{"total":84,"rows":[{"id":"2105.01051","title":"SUPERB: Speech processing Universal PERformance Benchmark","created":"2021-05-03","cited_by_count":666,"area":null},{"id":"2301.11325","title":"MusicLM: Generating Music From Text","created":"2023-01-26","cited_by_count":448,"area":null},{"id":"2205.10643","title":"Self-Supervised Speech Representation Learning: A Review","created":"2022-05-21","cited_by_count":260,"area":null},{"id":"2302.03917","title":"Noise2Music: Text-conditioned Music Generation with Diffusion Models","created":"2023-02-08","cited_by_count":173,"area":"diffusion"},{"id":"2103.06695","title":"BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation","created":"2021-03-11","cited_by_count":106,"area":null},{"id":"2109.13226","title":"BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition","created":"2021-09-27","cited_by_count":88,"area":null},{"id":"2201.03529","title":"Head2Toe: Utilizing Intermediate Representations for Better Transfer Learning","created":"2022-01-10","cited_by_count":83,"area":null},{"id":"2102.01243","title":"PSLA: Improving Audio Tagging with Pretraining, Sampling, Labeling, and Aggregation","created":"2021-02-02","cited_by_count":82,"area":null},{"id":"2203.03022","title":"HEAR: Holistic Evaluation of Audio Representations","created":"2022-03-06","cited_by_count":78,"area":null},{"id":"2203.01205","title":"Audio Self-supervised Learning: A Survey","created":"2022-03-02","cited_by_count":65,"area":null},{"id":"2206.05408","title":"Multi-instrument Music Synthesis with Spectrogram Diffusion","created":"2022-06-11","cited_by_count":42,"area":"diffusion"},{"id":"2210.07185","title":"On the Utility of Self-supervised Models for Prosody-related Tasks","created":"2022-10-13","cited_by_count":42,"area":null},{"id":"2303.11607","title":"Transformers in Speech Processing: A Survey","created":"2023-03-21","cited_by_count":39,"area":null},{"id":"2305.19753","title":"The Tunnel Effect: Building Data Representations in Deep Neural Networks","created":"2023-05-31","cited_by_count":34,"area":null},{"id":"2110.04621","title":"Universal Paralinguistic Speech Representations Using Self-Supervised Conformers","created":"2021-10-09","cited_by_count":32,"area":null},{"id":"2306.04186","title":"Self-supervised Audio Teacher-Student Transformer for Both Clip-level and Frame-level Tasks","created":"2023-06-07","cited_by_count":25,"area":"distill"},{"id":"2101.04792","title":"Learning Efficient Representations for Keyword Spotting with Triplet Loss","created":"2021-01-12","cited_by_count":24,"area":null},{"id":"2110.03414","title":"SERAB: A multi-lingual benchmark for speech emotion recognition","created":"2021-10-07","cited_by_count":22,"area":null},{"id":"2109.13510","title":"VoxCeleb Enrichment for Age and Gender Recognition","created":"2021-09-28","cited_by_count":20,"area":null},{"id":"2305.06594","title":"V2Meow: Meowing to the Visual Beat via Video-to-Music Generation","created":"2023-05-11","cited_by_count":18,"area":null},{"id":"2203.00236","title":"TRILLsson: Distilled Universal Paralinguistic Speech Representations","created":"2022-03-01","cited_by_count":16,"area":null},{"id":"2403.02522","title":"HeAR -- Health Acoustic Representations","created":"2024-03-04","cited_by_count":15,"area":null},{"id":"2110.14769","title":"Detecting Dementia from Speech and Transcripts using Transformers","created":"2021-10-27","cited_by_count":13,"area":null},{"id":"2204.12076","title":"ATST: Audio Representation Learning with Teacher-Student Transformer","created":"2022-04-26","cited_by_count":13,"area":"distill"},{"id":"2201.09165","title":"A Pre-trained Audio-Visual Transformer for Emotion Recognition","created":"2022-01-23","cited_by_count":12,"area":null},{"id":"2205.08383","title":"Bias and Fairness on Multimodal Emotion Detection Algorithms","created":"2022-05-11","cited_by_count":10,"area":null},{"id":"2206.12038","title":"BYOL-S: Learning Self-supervised Speech Representations by Bootstrapping","created":"2022-06-24","cited_by_count":10,"area":null},{"id":"2106.02443","title":"Teaching keyword spotters to spot new keywords with limited examples","created":"2021-06-04","cited_by_count":9,"area":null},{"id":"2306.08374","title":"SpeechGLUE: How Well Can Self-Supervised Speech Models Capture Linguistic Knowledge?","created":"2023-06-14","cited_by_count":9,"area":null},{"id":"2309.07391","title":"EnCodecMAE: Leveraging neural codecs for universal audio representation learning","created":"2023-09-14","cited_by_count":9,"area":null},{"id":"2602.07143","title":"Massive Sound Embedding Benchmark (MSEB)","created":"2026-02-06","cited_by_count":9,"area":null},{"id":"2107.08248","title":"Learning De-identified Representations of Prosody from Raw Audio","created":"2021-07-17","cited_by_count":8,"area":null},{"id":"2303.05737","title":"Clinical BERTScore: An Improved Measure of Automatic Speech Recognition Performance in Clinical Settings","created":"2023-03-10","cited_by_count":8,"area":null},{"id":"2107.00594","title":"Pretext Tasks selection for multitask self-supervised speech representation learning","created":"2021-07-01","cited_by_count":7,"area":null},{"id":"2110.08895","title":"DECAR: Deep Clustering for learning general-purpose Audio Representations","created":"2021-10-17","cited_by_count":7,"area":null},{"id":"2105.02132","title":"Self-Supervised Learning from Automatically Separated Sound Scenes","created":"2021-05-05","cited_by_count":6,"area":null},{"id":"2203.16637","title":"Hybrid Handcrafted and Learnable Audio Representation for Analysis of Speech Under Cognitive and Physical Load","created":"2022-03-30","cited_by_count":6,"area":null},{"id":"2212.08663","title":"Randomized Quantization: A Generic Augmentation for Data Agnostic Self-supervised Learning","created":"2022-12-19","cited_by_count":6,"area":null},{"id":"2304.00860","title":"Designing and Evaluating Speech Emotion Recognition Systems: A reality check case study with IEMOCAP","created":"2023-04-03","cited_by_count":6,"area":null},{"id":"2107.03985","title":"Comparing Supervised Models And Learned Speech Representations For Classifying Intelligibility Of Disordered Speech On Selected Phrases","created":"2021-07-08","cited_by_count":5,"area":null},{"id":"2203.11997","title":"Federated Self-Supervised Learning for Acoustic Event Classification","created":"2022-03-22","cited_by_count":5,"area":null},{"id":"2309.12283","title":"Performance Conditioning for Diffusion-Based Multi-Instrument Music Synthesis","created":"2023-09-21","cited_by_count":5,"area":null},{"id":"2109.11086","title":"Scenario Aware Speech Recognition: Advancements for Apollo Fearless Steps & CHiME-4 Corpora","created":"2021-09-23","cited_by_count":4,"area":null},{"id":"2111.14200","title":"Transfer Learning with Jukebox for Music Source Separation","created":"2021-11-28","cited_by_count":4,"area":null},{"id":"2204.04170","title":"Automatic Data Augmentation Selection and Parametrization in Contrastive Self-Supervised Speech Representation Learning","created":"2022-04-08","cited_by_count":4,"area":null},{"id":"2305.08099","title":"Self-supervised Neural Factor Analysis for Disentangling Utterance-level Speech Representations","created":"2023-05-14","cited_by_count":4,"area":null},{"id":"2306.04374","title":"Label Aware Speech Representation Learning For Language Identification","created":"2023-06-07","cited_by_count":4,"area":null},{"id":"2310.09623","title":"A Digital Language Coherence Marker for Monitoring Dementia","created":"2023-10-14","cited_by_count":4,"area":null},{"id":"2310.09897","title":"Reformulating NLP tasks to Capture Longitudinal Manifestation of Language Disorders in People with Dementia","created":"2023-10-15","cited_by_count":4,"area":null},{"id":"2409.02384","title":"STAB: Speech Tokenizer Assessment Benchmark","created":"2024-09-04","cited_by_count":4,"area":null},{"id":"2409.12170","title":"The Unreliability of Acoustic Systems in Alzheimer's Speech Datasets with Heterogeneous Recording Conditions","created":"2024-09-11","cited_by_count":4,"area":null},{"id":"2411.15128","title":"Health AI Developer Foundations","created":"2024-11-22","cited_by_count":4,"area":null},{"id":"2505.06660","title":"TS-SUPERB: A Target Speech Processing Benchmark for Speech Self-Supervised Learning Models","created":"2025-05-10","cited_by_count":4,"area":null},{"id":"2212.03968","title":"Multimodal Vision Transformers with Forced Attention for Behavior Analysis","created":"2022-12-07","cited_by_count":3,"area":null},{"id":"2304.05600","title":"Looking Similar, Sounding Different: Leveraging Counterfactual Cross-Modal Pairs for Audiovisual Representation Learning","created":"2023-04-12","cited_by_count":3,"area":null},{"id":"2109.01537","title":"A Longitudinal Multi-modal Dataset for Dementia Monitoring and Diagnosis","created":"2021-09-03","cited_by_count":2,"area":null},{"id":"2206.10188","title":"Analysis of Self-Supervised Learning and Dimensionality Reduction Methods in Clustering-Based Active Learning for Speech Emotion Recognition","created":"2022-06-21","cited_by_count":2,"area":null},{"id":"2211.09273","title":"Privacy against Real-Time Speech Emotion Detection via