 2. Departmen…
View article: SONYC-Backgrounds: a collection of urban background recordings from an acoustic sensor network
SONYC-Backgrounds: a collection of urban background recordings from an acoustic sensor network Open
Created by Aurora Cramer (1, 2), Mark Cartwright (3), Fatemeh Pishdadian (4), Juan Pablo Bello (1,2,5,6) 1. Music and Audio Research Lab, New York University 2. Department of Ele…
View article: A Modular Biomaterial Scaffold‐Based Vaccine Elicits Durable Adaptive Immunity to Subunit SARS‐CoV‐2 Antigens
A Modular Biomaterial Scaffold‐Based Vaccine Elicits Durable Adaptive Immunity to Subunit SARS‐CoV‐2 Antigens Open
The coronavirus disease 2019 (COVID‐19) pandemic demonstrates the importance of generating safe and efficacious vaccines that can be rapidly deployed against emerging pathogens. Subunit vaccines are considered among the safest, but protein…
View article: Enhancers of host immune tolerance to bacterial infection discovered using linked computational and experimental approaches
Enhancers of host immune tolerance to bacterial infection discovered using linked computational and experimental approaches Open
Current therapeutic strategies against bacterial infections focus on reduction of pathogen load through antibiotics; however, stimulation of host tolerance to infection might offer an alternative approach. Here we used computational transc…