{"total":21,"rows":[{"id":"2306.09344","title":"DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data","created":"2023-06-15","cited_by_count":337,"area":null},{"id":"2110.08791","title":"Taming Visually Guided Sound Generation","created":"2021-10-17","cited_by_count":136,"area":null},{"id":"2104.03538","title":"MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement","created":"2021-04-08","cited_by_count":114,"area":null},{"id":"2102.05109","title":"CDPAM: Contrastive learning for perceptual audio similarity","created":"2021-02-09","cited_by_count":42,"area":null},{"id":"2404.07336","title":"PEAVS: Perceptual Evaluation of Audio-Visual Synchrony Grounded in Viewers' Opinion Scores","created":"2024-04-10","cited_by_count":13,"area":null},{"id":"2104.12922","title":"One Billion Audio Sounds from GPU-enabled Modular Synthesis","created":"2021-04-27","cited_by_count":11,"area":null},{"id":"2211.08856","title":"Challenges in creative generative models for music: a divergence maximization perspective","created":"2022-11-16","cited_by_count":3,"area":null},{"id":"2302.13542","title":"Continuous descriptor-based control for deep audio synthesis","created":"2023-02-27","cited_by_count":3,"area":null},{"id":"2107.05222","title":"Perceptual-based deep-learning denoiser as a defense against adversarial attacks on ASR systems","created":"2021-07-12","cited_by_count":2,"area":null},{"id":"2207.00344","title":"Automatic Evaluation of Speaker Similarity","created":"2022-07-01","cited_by_count":2,"area":null},{"id":"2302.08088","title":"TAPLoss: A Temporal Acoustic Parameter Loss for Speech Enhancement","created":"2023-02-16","cited_by_count":2,"area":null},{"id":"2302.08095","title":"PAAPLoss: A Phonetic-Aligned Acoustic Parameter Loss for Speech Enhancement","created":"2023-02-16","cited_by_count":2,"area":null},{"id":"2306.07678","title":"Localization of Just Noticeable Difference for Image Compression","created":"2023-06-13","cited_by_count":2,"area":null},{"id":"2209.11003","title":"Predicting pairwise preferences between TTS audio stimuli using parallel ratings data and anti-symmetric twin neural networks","created":"2022-09-22","cited_by_count":1,"area":null},{"id":"2310.09388","title":"CORN: Co-Trained Full- And No-Reference Speech Quality Assessment","created":"2023-10-13","cited_by_count":1,"area":null},{"id":"2407.10328","title":"The Interpretation Gap in Text-to-Music Generation Models","created":"2024-07-14","cited_by_count":1,"area":null},{"id":"2507.11636","title":"JSQA: Speech Quality Assessment with Perceptually-Inspired Contrastive Pretraining Based on JND Audio Pairs","created":"2025-07-15","cited_by_count":1,"area":null},{"id":"2604.05039","title":"ID-Sim: An Identity-Focused Similarity Metric","created":"2026-04-06","cited_by_count":1,"area":null},{"id":"2111.04436","title":"SEOFP-NET: Compression and Acceleration of Deep Neural Networks for Speech Enhancement Using Sign-Exponent-Only Floating-Points","created":"2021-11-08","cited_by_count":0,"area":null},{"id":"2506.11811","title":"Abstract Sound Fusion with Unconditional Inversion Models","created":"2025-06-13","cited_by_count":0,"area":null},{"id":"2609.27195","title":"Quieter Than the Room: Representation Drift and Task Robustness in Speech Encoders","created":"2026-09-23","cited_by_count":0,"area":null}],"next_cursor":null}