{"list":"other","total":54,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2206.00364","title":"Elucidating the Design Space of Diffusion-Based Generative Models","created":"2022-06-01","cited_by_count":3045},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"2107.03006","title":"Structured Denoising Diffusion Models in Discrete State-Spaces","created":"2021-07-07","cited_by_count":1719},{"id":"2010.05646","title":"HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis","created":"2020-10-12","cited_by_count":1154},{"id":"2202.04200","title":"MaskGIT: Masked Generative Image Transformer","created":"2022-02-08","cited_by_count":1099},{"id":"2310.00426","title":"PixArt-$\\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis","created":"2023-09-30","cited_by_count":864},{"id":"2107.03312","title":"SoundStream: An End-to-End Neural Audio Codec","created":"2021-07-07","cited_by_count":771},{"id":"2310.16834","title":"Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution","created":"2023-10-25","cited_by_count":745},{"id":"2203.01941","title":"Autoregressive Image Generation using Residual Quantization","created":"2022-03-03","cited_by_count":722},{"id":"2210.13438","title":"High Fidelity Neural Audio Compression","created":"2022-10-24","cited_by_count":687},{"id":"2110.04627","title":"Vector-quantized Image Modeling with Improved VQGAN","created":"2021-10-09","cited_by_count":658},{"id":"2406.04329","title":"Simplified and Generalized Masked Diffusion for Discrete Data","created":"2024-06-06","cited_by_count":626},{"id":"2410.00037","title":"Moshi: a speech-text foundation model for real-time dialogue","created":"2024-09-17","cited_by_count":568},{"id":"2012.03411","title":"MLS: A Large-Scale Multilingual Dataset for Speech Research","created":"2020-12-07","cited_by_count":476},{"id":"2205.14987","title":"A Continuous Time Framework for Discrete Denoising Models","created":"2022-05-30","cited_by_count":451},{"id":"2306.06546","title":"High-Fidelity Audio Compression with Improved RVQGAN","created":"2023-06-11","cited_by_count":431},{"id":"1809.07454","title":"Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation","created":"2018-09-20","cited_by_count":406},{"id":"2312.02696","title":"Analyzing and Improving the Training Dynamics of Diffusion Models","created":"2023-12-05","cited_by_count":402},{"id":"2406.03736","title":"Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data","created":"2024-06-06","cited_by_count":381},{"id":"2010.00475","title":"FSD50K: An Open Dataset of Human-Labeled Sound Events","created":"2020-10-01","cited_by_count":342},{"id":"1612.01840","title":"FMA: A Dataset For Music Analysis","created":"2016-12-06","cited_by_count":207},{"id":"2104.09494","title":"NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasets","created":"2021-04-19","cited_by_count":192},{"id":"2110.01763","title":"DNSMOS P.835: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressors","created":"2021-10-05","cited_by_count":172},{"id":"2211.16750","title":"Score-based Continuous-time Discrete Diffusion Models","created":"2022-11-30","cited_by_count":169},{"id":"1907.01160","title":"WHAM!: Extending Speech Separation to Noisy Environments","created":"2019-07-02","cited_by_count":156},{"id":"2211.00802","title":"Concrete Score Matching: Generalized Score Matching for Discrete Data","created":"2022-11-02","cited_by_count":148},{"id":"2006.08195","title":"Neural Networks Fail to Learn Periodic Functions and How to Fix It","created":"2020-06-15","cited_by_count":100},{"id":"2409.09305","title":"The T05 System for The VoiceMOS Challenge 2024: Transfer Learning from Deep Image Classifier to Naturalness MOS Prediction of High-Quality Synthetic Speech","created":"2024-09-14","cited_by_count":83},{"id":"2002.08933","title":"Wavesplit: End-to-End Speech Separation by Speaker Clustering","created":"2020-02-20","cited_by_count":75},{"id":"2209.15174","title":"Music Source Separation with Band-split RNN","created":"2022-09-30","cited_by_count":70},{"id":"2303.11510","title":"ICASSP 2023 Deep Noise Suppression Challenge","created":"2023-03-21","cited_by_count":65},{"id":"2406.06185","title":"EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberation","created":"2024-06-10","cited_by_count":64},{"id":"2409.05377","title":"BigCodec: Pushing the Limits of Low-Bitrate Neural Speech Codec","created":"2024-09-09","cited_by_count":46},{"id":"2401.16812","title":"SpeechBERTScore: Reference-Aware Automatic Evaluation of Speech Generation Leveraging NLP Evaluation Metrics","created":"2024-01-30","cited_by_count":38},{"id":"2312.09747","title":"SELM: Speech Enhancement Using Discrete Tokens and Language Models","created":"2023-12-15","cited_by_count":36},{"id":"2406.02092","title":"MaskSR: Masked Language Model for Full-band Speech Restoration","created":"2024-06-04","cited_by_count":24},{"id":"2410.06675","title":"SCOREQ: Speech Quality Assessment with Contrastive Regression","created":"2024-10-09","cited_by_count":24},{"id":"2502.02942","title":"GenSE: Generative Speech Enhancement via Language Models using Hierarchical Modeling","created":"2025-02-05","cited_by_count":20},{"id":"2503.00493","title":"LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement","created":"2025-03-01","cited_by_count":19},{"id":"2502.04465","title":"FocalCodec: Low-Bitrate Speech Coding via Focal Modulation Networks","created":"2025-02-06","cited_by_count":18},{"id":"2310.08981","title":"Low-latency Speech Enhancement via Speech Token Generation","created":"2023-10-13","cited_by_count":8},{"id":"2502.16240","title":"Speech Enhancement Using Continuous Embeddings of Neural Audio Codec","created":"2025-02-22","cited_by_count":7},{"id":"2510.26299","title":"Modeling strategies for speech enhancement in the latent space of a neural audio codec","created":"2025-10-30","cited_by_count":6},{"id":"2409.09357","title":"Joint Semantic Knowledge Distillation and Masked Acoustic Modeling for Full-band Speech Restoration with Improved Intelligibility","created":"2024-09-14","cited_by_count":5},{"id":"2510.20441","title":"UniSE: A Unified Framework for Decoder-Only Autoregressive LM-Based Speech Enhancement","created":"2025-10-23","cited_by_count":4},{"id":"2510.02187","title":"High-Fidelity Speech Enhancement via Discrete Audio Tokens","created":"2025-10-02","cited_by_count":2},{"id":"2601.21940","title":"DisContSE: Single-Step Diffusion Speech Enhancement Based on Joint Discrete and Continuous Embeddings","created":"2026-01-29","cited_by_count":2},{"id":"2507.12825","title":"Autoregressive Speech Enhancement via Acoustic Tokens","created":"2025-07-17","cited_by_count":1},{"id":"2510.09974","title":"Universal Discrete-Domain Speech Enhancement","created":"2025-10-11","cited_by_count":1}],"next_cursor":null}