{"list":"other","total":71,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2006.11477","title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","created":"2020-06-20","cited_by_count":3905},{"id":"1904.01038","title":"fairseq: A Fast, Extensible Toolkit for Sequence Modeling","created":"2019-04-01","cited_by_count":1488},{"id":"2001.08210","title":"Multilingual Denoising Pre-training for Neural Machine Translation","created":"2020-01-22","cited_by_count":1035},{"id":"1912.07875","title":"Libri-Light: A Benchmark for ASR with Limited or No Supervision","created":"2019-12-17","cited_by_count":467},{"id":"2101.00390","title":"VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation","created":"2021-01-02","cited_by_count":463},{"id":"2106.06909","title":"GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio","created":"2021-06-13","cited_by_count":399},{"id":"1609.06773","title":"Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learning","created":"2016-09-21","cited_by_count":257},{"id":"2103.15316","title":"Whitening Sentence Representations for Better Semantics and Faster Retrieval","created":"2021-03-29","cited_by_count":202},{"id":"2010.05171","title":"fairseq S2T: Fast Speech-to-Text Modeling with fairseq","created":"2020-10-11","cited_by_count":176},{"id":"1811.00347","title":"How2: A Large-scale Dataset for Multimodal Language Understanding","created":"2018-11-01","cited_by_count":138},{"id":"1703.08581","title":"Sequence-to-Sequence Models Can Directly Translate Foreign Speech","created":"2017-03-24","cited_by_count":121},{"id":"1911.03167","title":"Europarl-ST: A Multilingual Corpus For Speech Translation Of Parliamentary Debates","created":"2019-11-08","cited_by_count":114},{"id":"1612.01744","title":"Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation","created":"2016-12-06","cited_by_count":113},{"id":"2102.01757","title":"The Multilingual TEDx Corpus for Speech Recognition and Translation","created":"2021-02-02","cited_by_count":101},{"id":"2007.16193","title":"SimulEval: An Evaluation Toolkit for Simultaneous Translation","created":"2020-07-31","cited_by_count":94},{"id":"2004.10234","title":"ESPnet-ST: All-in-One Speech Translation Toolkit","created":"2020-04-21","cited_by_count":82},{"id":"1905.11235","title":"CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition","created":"2019-05-27","cited_by_count":77},{"id":"1809.01431","title":"Pre-training on high-resource speech recognition improves low-resource speech-to-text translation","created":"2018-09-05","cited_by_count":70},{"id":"1802.04200","title":"End-to-End Automatic Speech Translation of Audiobooks","created":"2018-02-12","cited_by_count":65},{"id":"2204.05409","title":"Unified Speech-Text Pre-training for Speech Translation and Recognition","created":"2022-04-11","cited_by_count":64},{"id":"2205.02444","title":"Cross-modal Contrastive Learning for Speech Translation","created":"2022-05-05","cited_by_count":61},{"id":"1904.08075","title":"End-to-End Speech Translation with Knowledge Distillation","created":"2019-04-17","cited_by_count":58},{"id":"1811.02050","title":"Leveraging Weakly Supervised Data to Improve End-to-End Speech-to-Text Translation","created":"2018-11-05","cited_by_count":57},{"id":"2002.01320","title":"CoVoST: A Diverse Multilingual Speech-To-Text Translation Corpus","created":"2020-02-04","cited_by_count":57},{"id":"2004.10093","title":"Curriculum Pre-training for End-to-End Speech Translation","created":"2020-04-21","cited_by_count":57},{"id":"2203.10426","title":"STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translation","created":"2022-03-20","cited_by_count":57},{"id":"2010.14920","title":"Bridging the Modality Gap for Speech-to-Text Translation","created":"2020-10-28","cited_by_count":55},{"id":"1802.06655","title":"Tied Multitask Learning for Neural Speech Translation","created":"2018-02-19","cited_by_count":54},{"id":"2011.00747","title":"Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation","created":"2020-11-02","cited_by_count":54},{"id":"2106.01045","title":"Cascade versus Direct Speech Translation: Do the Differences Still Make a Difference?","created":"2021-06-02","cited_by_count":54},{"id":"2106.01463","title":"Lightweight Adapter Tuning for Multilingual Speech Translation","created":"2021-06-02","cited_by_count":54},{"id":"2105.03095","title":"Learning Shared Semantic Space for Speech-to-Text Translation","created":"2021-05-07","cited_by_count":49},{"id":"2104.10380","title":"End-to-end Speech Translation via Cross-modal Progressive Training","created":"2021-04-21","cited_by_count":47},{"id":"1911.08870","title":"A Comparative Study on End-to-end Speech to Text Translation","created":"2019-11-20","cited_by_count":40},{"id":"2106.04833","title":"RealTranS: