{"total":16,"rows":[{"id":"2106.05933","title":"PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition","created":"2021-06-10","cited_by_count":53,"area":null},{"id":"2104.13225","title":"Visually grounded models of spoken language: A survey of datasets, architectures and evaluation techniques","created":"2021-04-27","cited_by_count":32,"area":null},{"id":"2306.02902","title":"N-Shot Benchmarking of Whisper on Diverse Arabic Speech Recognition","created":"2023-06-05","cited_by_count":20,"area":null},{"id":"2305.18957","title":"Wave to Syntax: Probing spoken language models for syntax","created":"2023-05-30","cited_by_count":18,"area":null},{"id":"2101.08454","title":"Arabic Speech Recognition by End-to-End, Modular Systems and Human","created":"2021-01-21","cited_by_count":12,"area":null},{"id":"2209.06275","title":"PANCETTA: Phoneme Aware Neural Completion to Elicit Tongue Twisters Automatically","created":"2022-09-13","cited_by_count":6,"area":null},{"id":"2509.15655","title":"Layer-wise Minimal Pair Probing Reveals Contextual Grammatical-Conceptual Hierarchy in Speech Representations","created":"2025-09-19","cited_by_count":5,"area":null},{"id":"2305.07034","title":"Quran Recitation Recognition using End-to-End Deep Learning","created":"2023-05-10","cited_by_count":3,"area":null},{"id":"2310.11069","title":"VoxArabica: A Robust Dialect-Aware Arabic Speech Recognition System","created":"2023-10-17","cited_by_count":3,"area":null},{"id":"2111.04194","title":"Retrieving Speaker Information from Personalized Acoustic Models for Speech Recognition","created":"2021-11-07","cited_by_count":2,"area":null},{"id":"2212.10826","title":"End-to-End Automatic Speech Recognition model for the Sudanese Dialect","created":"2022-12-21","cited_by_count":2,"area":null},{"id":"2506.02181","title":"Echoes of Phonetics: Unveiling Relevant Acoustic Cues for ASR via Feature Attribution","created":"2025-06-02","cited_by_count":2,"area":null},{"id":"2402.19443","title":"Probing the Information Encoded in Neural-based Acoustic Models of Automatic Speech Recognition Systems","created":"2024-02-29","cited_by_count":1,"area":null},{"id":"2507.13977","title":"Open Automatic Speech Recognition Models for Classical and Modern Standard Arabic","created":"2025-07-18","cited_by_count":1,"area":null},{"id":"2508.17914","title":"Evaluating the Representation of Vowels in Wav2Vec Feature Extractor: A Layer-Wise Analysis Using MFCCs","created":"2025-08-25","cited_by_count":0,"area":null},{"id":"2601.06972","title":"Categorize Early, Integrate Late: Divergent Processing Strategies in Automatic Speech Recognition","created":"2026-01-11","cited_by_count":0,"area":null}],"next_cursor":null}