{"total":21,"rows":[{"id":"2406.00899","title":"YODAS: Youtube-Oriented Dataset for Audio and Speech","created":"2024-06-02","cited_by_count":60,"area":null},{"id":"2406.09282","title":"On the Effects of Heterogeneous Data Sources on Speech-to-Text Foundation Models","created":"2024-06-13","cited_by_count":10,"area":null},{"id":"2406.18301","title":"MSR-86K: An Evolving, Multilingual Corpus with 86,300 Hours of Transcribed Audio for Speech Recognition Research","created":"2024-06-26","cited_by_count":9,"area":null},{"id":"2401.09759","title":"SlideAVSR: A Dataset of Paper Explanation Videos for Audio-Visual Speech Recognition","created":"2024-01-18","cited_by_count":7,"area":null},{"id":"2410.03240","title":"Beyond Film Subtitles: Is YouTube the Best Approximation of Spoken Vocabulary?","created":"2024-10-04","cited_by_count":5,"area":null},{"id":"2505.19800","title":"MOLE: Metadata Extraction and Validation in Scientific Papers Using LLMs","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2405.01293","title":"Low-resource speech recognition and dialect identification of Irish in a multi-task framework","created":"2024-05-02","cited_by_count":3,"area":null},{"id":"2506.01439","title":"Whale: Large-Scale multilingual ASR model with w2v-BERT and E-Branchformer with large speech data","created":"2025-06-02","cited_by_count":3,"area":null},{"id":"2312.07338","title":"Self-supervised Adaptive Pre-training of Multilingual Speech Models for Language and Dialect Identification","created":"2023-12-12","cited_by_count":2,"area":null},{"id":"2407.15828","title":"J-CHAT: Japanese Large-scale Spoken Dialogue Corpus for Spoken Dialogue Language Modeling","created":"2024-07-22","cited_by_count":2,"area":null},{"id":"2309.09443","title":"Enhancing Multilingual Speech Recognition through Language Prompt Tuning and Frame-Level Language Adapter","created":"2023-09-18","cited_by_count":0,"area":null},{"id":"2311.08141","title":"GMTR: Graph Matching Transformers","created":"2023-11-14","cited_by_count":0,"area":null},{"id":"2312.16805","title":"DarkShot: Lighting Dark Images with Low-Compute and High-Quality","created":"2023-12-28","cited_by_count":0,"area":null},{"id":"2401.05431","title":"TRLS: A Time Series Representation Learning Framework via Spectrogram for Medical Signal Processing","created":"2024-01-06","cited_by_count":0,"area":null},{"id":"2401.05432","title":"TEN-GUARD: Tensor Decomposition for Backdoor Attack Detection in Deep Neural Networks","created":"2024-01-06","cited_by_count":0,"area":null},{"id":"2403.13663","title":"T-Pixel2Mesh: Combining Global and Local Transformer for 3D Mesh Generation from a Single Image","created":"2024-03-20","cited_by_count":0,"area":null},{"id":"2408.17101","title":"Strategic Arms with Side Communication Prevail Over Low-Regret MAB Algorithms","created":"2024-08-30","cited_by_count":0,"area":null},{"id":"2410.11162","title":"Towards General Deepfake Detection with Dynamic Curriculum","created":"2024-10-15","cited_by_count":0,"area":null},{"id":"2410.13409","title":"Attr-Int: A Simple and Effective Entity Alignment Framework for Heterogeneous Knowledge Graphs","created":"2024-10-17","cited_by_count":0,"area":null},{"id":"2507.06486","title":"Mask6D: Masked Pose Priors For 6D Object Pose Estimation","created":"2025-07-09","cited_by_count":0,"area":null},{"id":"2609.11772","title":"Whisper-Based Speech Transcription from Videos Across Multiple Languages for Cross-Cultural Understanding","created":"2026-09-10","cited_by_count":0,"area":null}],"next_cursor":null}