End-to-End Simultaneous Speech Translation with Convolutional Weighted-Shrinking Transformer","created":"2021-06-09","cited_by_count":40},{"id":"1910.00254","title":"Multilingual End-to-End Speech Translation","created":"2019-10-01","cited_by_count":37},{"id":"2104.06678","title":"Large-Scale Self- and Semi-Supervised Learning for Speech Translation","created":"2021-04-14","cited_by_count":36},{"id":"1802.03142","title":"Augmenting Librispeech with French Translations: A Multimodal Corpus for Direct Speech Translation Evaluation","created":"2018-02-09","cited_by_count":34},{"id":"2212.07850","title":"Attention as a Guide for Simultaneous Speech Translation","created":"2022-12-15","cited_by_count":32},{"id":"2106.06636","title":"Direct Simultaneous Speech-to-Text Translation Assisted by Synchronized Streaming ASR","created":"2021-06-11","cited_by_count":31},{"id":"2204.05352","title":"Large-Scale Streaming End-to-End Speech Translation with Neural Transducers","created":"2022-04-11","cited_by_count":31},{"id":"1904.07209","title":"Attention-Passing Models for Robust and Data-Efficient End-to-End Speech Translation","created":"2019-04-15","cited_by_count":30},{"id":"2109.07368","title":"Learning When to Translate for Streaming Speech","created":"2021-09-15","cited_by_count":30},{"id":"1906.00048","title":"Thinking Slow about Latency Evaluation for Simultaneous Machine Translation","created":"2019-05-31","cited_by_count":28},{"id":"2204.05076","title":"End-to-End Speech Translation for Code Switched Speech","created":"2022-04-11","cited_by_count":26},{"id":"2206.04571","title":"Revisiting End-to-End Speech-to-Text Translation From Scratch","created":"2022-06-09","cited_by_count":26},{"id":"2301.11716","title":"Pre-training for Speech Translation: CTC Meets Optimal Transport","created":"2023-01-27","cited_by_count":25},{"id":"2012.10018","title":"NeurST: Neural Speech Translation Toolkit","created":"2020-12-18","cited_by_count":23},{"id":"2204.03939","title":"GigaST: A 10,000-hour Pseudo Speech Translation Corpus","created":"2022-04-08","cited_by_count":20},{"id":"1910.03320","title":"One-To-Many Multilingual End-to-end Speech Translation","created":"2019-10-08","cited_by_count":17},{"id":"2105.04512","title":"End-to-End Speech Translation with Pre-trained Models and Adapters: UPC at IWSLT 2021","created":"2021-05-10","cited_by_count":16},{"id":"2207.00952","title":"M-Adapter: Modality Adaptation for End-to-End Speech-to-Text Translation","created":"2022-07-03","cited_by_count":15},{"id":"2306.11646","title":"Recent Advances in Direct Speech-to-text Translation","created":"2023-06-20","cited_by_count":15},{"id":"2204.09595","title":"Exploring Continuous Integrate-and-Fire for Adaptive Simultaneous Speech Translation","created":"2022-03-22","cited_by_count":14},{"id":"2210.10191","title":"Simple and Effective Unsupervised Speech Translation","created":"2022-10-18","cited_by_count":12},{"id":"1702.03856","title":"Towards speech-to-text translation without speech recognition","created":"2017-02-13","cited_by_count":11},{"id":"2012.04964","title":"On Knowledge Distillation for Direct Speech Translation","created":"2020-12-09","cited_by_count":11},{"id":"1710.03501","title":"A Very Low Resource Language Speech Corpus for Computational Language Documentation Experiments","created":"2017-10-10","cited_by_count":9},{"id":"2107.02875","title":"Kosp2e: Korean Speech to English Translation Corpus","created":"2021-07-06","cited_by_count":7},{"id":"2304.10309","title":"Improving Speech Translation by Cross-Modal Multi-Grained Contrastive Learning","created":"2023-04-20","cited_by_count":7},{"id":"2006.02814","title":"CSTNet: Contrastive Speech Translation Network for Self-Supervised Speech Representation Learning","created":"2020-06-04","cited_by_count":6},{"id":"2103.13439","title":"StyleKQC: A Style-Variant Paraphrase Corpus for Korean Questions and Commands","created":"2021-03-24","cited_by_count":5},{"id":"2204.01235","title":"An Analysis of Semantically-Aligned Speech-Text Embeddings","created":"2022-04-04","cited_by_count":5},{"id":"2204.09028","title":"On the Locality of Attention in Direct Speech Translation","created":"2022-04-19","cited_by_count":5},{"id":"2010.12829","title":"Multilingual Speech Translation with Efficient Finetuning of Pretrained Models","created":"2020-10-24","cited_by_count":4},{"id":"1609.08139","title":"An Unsupervised Probability Model for Speech-to-Translation Alignment of Low-Resource Languages","created":"2016-09-26","cited_by_count":3},{"id":"2212.08911","title":"AdaTranS: Adapting with Boundary-based Shrinking for End-to-End Speech Translation","created":"2022-12-17","cited_by_count":3}],"next_cursor":null}