标签:sound

GANs & REELS Creating Irish Music Using a Generative Adversarial Network

GANs & REELS Creating Irish Music Using a Generative Adversarial Network Antonina Kolokolova, Mitchell Billard, Robert Bishop, Moustafa Elsisy & Zachary NorthcottDepartme……

Automatic selection of eye tracking variables in visual categorization in adults and infants

Automatic selection of eye tracking variables in visual categorization in adults and infants Samuel Rivera13   Catherine A. Best23   Hyungwook Yim23 &ems……

Optimizing Short-Time Fourier Transform Parameters via Gradient Descent

Optimizing Short-Time Fourier Transform Parameters via Gradient Descent Abstract The Short-Time Fourier Transform (STFT) has been a staple of signal processing, often being the……

Attribution Preservation in Network Compression for Reliable Network Interpretation

Attribution Preservation in Network Compression for Reliable Network Interpretation Geondo Park1, June Yong Yang11, Sung Ju Hwang1,2, Eunho Yang1,2KAIST1, AITRICS2, South Korea{g……

Customizing Triggers with Concealed Data Poisoning

Customizing Triggers with Concealed Data Poisoning Eric Wallace★UC Berkeley&Tony Z. Zhao★UC Berkeley{ericwallace,tonyzhao0824}@berkeley.edu &Shi FengUniversit……

Neural Passage Retrieval with Improved Negative Contrast

Neural Passage Retrieval with Improved Negative Contrast Jing Lu1, Gustavo Hernández Ábrego2, Ji Ma2, Jianmo Ni2, Yinfei Yang21Human Language Technology Research In……

Transcription Is All You Need: Learning to Separate Musical Mixtures with Score as Supervision

Transcription Is All You Need: Learning to Separate Musical Mixtures with Score as Supervision Abstract Most music source separation systems require large collections of isolat……

WaveTransformer: A Novel Architecture for Audio Captioning Based on Learning Temporal and Time-Frequency Information

WaveTransformer: A Novel Architecture for Audio Captioning Based on Learning Temporal and Time-Frequency Information An Tran, Konstantinos Drossos, and Tuomas VirtanenAudio Resea……

Where Is the Normative Proof? Assumptions and Contradictions in ML Fairness Research

Where Is the Normative Proof? Assumptions and Contradictions in ML Fairness Research A. Feder CooperDepartment of Computer ScienceCornell Universityafc78@cornell.edu Abstract……

MicAugment: One-shot Microphone Style Transfer

MicAugment: One-shot Microphone Style Transfer Abstract A crucial aspect for the successful deployment of audio-based models “in-the-wild” is the robustness to the ……