{"total":57,"rows":[{"id":"2101.08779","title":"AI Choreographer: Music Conditioned 3D Dance Generation with AIST++","created":"2021-01-21","cited_by_count":485,"area":null},{"id":"2306.12925","title":"AudioPaLM: A Large Language Model That Can Speak and Listen","created":"2023-06-22","cited_by_count":343,"area":null},{"id":"2107.05604","title":"Direct speech-to-speech translation with discrete units","created":"2021-07-12","cited_by_count":149,"area":null},{"id":"2107.08661","title":"Translatotron 2: High-quality direct speech-to-speech translation with voice preservation","created":"2021-07-19","cited_by_count":71,"area":null},{"id":"2201.03713","title":"CVSS Corpus and Massively Multilingual Speech-to-Speech Translation","created":"2022-01-11","cited_by_count":71,"area":null},{"id":"2204.05409","title":"Unified Speech-Text Pre-training for Speech Translation and Recognition","created":"2022-04-11","cited_by_count":64,"area":null},{"id":"2212.08055","title":"UnitY: Two-pass Direct Speech-to-speech Translation with Discrete Units","created":"2022-12-15","cited_by_count":60,"area":null},{"id":"2203.10426","title":"STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translation","created":"2022-03-20","cited_by_count":57,"area":null},{"id":"2106.01045","title":"Cascade versus Direct Speech Translation: Do the Differences Still Make a Difference?","created":"2021-06-02","cited_by_count":54,"area":null},{"id":"2105.03095","title":"Learning Shared Semantic Space for Speech-to-Text Translation","created":"2021-05-07","cited_by_count":49,"area":null},{"id":"2102.05766","title":"Fused Acoustic and Text Encoding for Multimodal Bilingual Pretraining and Speech Translation","created":"2021-02-10","cited_by_count":47,"area":null},{"id":"2204.02967","title":"Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentation","created":"2022-04-06","cited_by_count":44,"area":null},{"id":"2106.04833","title":"RealTranS: End-to-End Simultaneous Speech Translation with Convolutional Weighted-Shrinking Transformer","created":"2021-06-09","cited_by_count":40,"area":null},{"id":"2104.06678","title":"Large-Scale Self- and Semi-Supervised Learning for Speech Translation","created":"2021-04-14","cited_by_count":36,"area":null},{"id":"2204.05352","title":"Large-Scale Streaming End-to-End Speech Translation with Neural Transducers","created":"2022-04-11","cited_by_count":31,"area":null},{"id":"2109.07368","title":"Learning When to Translate for Streaming Speech","created":"2021-09-15","cited_by_count":30,"area":null},{"id":"2203.08757","title":"Sample, Translate, Recombine: Leveraging Audio Alignments for Data Augmentation in End-to-end Speech Translation","created":"2022-03-16","cited_by_count":27,"area":"distill"},{"id":"2203.09866","title":"Under the Morphosyntactic Lens: A Multifaceted Evaluation of Gender Bias in Speech Translation","created":"2022-03-18","cited_by_count":23,"area":null},{"id":"2212.09359","title":"WACO: Word-Aligned Contrastive Learning for Speech Translation","created":"2022-12-19","cited_by_count":21,"area":null},{"id":"2203.13339","title":"Leveraging unsupervised and weakly-supervised data to improve direct speech-to-speech translation","created":"2022-03-24","cited_by_count":20,"area":null},{"id":"2204.03939","title":"GigaST: A 10,000-hour Pseudo Speech Translation Corpus","created":"2022-04-08","cited_by_count":20,"area":null},{"id":"2104.11710","title":"Beyond Voice Activity Detection: Hybrid Audio Segmentation for Direct Speech Translation","created":"2021-04-23","cited_by_count":17,"area":null},{"id":"2305.08706","title":"Understanding and Bridging the Modality Gap for Speech Translation","created":"2023-05-15","cited_by_count":15,"area":null},{"id":"2306.11646","title":"Recent Advances in Direct Speech-to-text Translation","created":"2023-06-20","cited_by_count":15,"area":null},{"id":"2312.02512","title":"AV2AV: Direct Audio-Visual Speech to Audio-Visual Speech Translation with Unified Audio-Visual Speech Representation","created":"2023-12-05","cited_by_count":14,"area":null},{"id":"2402.10422","title":"Pushing the Limits of Zero-shot End-to-End Speech Translation","created":"2024-02-16","cited_by_count":14,"area":null},{"id":"2410.01036","title":"MOSEL: 950,000 Hours of Speech Data for Open-Source Speech Foundation Model Training on EU Languages","created":"2024-10-01","cited_by_count":14,"area":null},{"id":"2205.08993","title":"Leveraging