{"list":"other","total":65,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2211.06687","title":"Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation","created":"2022-11-12","cited_by_count":719},{"id":"2210.13438","title":"High Fidelity Neural Audio Compression","created":"2022-10-24","cited_by_count":687},{"id":"2004.14368","title":"VGGSound: A Large-scale Audio-Visual Dataset","created":"2020-04-29","cited_by_count":648},{"id":"2209.03143","title":"AudioLM: a Language Modeling Approach to Audio Generation","created":"2022-09-07","cited_by_count":616},{"id":"1912.07875","title":"Libri-Light: A Benchmark for ASR with Limited or No Supervision","created":"2019-12-17","cited_by_count":467},{"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":"1910.09387","title":"Clotho: An Audio Captioning Dataset","created":"2019-10-21","cited_by_count":358},{"id":"2308.05734","title":"AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining","created":"2023-08-10","cited_by_count":344},{"id":"2010.00475","title":"FSD50K: An Open Dataset of Human-Labeled Sound Events","created":"2020-10-01","cited_by_count":342},{"id":"2209.15352","title":"AudioGen: Textually Guided Audio Generation","created":"2022-09-30","cited_by_count":295},{"id":"2207.06405","title":"Masked Autoencoders that Listen","created":"2022-07-13","cited_by_count":273},{"id":"2303.17395","title":"WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research","created":"2023-03-30","cited_by_count":267},{"id":"1804.03160","title":"The Sound of Pixels","created":"2018-04-09","cited_by_count":259},{"id":"1708.07524","title":"Supervised Speech Separation Based on Deep Learning: An Overview","created":"2017-08-24","cited_by_count":216},{"id":"1607.00325","title":"Permutation Invariant Training of Deep Models for Speaker-Independent Multi-talker Speech Separation","created":"2016-07-01","cited_by_count":191},{"id":"2402.01831","title":"Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities","created":"2024-02-02","cited_by_count":186},{"id":"1804.03619","title":"Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation","created":"2018-04-10","cited_by_count":162},{"id":"2310.00704","title":"UniAudio: An Audio Foundation Model Toward Universal Audio Generation","created":"2023-10-01","cited_by_count":127},{"id":"1904.07750","title":"Co-Separating Sounds of Visual Objects","created":"2019-04-16","cited_by_count":110},{"id":"2109.13821","title":"Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme","created":"2021-09-28","cited_by_count":100},{"id":"2304.00830","title":"AUDIT: Audio Editing by Following Instructions with Latent Diffusion Models","created":"2023-04-03","cited_by_count":83},{"id":"1910.12607","title":"Generative Pre-Training for Speech with Autoregressive Predictive Coding","created":"2019-10-23","cited_by_count":82},{"id":"2203.16691","title":"MAE-AST: Masked Autoencoding Audio Spectrogram Transformer","created":"2022-03-30","cited_by_count":82},{"id":"2203.03022","title":"HEAR: Holistic Evaluation of Audio Representations","created":"2022-03-06","cited_by_count":78},{"id":"2005.08392","title":"Vector-Quantized Autoregressive Predictive Coding","created":"2020-05-17","cited_by_count":69},{"id":"2011.01143","title":"Into the Wild with AudioScope: Unsupervised Audio-Visual Separation of On-Screen Sounds","created":"2020-11-02","cited_by_count":55},{"id":"2109.05418","title":"Decoupling Magnitude and Phase Estimation with Deep ResUNet for Music Source Separation","created":"2021-09-12","cited_by_count":48},{"id":"2203.15147","title":"Separate What You Describe: Language-Queried Audio Source Separation","created":"2022-03-28","cited_by_count":45},{"id":"2308.05037","title":"Separate Anything You Describe","created":"2023-08-09","cited_by_count":43},{"id":"2105.04090","title":"MuseMorphose: Full-Song and Fine-Grained Piano Music Style Transfer with One Transformer VAE","created":"2021-05-10","cited_by_count":40},{"id":"2009.06122","title":"ICASSP 2021 Deep Noise Suppression