Acoustic Adversarial Evasion of Machine Learning","created":"2022-11-17","cited_by_count":2,"area":null},{"id":"2309.05843","title":"Optimizing Audio Augmentations for Contrastive Learning of Health-Related Acoustic Signals","created":"2023-09-11","cited_by_count":2,"area":null},{"id":"2404.10419","title":"MAD Speech: Measures of Acoustic Diversity of Speech","created":"2024-04-16","cited_by_count":2,"area":null},{"id":"2406.06341","title":"Predicting Heart Activity from Speech using Data-driven and Knowledge-based features","created":"2024-06-10","cited_by_count":2,"area":null},{"id":"2112.08165","title":"Chimpanzee voice prints? Insights from transfer learning experiments from human voices","created":"2021-12-15","cited_by_count":1,"area":null},{"id":"2203.13628","title":"DeLoRes: Decorrelating Latent Spaces for Low-Resource Audio Representation Learning","created":"2022-03-25","cited_by_count":1,"area":null},{"id":"2210.08610","title":"Robust, General, and Low Complexity Acoustic Scene Classification Systems and An Effective Visualization for Presenting a Sound Scene Context","created":"2022-10-16","cited_by_count":1,"area":null},{"id":"2307.07325","title":"Representation Learning With Hidden Unit Clustering For Low Resource Speech Applications","created":"2023-07-14","cited_by_count":1,"area":null},{"id":"2309.10280","title":"Crowdotic: A Privacy-Preserving Hospital Waiting Room Crowd Density Estimation with Non-speech Audio","created":"2023-09-19","cited_by_count":1,"area":null},{"id":"2312.16599","title":"Relationship between auditory and semantic entrainment using Deep Neural Networks (DNN)","created":"2023-12-27","cited_by_count":1,"area":null},{"id":"2502.06664","title":"Evaluation of Deep Audio Representations for Hearables","created":"2025-02-10","cited_by_count":1,"area":null},{"id":"2506.08457","title":"Audio Generation Through Score-Based Generative Modeling: Design Principles and Implementation","created":"2025-06-10","cited_by_count":1,"area":"diffusion"},{"id":"2106.08596","title":"Temporal Convolution Networks with Positional Encoding for Evoked Expression Estimation","created":"2021-06-16","cited_by_count":0,"area":null},{"id":"2203.00613","title":"Towards a Common Speech Analysis Engine","created":"2022-03-01","cited_by_count":0,"area":null},{"id":"2207.05784","title":"Distilled Non-Semantic Speech Embeddings with Binary Neural Networks for Low-Resource Devices","created":"2022-07-12","cited_by_count":0,"area":null},{"id":"2306.00481","title":"Automatic Data Augmentation for Domain Adapted Fine-Tuning of Self-Supervised Speech Representations","created":"2023-06-01","cited_by_count":0,"area":null},{"id":"2306.10843","title":"Female mosquito detection by means of AI techniques inside release containers in the context of a Sterile Insect Technique program","created":"2023-06-19","cited_by_count":0,"area":null},{"id":"2307.10982","title":"MASR: Multi-label Aware Speech Representation","created":"2023-07-20","cited_by_count":0,"area":null},{"id":"2309.11294","title":"Beyond Accuracy: Measuring Representation Capacity of Embeddings to Preserve Structural and Contextual Information","created":"2023-09-20","cited_by_count":0,"area":null},{"id":"2312.06833","title":"The unreasonable effectiveness of AI CADe polyp detectors to generalize to new countries","created":"2023-12-11","cited_by_count":0,"area":null},{"id":"2402.10100","title":"Tuning In: Analysis of Audio Classifier Performance in Clinical Settings with Limited Data","created":"2024-02-07","cited_by_count":0,"area":null},{"id":"2403.09920","title":"Predicting Generalization of AI Colonoscopy Models to Unseen Data","created":"2024-03-14","cited_by_count":0,"area":null},{"id":"2403.15170","title":"Exploring the Task-agnostic Trait of Self-supervised Learning in the Context of Detecting Mental Disorders","created":"2024-03-22","cited_by_count":0,"area":null},{"id":"2503.04802","title":"The order in speech disorder: a scoping review of state of the art machine learning methods for clinical speech classification","created":"2025-03-03","cited_by_count":0,"area":null},{"id":"2509.00186","title":"Generalizable Audio Spoofing Detection using Non-Semantic Representations","created":"2025-08-29","cited_by_count":0,"area":null},{"id":"2607.13278","title":"Adapting Diffusion-Based Music Synthesis to Speech and Singing Voice Conversion","created":"2026-07-14","cited_by_count":0,"area":"diffusion"},{"id":"2608.16203","title":"INSPIRE: A Benchmark for Instruction-Aware Speech Retrieval","created":"2026-08-17","cited_by_count":0,"area":null}],"next_cursor":null}