{"total":20,"rows":[{"id":"2401.01572","title":"Hallucinations in Neural Automatic Speech Recognition: Identifying Errors and Hallucinatory Models","created":"2024-01-03","cited_by_count":27,"area":null},{"id":"2204.00540","title":"End-to-End Integration of Speech Recognition, Speech Enhancement, and Self-Supervised Learning Representation","created":"2022-04-01","cited_by_count":17,"area":null},{"id":"2304.04974","title":"Wav2code: Restore Clean Speech Representations via Codebook Lookup for Noise-Robust ASR","created":"2023-04-11","cited_by_count":10,"area":null},{"id":"2308.10415","title":"TokenSplit: Using Discrete Speech Representations for Direct, Refined, and Transcript-Conditioned Speech Separation and Recognition","created":"2023-08-21","cited_by_count":8,"area":null},{"id":"2502.13645","title":"Measuring the Effect of Transcription Noise on Downstream Language Understanding Tasks","created":"2025-02-19","cited_by_count":7,"area":null},{"id":"2407.11828","title":"Vibravox: A Dataset of French Speech Captured with Body-conduction Audio Sensors","created":"2024-07-16","cited_by_count":5,"area":null},{"id":"2406.05699","title":"An Investigation of Noise Robustness for Flow-Matching-Based Zero-Shot TTS","created":"2024-06-09","cited_by_count":4,"area":null},{"id":"2502.20311","title":"Adapting Automatic Speech Recognition for Accented Air Traffic Control Communications","created":"2025-02-27","cited_by_count":3,"area":null},{"id":"2408.06264","title":"Audio Enhancement for Computer Audition -- An Iterative Training Paradigm Using Sample Importance","created":"2024-08-12","cited_by_count":2,"area":null},{"id":"2502.20040","title":"CleanMel: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASR","created":"2025-02-27","cited_by_count":2,"area":null},{"id":"2309.08454","title":"Combining TF-GridNet and Mixture Encoder for Continuous Speech Separation for Meeting Transcription","created":"2023-09-15","cited_by_count":1,"area":null},{"id":"2506.18714","title":"Frequency-Weighted Training Losses for Phoneme-Level DNN-based Speech Enhancement","created":"2025-06-23","cited_by_count":1,"area":null},{"id":"2509.10143","title":"Error Analysis in a Modular Meeting Transcription System","created":"2025-09-12","cited_by_count":1,"area":null},{"id":"2309.09270","title":"Continuous Modeling of the Denoising Process for Speech Enhancement Based on Deep Learning","created":"2023-09-17","cited_by_count":0,"area":null},{"id":"2502.07205","title":"VINP: Variational Bayesian Inference with Neural Speech Prior for Joint ASR-Effective Speech Dereverberation and Blind RIR Identification","created":"2025-02-11","cited_by_count":0,"area":null},{"id":"2508.08967","title":"Revealing the Role of Audio Channels in ASR Performance Degradation","created":"2025-08-12","cited_by_count":0,"area":null},{"id":"2508.10436","title":"Alternating Approach-Putt Models for Multi-Stage Speech Enhancement","created":"2025-08-14","cited_by_count":0,"area":null},{"id":"2602.20967","title":"Training-Free Intelligibility-Guided Observation Addition for Noisy ASR","created":"2026-02-24","cited_by_count":0,"area":null},{"id":"2608.30326","title":"Parallel Time-Band Mixing with Learned Observation-Adding for Robust ASR Front-Ends","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.00276","title":"Cleaner Speech, Weaker Generalization: Revisiting Pitt-Derived Benchmarks for Alzheimer's Disease Detection","created":"2026-08-31","cited_by_count":0,"area":null}],"next_cursor":null}