{"list":"other","total":56,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"2005.08100","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","created":"2020-05-16","cited_by_count":1863},{"id":"1804.08771","title":"A Call for Clarity in Reporting BLEU Scores","created":"2018-04-23","cited_by_count":1799},{"id":"1607.04606","title":"Enriching Word Vectors with Subword Information","created":"2016-07-15","cited_by_count":1583},{"id":"1904.01038","title":"fairseq: A Fast, Extensible Toolkit for Sequence Modeling","created":"2019-04-01","cited_by_count":1488},{"id":"1912.06670","title":"Common Voice: A Massively-Multilingual Speech Corpus","created":"2019-12-13","cited_by_count":1384},{"id":"1904.08779","title":"SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition","created":"2019-04-18","cited_by_count":1380},{"id":"1606.07947","title":"Sequence-Level Knowledge Distillation","created":"2016-06-25","cited_by_count":801},{"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":"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":"1805.04699","title":"TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptation","created":"2018-05-12","cited_by_count":226},{"id":"2010.05171","title":"fairseq S2T: Fast Speech-to-Text Modeling with fairseq","created":"2020-10-11","cited_by_count":176},{"id":"2004.08728","title":"SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddings","created":"2020-04-18","cited_by_count":156},{"id":"1805.06297","title":"A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings","created":"2018-05-16","cited_by_count":146},{"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":"2004.06358","title":"Speech Translation and the End-to-End Promise: Taking Stock of Where We Are","created":"2020-04-14","cited_by_count":77},{"id":"2007.09127","title":"CTC-Segmentation of Large Corpora for German End-to-end Speech Recognition","created":"2020-07-17","cited_by_count":76},{"id":"2007.10310","title":"CoVoST 2 and Massively Multilingual Speech-to-Text Translation","created":"2020-07-20","cited_by_count":74},{"id":"1802.04200","title":"End-to-End Automatic Speech Translation of Audiobooks","created":"2018-02-12","cited_by_count":65},{"id":"2010.14920","title":"Bridging the Modality Gap for Speech-to-Text Translation","created":"2020-10-28","cited_by_count":55},{"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":"2206.00888","title":"Squeezeformer: An Efficient Transformer for Automatic Speech Recognition","created":"2022-06-02","cited_by_count":51},{"id":"2102.01578","title":"CTC-based Compression for Direct Speech Translation","created":"2021-02-02","cited_by_count":45},{"id":"2109.01163","title":"Efficient conformer: Progressive downsampling and grouped attention for automatic speech recognition","created":"2021-08-31","cited_by_count":42},{"id":"1911.08870","title":"A Comparative Study on End-to-end Speech to Text Translation","created":"2019-11-20","cited_by_count":40},{"id":"1910.00254","title":"Multilingual End-to-End Speech Translation","created":"2019-10-01","cited_by_count":37},{"id":"1910.10408","title":"Controlling the Output Length of Neural Machine Translation","created":"2019-10-23","cited_by_count":36},{"id":"2202.04774","title":"SHAS: Approaching optimal Segmentation for End-to-End Speech Translation","created":"2022-02-09","cited_by_count":26},{"id":"2006.01080","title":"Is 42 the Answer to Everything in Subtitling-oriented Speech Translation?","created":"2020-06-01","cited_by_count":21},{"id":"2110.03847","title":"Machine Translation Verbosity Control for Automatic Dubbing","created":"2021-10-08","cited_by_count":18},{"id":"2112.08682","title":"Isometric MT: Neural Machine Translation for Automatic Dubbing","created":"2021-12-16","cited_by_count":18},{"id":"2002.10829","title":"MuST-Cinema: a Speech-to-Subtitles corpus","created":"2020-02-25","cited_by_count":17},{"id":"2010.13047","title":"Orthros: Non-autoregressive End-to-end Speech Translation with Dual-decoder","created":"2020-10-25","cited_by_count":17},{"id":"2104.11710","title":"Beyond Voice Activity Detection: Hybrid Audio Segmentation for Direct Speech Translation","created":"2021-04-23","cited_by_count":17},{"id":"2109.04574","title":"Speechformer: Reducing Information Loss in Direct Speech Translation","created":"2021-09-09","cited_by_count":15},{"id":"2112.08548","title":"Isochrony-Aware Neural Machine Translation for Automatic Dubbing","created":"2021-12-16","cited_by_count":14},{"id":"2205.02629","title":"Efficient yet Competitive Speech Translation: FBK@IWSLT2022","created":"2022-05-05","cited_by_count":14},{"id":"1908.07226","title":"Prosodic Phrase Alignment for Machine Dubbing","created":"2019-08-20","cited_by_count":13},{"id":"2109.07439","title":"Is \"moby dick\" a Whale or a Bird? Named Entities and Terminology in Speech Translation","created":"2021-09-15","cited_by_count":11},{"id":"2005.12143","title":"Adapting End-to-End Speech Recognition for Readable Subtitles","created":"2020-05-25","cited_by_count":10},{"id":"2101.09149","title":"Streaming Models for Joint Speech Recognition and Translation","created":"2021-01-22","cited_by_count":10},{"id":"2109.04411","title":"Non-autoregressive End-to-end Speech Translation with Parallel Autoregressive Rescoring","created":"2021-09-09","cited_by_count":9},{"id":"2205.05805","title":"SubER: A Metric for Automatic Evaluation of Subtitle Quality","created":"2022-05-11","cited_by_count":9},{"id":"2107.06246","title":"Between Flexibility and Consistency: Joint Generation of Captions and Subtitles","created":"2021-07-13","cited_by_count":7},{"id":"2205.06522","title":"Joint Generation of Captions and Subtitles with Dual Decoding","created":"2022-05-13","cited_by_count":5},{"id":"2208.07657","title":"Uconv-Conformer: High Reduction of Input Sequence Length for End-to-End Speech Recognition","created":"2022-08-16","cited_by_count":5},{"id":"2209.10608","title":"Dodging the Data Bottleneck: Automatic Subtitling with Automatically Segmented ST Corpora","created":"2022-09-21","cited_by_count":5},{"id":"2205.09360","title":"Evaluating Subtitle Segmentation for End-to-end Generation Systems","created":"2022-05-19","cited_by_count":4},{"id":"2107.09433","title":"Seed Words Based Data Selection for Language Model Adaptation","created":"2021-07-20","cited_by_count":1}],"next_cursor":null}