{"total":30,"rows":[{"id":"2111.10592","title":"Deep Spoken Keyword Spotting: An Overview","created":"2021-11-20","cited_by_count":43,"area":null},{"id":"2303.11607","title":"Transformers in Speech Processing: A Survey","created":"2023-03-21","cited_by_count":39,"area":null},{"id":"2307.10655","title":"A Survey of What to Share in Federated Learning: Perspectives on Model Utility, Privacy Leakage, and Communication Efficiency","created":"2023-07-20","cited_by_count":21,"area":null},{"id":"2211.08469","title":"Deep learning for table detection and structure recognition: A survey","created":"2022-11-15","cited_by_count":15,"area":null},{"id":"2405.07354","title":"SoccerNet-Echoes: A Soccer Game Audio Commentary Dataset","created":"2024-05-12","cited_by_count":12,"area":null},{"id":"2412.13573","title":"Seeking Consistent Flat Minima for Better Domain Generalization via Refining Loss Landscapes","created":"2024-12-18","cited_by_count":10,"area":null},{"id":"2102.06237","title":"An Investigation of End-to-End Models for Robust Speech Recognition","created":"2021-02-11","cited_by_count":9,"area":null},{"id":"2603.16952","title":"Embodied Foundation Models at the Edge: A Survey of Deployment Constraints and Mitigation Strategies","created":"2026-03-16","cited_by_count":9,"area":null},{"id":"2111.15156","title":"Automated Speech Scoring System Under The Lens: Evaluating and interpreting the linguistic cues for language proficiency","created":"2021-11-30","cited_by_count":6,"area":null},{"id":"2304.08275","title":"Implementing Responsible AI: Tensions and Trade-Offs Between Ethics Aspects","created":"2023-04-17","cited_by_count":6,"area":null},{"id":"2502.07255","title":"Beyond Confidence: Adaptive Abstention in Dual-Threshold Conformal Prediction for Autonomous System Perception","created":"2025-02-11","cited_by_count":6,"area":null},{"id":"2105.09930","title":"Mondegreen: A Post-Processing Solution to Speech Recognition Error Correction for Voice Search Queries","created":"2021-05-20","cited_by_count":4,"area":null},{"id":"2207.11951","title":"Deep Forest with Hashing Screening and Window Screening","created":"2022-07-25","cited_by_count":3,"area":null},{"id":"2303.07449","title":"Blind Acoustic Room Parameter Estimation Using Phase Features","created":"2023-03-13","cited_by_count":3,"area":null},{"id":"2109.12838","title":"MUTEN: Boosting Gradient-Based Adversarial Attacks via Mutant-Based Ensembles","created":"2021-09-27","cited_by_count":2,"area":null},{"id":"2304.01346","title":"Towards an Hybrid Hodgkin-Huxley Action Potential Generation Model","created":"2023-03-15","cited_by_count":2,"area":null},{"id":"2305.03963","title":"Beyond the Model: Data Pre-processing Attack to Deep Learning Models in Android Apps","created":"2023-05-06","cited_by_count":2,"area":null},{"id":"2312.06082","title":"XAI meets Biology: A Comprehensive Review of Explainable AI in Bioinformatics Applications","created":"2023-12-11","cited_by_count":2,"area":null},{"id":"2403.10663","title":"Not Just Change the Labels, Learn the Features: Watermarking Deep Neural Networks with Multi-View Data","created":"2024-03-15","cited_by_count":2,"area":null},{"id":"2108.01245","title":"The Performance Evaluation of Attention-Based Neural ASR under Mixed Speech Input","created":"2021-08-03","cited_by_count":1,"area":null},{"id":"2205.01751","title":"On monoaural speech enhancement for automatic recognition of real noisy speech using mixture invariant training","created":"2022-05-03","cited_by_count":1,"area":null},{"id":"2209.15278","title":"Rethinking skip connection model as a learnable Markov chain","created":"2022-09-30","cited_by_count":1,"area":null},{"id":"2407.12094","title":"Identifying Speakers in Dialogue Transcripts: A Text-based Approach Using Pretrained Language Models","created":"2024-07-16","cited_by_count":1,"area":null},{"id":"2601.13148","title":"ICo3D: An Interactive Conversational 3D Virtual Human","created":"2026-01-19","cited_by_count":1,"area":null},{"id":"2105.04729","title":"Unsupervised domain adaptation via double classifiers based on high confidence pseudo label","created":"2021-05-11","cited_by_count":0,"area":null},{"id":"2408.05917","title":"Inverse design of Non-parameterized Ventilated Acoustic Resonator via Variational Autoencoder with Acoustic Response-encoded Latent Space","created":"2024-08-12","cited_by_count":0,"area":null},{"id":"2410.08300","title":"A Framework to Enable Algorithmic Design Choice Exploration in DNNs","created":"2024-10-10","cited_by_count":0,"area":null},{"id":"2512.06304","title":"Degrading Voice: A Comprehensive Overview of Robust Voice Conversion Through Input Manipulation","created":"2025-12-06","cited_by_count":0,"area":null},{"id":"2604.14200","title":"Retina gap junctions support the robust perception by warping neural representational geometries along the visual hierarchy","created":"2026-04-03","cited_by_count":0,"area":null},{"id":"2609.31787","title":"Optimal transport meets speech: a tutorial review","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}