{"list":"other","total":57,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"1808.06226","title":"SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing","created":"2018-08-19","cited_by_count":1989},{"id":"1804.08771","title":"A Call for Clarity in Reporting BLEU Scores","created":"2018-04-23","cited_by_count":1799},{"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":"2207.04672","title":"No Language Left Behind: Scaling Human-Centered Machine Translation","created":"2022-07-11","cited_by_count":1312},{"id":"2002.04745","title":"On Layer Normalization in the Transformer Architecture","created":"2020-02-12","cited_by_count":922},{"id":"2111.09296","title":"XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale","created":"2021-11-17","cited_by_count":601},{"id":"2205.12446","title":"FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech","created":"2022-05-25","cited_by_count":469},{"id":"1912.07875","title":"Libri-Light: A Benchmark for ASR with Limited or No Supervision","created":"2019-12-17","cited_by_count":467},{"id":"2008.00401","title":"Multilingual Translation with Extensible Multilingual Pretraining and Finetuning","created":"2020-08-02","cited_by_count":287},{"id":"1506.05439","title":"Learning with a Wasserstein Loss","created":"2015-06-17","cited_by_count":196},{"id":"2010.05171","title":"fairseq S2T: Fast Speech-to-Text Modeling with fairseq","created":"2020-10-11","cited_by_count":176},{"id":"2006.06264","title":"Tangled up in BLEU: Reevaluating the Evaluation of Automatic Machine Translation Evaluation Metrics","created":"2020-06-11","cited_by_count":158},{"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":"2010.11430","title":"Self-training and Pre-training are Complementary for Speech Recognition","created":"2020-10-22","cited_by_count":99},{"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":"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":"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":"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":"2106.01045","title":"Cascade versus Direct Speech Translation: Do the Differences Still Make a Difference?","created":"2021-06-02","cited_by_count":54},{"id":"2107.05782","title":"Improving Speech Translation by Understanding and Learning from the Auxiliary Text Translation Task","created":"2021-07-12","cited_by_count":54},{"id":"2010.11338","title":"A General Multi-Task Learning Framework to Leverage Text Data for Speech to Text Tasks","created":"2020-10-21","cited_by_count":51},{"id":"2105.03095","title":"Learning Shared Semantic Space for Speech-to-Text Translation","created":"2021-05-07","cited_by_count":49},{"id":"2105.05752","title":"Stacked Acoustic-and-Textual Encoding: Integrating the Pre-trained Models into Speech Translation Encoders","created":"2021-05-12","cited_by_count":48},{"id":"2104.10380","title":"End-to-end Speech Translation via Cross-modal Progressive Training","created":"2021-04-21","cited_by_count":47},{"id":"2102.01578","title":"CTC-based Compression for Direct Speech Translation","created":"2021-02-02","cited_by_count":45},{"id":"2210.03730","title":"SpeechUT: Bridging Speech and Text with Hidden-Unit for Encoder-Decoder Based Speech-Text Pre-training","created":"2022-10-07","cited_by_count":40},{"id":"1901.06283","title":"Improving Sequence-to-Sequence Learning via Optimal Transport","created":"2019-01-18","cited_by_count":33},{"id":"2006.02965","title":"End-to-End Speech-Translation with Knowledge Distillation: FBK@IWSLT2020","created":"2020-06-04","cited_by_count":31},{"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},{"id":"2301.11716","title":"Pre-training for Speech Translation: CTC Meets Optimal Transport","created":"2023-01-27","cited_by_count":25},{"id":"2004.06575","title":"Multilingual Machine Translation: Closing the Gap between Shared and Language-specific Encoder-Decoders","created":"2020-04-14","cited_by_count":23},{"id":"2212.09359","title":"WACO: Word-Aligned Contrastive Learning for Speech Translation","created":"2022-12-19","cited_by_count":21},{"id":"2110.02887","title":"Using Optimal Transport as Alignment Objective for fine-tuning Multilingual Contextualized Embeddings","created":"2021-10-06","cited_by_count":19},{"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":"2205.12216","title":"T-Modules: Translation Modules for Zero-Shot Cross-Modal Machine Translation","created":"2022-05-24","cited_by_count":16},{"id":"2305.08706","title":"Understanding and Bridging the Modality Gap for Speech Translation","created":"2023-05-15","cited_by_count":15},{"id":"2005.10678","title":"Worse WER, but Better BLEU? Leveraging Word Embedding as Intermediate in Multitask End-to-End Speech Translation","created":"2020-05-21","cited_by_count":12},{"id":"2011.01097","title":"Enabling Zero-shot Multilingual Spoken Language Translation with Language-Specific Encoders and Decoders","created":"2020-11-02","cited_by_count":10},{"id":"2305.07310","title":"Improving Zero-shot Multilingual Neural Machine Translation by Leveraging Cross-lingual Consistency Regularization","created":"2023-05-12","cited_by_count":10},{"id":"2306.07763","title":"NAVER LABS Europe's Multilingual Speech Translation Systems for the IWSLT 2023 Low-Resource Track","created":"2023-06-13","cited_by_count":9},{"id":"2310.02050","title":"Tuning Large language model for End-to-end Speech Translation","created":"2023-10-03","cited_by_count":9},{"id":"2210.09556","title":"Discrete Cross-Modal Alignment Enables Zero-Shot Speech Translation","created":"2022-10-18","cited_by_count":6},{"id":"2212.09699","title":"SegAugment: Maximizing the Utility of Speech Translation Data with Segmentation-based Augmentations","created":"2022-12-19","cited_by_count":6},{"id":"2308.14482","title":"An Empirical Study of Consistency Regularization for End-to-End Speech-to-Text Translation","created":"2023-08-28","cited_by_count":6},{"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},{"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},{"id":"2306.01327","title":"Speech Translation with Foundation Models and Optimal Transport: UPC at IWSLT23","created":"2023-06-02","cited_by_count":1}],"next_cursor":null}