{"total":21,"rows":[{"id":"2110.07603","title":"Sub-word Level Lip Reading With Visual Attention","created":"2021-10-14","cited_by_count":63,"area":null},{"id":"2111.10592","title":"Deep Spoken Keyword Spotting: An Overview","created":"2021-11-20","cited_by_count":43,"area":null},{"id":"2103.16481","title":"Read and Attend: Temporal Localisation in Sign Language Videos","created":"2021-03-30","cited_by_count":34,"area":null},{"id":"2111.03635","title":"BBC-Oxford British Sign Language Dataset","created":"2021-11-05","cited_by_count":28,"area":null},{"id":"2203.03598","title":"Audio-visual Generalised Zero-shot Learning with Cross-modal Attention and Language","created":"2022-03-07","cited_by_count":27,"area":null},{"id":"2201.02495","title":"Sign Language Video Retrieval with Free-Form Textual Queries","created":"2022-01-07","cited_by_count":23,"area":null},{"id":"2206.15400","title":"Learning Audio-Text Agreement for Open-vocabulary Keyword Spotting","created":"2022-06-30","cited_by_count":20,"area":null},{"id":"2208.02802","title":"Automatic dense annotation of large-vocabulary sign language videos","created":"2022-08-04","cited_by_count":20,"area":null},{"id":"2303.05309","title":"MixSpeech: Cross-Modality Self-Learning with Audio-Visual Stream Mixup for Visual Speech Translation and Recognition","created":"2023-03-09","cited_by_count":14,"area":null},{"id":"2205.04152","title":"Scaling up sign spotting through sign language dictionaries","created":"2022-05-09","cited_by_count":12,"area":null},{"id":"2110.15957","title":"Visual Keyword Spotting with Attention","created":"2021-10-29","cited_by_count":11,"area":null},{"id":"2306.07744","title":"Contrastive Learning-Based Audio to Lyrics Alignment for Multiple Languages","created":"2023-06-13","cited_by_count":11,"area":null},{"id":"2211.08954","title":"Weakly-supervised Fingerspelling Recognition in British Sign Language Videos","created":"2022-11-16","cited_by_count":10,"area":null},{"id":"2508.08237","title":"VGGSounder: Audio-Visual Evaluations for Foundation Models","created":"2025-08-11","cited_by_count":8,"area":null},{"id":"2203.13291","title":"Searching for fingerspelled content in American Sign Language","created":"2022-03-24","cited_by_count":5,"area":null},{"id":"2309.09552","title":"A Multitask Training Approach to Enhance Whisper with Contextual Biasing and Open-Vocabulary Keyword Spotting","created":"2023-09-18","cited_by_count":5,"area":null},{"id":"2303.08670","title":"Deep Visual Forced Alignment: Learning to Align Transcription with Talking Face Video","created":"2023-02-27","cited_by_count":4,"area":null},{"id":"2308.12419","title":"Toward American Sign Language Processing in the Real World: Data, Tasks, and Methods","created":"2023-08-23","cited_by_count":1,"area":null},{"id":"2202.08509","title":"A Study of Designing Compact Audio-Visual Wake Word Spotting System Based on Iterative Fine-Tuning in Neural Network Pruning","created":"2022-02-17","cited_by_count":0,"area":null},{"id":"2503.03286","title":"Enhancing Visual Forced Alignment with Local Context-Aware Feature Extraction and Multi-Task Learning","created":"2025-03-05","cited_by_count":0,"area":null},{"id":"2609.01886","title":"SignMatch: Matching Dictionary Signs to Continuous Sign Language Video","created":"2026-09-01","cited_by_count":0,"area":null}],"next_cursor":null}