{"list":"other","total":73,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"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":"2004.14368","title":"VGGSound: A Large-scale Audio-Visual Dataset","created":"2020-04-29","cited_by_count":648},{"id":"2301.12503","title":"AudioLDM: Text-to-Audio Generation with Latent Diffusion Models","created":"2023-01-29","cited_by_count":599},{"id":"1912.10211","title":"PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition","created":"2019-12-21","cited_by_count":574},{"id":"2203.02053","title":"Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning","created":"2022-03-03","cited_by_count":561},{"id":"1811.02508","title":"SDR - half-baked or well done?","created":"2018-11-06","cited_by_count":423},{"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":"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":"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":"2207.09983","title":"Diffsound: Discrete Diffusion Model for Text-to-sound Generation","created":"2022-07-20","cited_by_count":257},{"id":"1708.07524","title":"Supervised Speech Separation Based on Deep Learning: An Overview","created":"2017-08-24","cited_by_count":216},{"id":"1508.04306","title":"Deep clustering: Discriminative embeddings for segmentation and separation","created":"2015-08-18","cited_by_count":212},{"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":"2202.00874","title":"HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection","created":"2022-02-02","cited_by_count":176},{"id":"1703.09452","title":"SEGAN: Speech Enhancement Generative Adversarial Network","created":"2017-03-28","cited_by_count":166},{"id":"2005.11262","title":"LibriMix: An Open-Source Dataset for Generalizable Speech Separation","created":"2020-05-22","cited_by_count":155},{"id":"2304.13731","title":"Text-to-Audio Generation using Instruction-Tuned LLM and Latent Diffusion Model","created":"2023-04-24","cited_by_count":145},{"id":"1806.03185","title":"Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separation","created":"2018-06-08","cited_by_count":125},{"id":"2101.03149","title":"VisualVoice: Audio-Visual Speech Separation with Cross-Modal Consistency","created":"2021-01-08","cited_by_count":114},{"id":"1905.04874","title":"MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement","created":"2019-05-13","cited_by_count":104},{"id":"2305.18474","title":"Make-An-Audio 2: Temporal-Enhanced Text-to-Audio Generation","created":"2023-05-29","cited_by_count":90},{"id":"2112.09418","title":"Audio Retrieval with Natural Language Queries: A Benchmark Study","created":"2021-12-17","cited_by_count":61},{"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":"2107.09817","title":"Audio Captioning Transformer","created":"2021-07-21","cited_by_count":55},{"id":"1909.01174","title":"Demucs: Deep Extractor for Music Sources with extra unlabeled data remixed","created":"2019-09-03","cited_by_count":54},{"id":"2305.13686","title":"MP-SENet: A Speech Enhancement Model with Parallel Denoising of Magnitude and Phase Spectra","created":"2023-05-23","cited_by_count":52},{"id":"2105.02192","title":"Audio Retrieval with Natural Language Queries","created":"2021-05-05","cited_by_count":49},{"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":"2203.15149","title":"CMGAN: Conformer-based Metric GAN for Speech Enhancement","created":"2022-03-28","cited_by_count":45},{"id":"1905.03330","title":"Universal Sound Separation","created":"2019-05-08","cited_by_count":41},{"id":"1706.10006","title":"Automated Audio Captioning with Recurrent Neural Networks","created":"2017-06-30","cited_by_count":40},{"id":"1904.03760","title":"Time Domain Audio Visual Speech Separation","created":"2019-04-07","cited_by_count":30},{"id":"2203.15537","title":"On Metric Learning for Audio-Text Cross-Modal Retrieval","created":"2022-03-29","cited_by_count":30},{"id":"2109.11955","title":"Visual Scene Graphs for Audio Source Separation","created":"2021-09-24","cited_by_count":29},{"id":"2006.05712","title":"Listen to What You Want: Neural Network-based Universal Sound Selector","created":"2020-06-10","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":"2303.17489","title":"Prefix tuning for automated audio captioning","created":"2023-03-30","cited_by_count":27},{"id":"2307.14335","title":"WavJourney: Compositional Audio Creation with Large Language Models","created":"2023-07-26","cited_by_count":27},{"id":"2007.00222","title":"A Transformer-based Audio Captioning Model with Keyword Estimation","created":"2020-07-01","cited_by_count":24},{"id":"2107.09998","title":"Conditional Sound Generation Using Neural Discrete Time-Frequency Representation Learning","created":"2021-07-21","cited_by_count":24},{"id":"1811.11307","title":"Improved Speech Enhancement with the Wave-U-Net","created":"2018-11-27","cited_by_count":23},{"id":"2204.05738","title":"Text-Driven Separation of Arbitrary Sounds","created":"2022-04-12","cited_by_count":23},{"id":"2205.05949","title":"Automated Audio Captioning: An Overview of Recent Progress and New Challenges","created":"2022-05-12","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":"1704.02223","title":"An Overview of Cross-media Retrieval: Concepts, Methodologies, Benchmarks and Challenges","created":"2017-04-07","cited_by_count":21},{"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":"2203.02838","title":"Leveraging Pre-trained BERT for Audio Captioning","created":"2022-03-06","cited_by_count":18},{"id":"1908.06593","title":"Audio query-based music source separation","created":"2019-08-19","cited_by_count":17},{"id":"2107.09990","title":"CL4AC: A Contrastive Loss for Audio Captioning","created":"2021-07-21","cited_by_count":16},{"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":"2210.16428","title":"Visually-Aware Audio Captioning With Adaptive Audio-Visual Attention","created":"2022-10-28","cited_by_count":13},{"id":"2203.13645","title":"Audio-text Retrieval in Context","created":"2022-03-25","cited_by_count":10},{"id":"2204.00821","title":"Improving Target Sound Extraction with Timestamp Information","created":"2022-04-02","cited_by_count":10},{"id":"2303.03857","title":"Leveraging Pre-trained AudioLDM for Sound Generation: A Benchmark Study","created":"2023-03-07","cited_by_count":10},{"id":"2305.17719","title":"Adapting Language-Audio Models as Few-Shot Audio Learners","created":"2023-05-28","cited_by_count":10},{"id":"2306.10359","title":"Text-Driven Foley Sound Generation With Latent Diffusion Model","created":"2023-06-17","cited_by_count":10},{"id":"2102.09971","title":"Speech enhancement with weakly labelled data from AudioSet","created":"2021-02-19","cited_by_count":9},{"id":"2205.01273","title":"Few-Shot Musical Source Separation","created":"2022-05-03","cited_by_count":9},{"id":"2211.05927","title":"Optimal Condition Training for Target Source Separation","created":"2022-11-11","cited_by_count":5},{"id":"2207.07429","title":"Continual Learning For On-Device Environmental Sound Classification","created":"2022-07-15","cited_by_count":4},{"id":"2306.08956","title":"Multi-Loss Convolutional Network with Time-Frequency Attention for Speech Enhancement","created":"2023-06-15","cited_by_count":2}],"next_cursor":null}