{"total":14,"rows":[{"id":"2305.17733","title":"Investigating Pre-trained Audio Encoders in the Low-Resource Condition","created":"2023-05-28","cited_by_count":11,"area":null},{"id":"2210.08759","title":"Towards Relation Extraction From Speech","created":"2022-10-17","cited_by_count":10,"area":null},{"id":"2309.07707","title":"CoLLD: Contrastive Layer-to-layer Distillation for Compressing Multilingual Pre-trained Speech Encoders","created":"2023-09-14","cited_by_count":9,"area":null},{"id":"2312.01053","title":"End-to-End Speech-to-Text Translation: A Survey","created":"2023-12-02","cited_by_count":9,"area":null},{"id":"2411.17666","title":"How do Multimodal Foundation Models Encode Text and Speech? An Analysis of Cross-Lingual and Cross-Modal Representations","created":"2024-11-26","cited_by_count":9,"area":null},{"id":"2210.08174","title":"Generating Synthetic Speech from SpokenVocab for Speech Translation","created":"2022-10-15","cited_by_count":5,"area":null},{"id":"2401.15385","title":"Towards Event Extraction from Speech with Contextual Clues","created":"2024-01-27","cited_by_count":3,"area":null},{"id":"2506.02172","title":"Different Speech Translation Models Encode and Translate Speaker Gender Differently","created":"2025-06-02","cited_by_count":3,"area":null},{"id":"2210.08475","title":"RedApt: An Adaptor for wav2vec 2 Encoding \\\\ Faster and Smaller Speech Translation without Quality Compromise","created":"2022-10-16","cited_by_count":2,"area":null},{"id":"2306.01327","title":"Speech Translation with Foundation Models and Optimal Transport: UPC at IWSLT23","created":"2023-06-02","cited_by_count":1,"area":null},{"id":"2406.14177","title":"SimulSeamless: FBK at IWSLT 2024 Simultaneous Speech Translation","created":"2024-06-20","cited_by_count":1,"area":null},{"id":"2406.17257","title":"Leveraging Parameter-Efficient Transfer Learning for Multi-Lingual Text-to-Speech Adaptation","created":"2024-06-25","cited_by_count":1,"area":null},{"id":"2410.05146","title":"CTC-GMM: CTC guided modality matching for fast and accurate streaming speech translation","created":"2024-10-07","cited_by_count":1,"area":null},{"id":"2410.13445","title":"Parameter-efficient Adaptation of Multilingual Multimodal Models for Low-resource ASR","created":"2024-10-17","cited_by_count":0,"area":null}],"next_cursor":null}