Pseudo-labeled Data to Improve Direct Speech-to-Speech Translation","created":"2022-05-18","cited_by_count":12,"area":null},{"id":"2211.02499","title":"A Weakly-Supervised Streaming Multilingual Speech Model with Truly Zero-Shot Capability","created":"2022-11-04","cited_by_count":12,"area":null},{"id":"2305.17547","title":"Translatotron 3: Speech to Speech Translation with Monolingual Data","created":"2023-05-27","cited_by_count":12,"area":null},{"id":"2303.00978","title":"Leveraging Large Text Corpora for End-to-End Speech Summarization","created":"2023-03-02","cited_by_count":11,"area":null},{"id":"2109.04411","title":"Non-autoregressive End-to-end Speech Translation with Parallel Autoregressive Rescoring","created":"2021-09-09","cited_by_count":9,"area":null},{"id":"2212.01778","title":"Improving End-to-end Speech Translation by Leveraging Auxiliary Speech and Text Data","created":"2022-12-04","cited_by_count":9,"area":null},{"id":"2305.08709","title":"Back Translation for Speech-to-text Translation Without Transcripts","created":"2023-05-15","cited_by_count":9,"area":null},{"id":"2305.14838","title":"ComSL: A Composite Speech-Language Model for End-to-End Speech-to-Text Translation","created":"2023-05-24","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":"2210.14514","title":"Improving Speech-to-Speech Translation Through Unlabeled Text","created":"2022-10-26","cited_by_count":8,"area":null},{"id":"2304.10309","title":"Improving Speech Translation by Cross-Modal Multi-Grained Contrastive Learning","created":"2023-04-20","cited_by_count":7,"area":null},{"id":"2106.12607","title":"Dealing with training and test segmentation mismatch: FBK@IWSLT2021","created":"2021-06-23","cited_by_count":6,"area":"distill"},{"id":"2210.09556","title":"Discrete Cross-Modal Alignment Enables Zero-Shot Speech Translation","created":"2022-10-18","cited_by_count":6,"area":null},{"id":"2212.09699","title":"SegAugment: Maximizing the Utility of Speech Translation Data with Segmentation-based Augmentations","created":"2022-12-19","cited_by_count":6,"area":null},{"id":"2107.06010","title":"Zero-shot Speech Translation","created":"2021-07-13","cited_by_count":5,"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":"2201.11172","title":"Tackling data scarcity in speech translation using zero-shot multilingual machine translation techniques","created":"2022-01-26","cited_by_count":4,"area":null},{"id":"2502.00377","title":"When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation","created":"2025-02-01","cited_by_count":4,"area":null},{"id":"2105.07319","title":"The Volctrans Neural Speech Translation System for IWSLT 2021","created":"2021-05-16","cited_by_count":3,"area":null},{"id":"2206.05777","title":"The YiTrans End-to-End Speech Translation System for IWSLT 2022 Offline Shared Task","created":"2022-06-12","cited_by_count":3,"area":null},{"id":"2305.14042","title":"Improving speech translation by fusing speech and text","created":"2023-05-23","cited_by_count":3,"area":null},{"id":"2309.04557","title":"Regret-Optimal Federated Transfer Learning for Kernel Regression with Applications in American Option Pricing","created":"2023-09-08","cited_by_count":2,"area":null},{"id":"2211.04939","title":"Efficient Speech Translation with Pre-trained Models","created":"2022-11-09","cited_by_count":1,"area":null},{"id":"2307.08426","title":"Improving End-to-End Speech Translation by Imitation-Based Knowledge Distillation with Synthetic Transcripts","created":"2023-07-17","cited_by_count":1,"area":"distill"},{"id":"2406.02133","title":"SimulTron: On-Device Simultaneous Speech to Speech Translation","created":"2024-06-04","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":"2506.00740","title":"Length Aware Speech Translation for Video Dubbing","created":"2025-05-31","cited_by_count":1,"area":null},{"id":"2503.11080","title":"Joint Training And Decoding for Multilingual End-to-End Simultaneous Speech Translation","created":"2025-03-14","cited_by_count":0,"area":null},{"id":"2503.14185","title":"AdaST: Dynamically Adapting Encoder States in the Decoder for End-to-End Speech-to-Text Translation","created":"2025-03-18","cited_by_count":0,"area":null},{"id":"2506.02995","title":"It's Not a Walk in the Park! Challenges of Idiom Translation in Speech-to-text Systems","created":"2025-06-03","cited_by_count":0,"area":null}],"next_cursor":null}