Challenge","created":"2020-09-14","cited_by_count":27},{"id":"2112.07891","title":"Zero-shot Audio Source Separation through Query-based Learning from Weakly-labeled Data","created":"2021-12-15","cited_by_count":27},{"id":"2303.10667","title":"Audio-Text Models Do Not Yet Leverage Natural Language","created":"2023-03-19","cited_by_count":26},{"id":"2204.05738","title":"Text-Driven Separation of Arbitrary Sounds","created":"2022-04-12","cited_by_count":23},{"id":"2212.07065","title":"CLIPSep: Learning Text-queried Sound Separation with Noisy Unlabeled Videos","created":"2022-12-14","cited_by_count":23},{"id":"2211.02250","title":"Real-Time Target Sound Extraction","created":"2022-11-04","cited_by_count":22},{"id":"2011.11844","title":"Densely connected multidilated convolutional networks for dense prediction tasks","created":"2020-11-21","cited_by_count":21},{"id":"2409.07614","title":"FlowSep: Language-Queried Sound Separation with Rectified Flow Matching","created":"2024-09-11","cited_by_count":21},{"id":"1904.11148","title":"Divide and Conquer: A Deep CASA Approach to Talker-independent Monaural Speaker Separation","created":"2019-04-25","cited_by_count":20},{"id":"2303.16342","title":"Language-Guided Audio-Visual Source Separation via Trimodal Consistency","created":"2023-03-28","cited_by_count":20},{"id":"2011.02421","title":"One-shot conditional audio filtering of arbitrary sounds","created":"2020-11-04","cited_by_count":18},{"id":"2202.07273","title":"SpeechPainter: Text-conditioned Speech Inpainting","created":"2022-02-15","cited_by_count":17},{"id":"2005.05032","title":"GACELA -- A generative adversarial context encoder for long audio inpainting","created":"2020-05-11","cited_by_count":15},{"id":"2305.07447","title":"Universal Source Separation with Weakly Labelled Data","created":"2023-05-11","cited_by_count":15},{"id":"2204.03895","title":"SoundBeam: Target sound extraction conditioned on sound-class labels and enrollment clues for increased performance and continuous learning","created":"2022-04-08","cited_by_count":14},{"id":"1911.02182","title":"Finding Strength in Weakness: Learning to Separate Sounds with Weak Supervision","created":"2019-11-06","cited_by_count":13},{"id":"2310.04567","title":"DPM-TSE: A Diffusion Probabilistic Model for Target Sound Extraction","created":"2023-10-06","cited_by_count":12},{"id":"2306.00561","title":"Masked Autoencoders with Multi-Window Local-Global Attention Are Better Audio Learners","created":"2023-06-01","cited_by_count":11},{"id":"2204.00821","title":"Improving Target Sound Extraction with Timestamp Information","created":"2022-04-02","cited_by_count":10},{"id":"2106.00847","title":"Sparse, Efficient, and Semantic Mixture Invariant Training: Taming In-the-Wild Unsupervised Sound Separation","created":"2021-06-01","cited_by_count":9},{"id":"2410.21269","title":"OmniSep: Unified Omni-Modality Sound Separation with Query-Mixup","created":"2024-10-28","cited_by_count":8},{"id":"2202.03875","title":"MixCycle: Unsupervised Speech Separation via Cyclic Mixture Permutation Invariant Training","created":"2022-02-08","cited_by_count":7},{"id":"2207.08363","title":"Latent-Domain Predictive Neural Speech Coding","created":"2022-07-18","cited_by_count":7},{"id":"2404.01740","title":"Weakly-supervised Audio Separation via Bi-modal Semantic Similarity","created":"2024-04-02","cited_by_count":5},{"id":"2407.04936","title":"A Reference-free Metric for Language-Queried Audio Source Separation using Contrastive Language-Audio Pretraining","created":"2024-07-06","cited_by_count":5},{"id":"2409.13152","title":"Leveraging Audio-Only Data for Text-Queried Target Sound Extraction","created":"2024-09-20","cited_by_count":4},{"id":"2409.09398","title":"Language-Queried Target Sound Extraction Without Parallel Training Data","created":"2024-09-14","cited_by_count":3},{"id":"2503.12115","title":"Universal Speech Token Learning via Low-Bitrate Neural Codec and Pretrained Representations","created":"2025-03-15","cited_by_count":3}],"next_cursor":null}