{"list":"other","total":60,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2106.07447","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","created":"2021-06-14","cited_by_count":2342},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"2005.08100","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","created":"2020-05-16","cited_by_count":1863},{"id":"1904.08779","title":"SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition","created":"2019-04-18","cited_by_count":1380},{"id":"2001.08210","title":"Multilingual Denoising Pre-training for Neural Machine Translation","created":"2020-01-22","cited_by_count":1035},{"id":"2202.03555","title":"data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language","created":"2022-02-07","cited_by_count":727},{"id":"2006.13979","title":"Unsupervised Cross-lingual Representation Learning for Speech Recognition","created":"2020-06-24","cited_by_count":501},{"id":"2110.07205","title":"SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing","created":"2021-10-14","cited_by_count":180},{"id":"1703.08581","title":"Sequence-to-Sequence Models Can Directly Translate Foreign Speech","created":"2017-03-24","cited_by_count":121},{"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":"2202.01374","title":"mSLAM: Massively multilingual joint pre-training for speech and text","created":"2022-02-03","cited_by_count":108},{"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":"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":"2006.05754","title":"Gender in Danger? Evaluating Speech Translation Technology on the MuST-SHE Corpus","created":"2020-06-10","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":"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":"2102.05766","title":"Fused Acoustic and Text Encoding for Multimodal Bilingual Pretraining and Speech Translation","created":"2021-02-10","cited_by_count":47},{"id":"2104.10380","title":"End-to-end Speech Translation via Cross-modal Progressive Training","created":"2021-04-21","cited_by_count":47},{"id":"1910.00254","title":"Multilingual End-to-End Speech Translation","created":"2019-10-01","cited_by_count":37},{"id":"2006.02490","title":"Self-Training for End-to-End Speech Translation","created":"2020-06-03","cited_by_count":36},{"id":"2104.06678","title":"Large-Scale Self- and Semi-Supervised Learning for Speech Translation","created":"2021-04-14","cited_by_count":36},{"id":"2006.02965","title":"End-to-End Speech-Translation with Knowledge Distillation: FBK@IWSLT2020","created":"2020-06-04","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":"2104.06457","title":"Source and Target Bidirectional Knowledge Distillation for End-to-end Speech Translation","created":"2021-04-13","cited_by_count":28},{"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":"2202.04774","title":"SHAS: Approaching optimal Segmentation for End-to-End Speech Translation","created":"2022-02-09","cited_by_count":26},{"id":"2204.05076","title":"End-to-End Speech Translation for Code Switched Speech","created":"2022-04-11","cited_by_count":26},{"id":"2205.01086","title":"Wav2Seq: Pre-training Speech-to-Text Encoder-Decoder Models Using Pseudo Languages","created":"2022-05-02","cited_by_count":26},{"id":"2105.04840","title":"Investigating the Reordering Capability in CTC-based Non-Autoregressive End-to-End Speech Translation","created":"2021-05-11","cited_by_count":23},{"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},{"id":"1912.07240","title":"Synchronous Speech Recognition and Speech-to-Text Translation with Interactive Decoding","created":"2019-12-16","cited_by_count":21},{"id":"2006.12124","title":"Self-Supervised Representations Improve End-to-End Speech Translation","created":"2020-06-22","cited_by_count":21},{"id":"1911.08876","title":"On Using SpecAugment for End-to-End Speech Translation","created":"2019-11-20","cited_by_count":19},{"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":"2204.09595","title":"Exploring Continuous Integrate-and-Fire for Adaptive Simultaneous Speech Translation","created":"2022-03-22","cited_by_count":14},{"id":"2002.12231","title":"SkinAugment: Auto-Encoding Speaker Conversions for Automatic Speech Translation","created":"2020-02-27","cited_by_count":13},{"id":"2010.11445","title":"MAM: Masked Acoustic Modeling for End-to-End Speech-to-Text Translation","created":"2020-10-22","cited_by_count":13},{"id":"2210.01512","title":"Code-Switching without Switching: Language Agnostic End-to-End Speech Translation","created":"2022-10-04","cited_by_count":13},{"id":"2105.13782","title":"How to Split: the Effect of Word Segmentation on Gender Bias in Speech Translation","created":"2021-05-28","cited_by_count":11},{"id":"2109.12804","title":"Fast-MD: Fast Multi-Decoder End-to-End Speech Translation with Non-Autoregressive Hidden Intermediates","created":"2021-09-27","cited_by_count":9},{"id":"2205.06755","title":"Who Are We Talking About? Handling Person Names in Speech Translation","created":"2022-05-13","cited_by_count":8},{"id":"2212.09553","title":"Mu$^{2}$SLAM: Multitask, Multilingual Speech and Language Models","created":"2022-12-19","cited_by_count":7},{"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":"2210.11987","title":"Joint Speech Translation and Named Entity Recognition","created":"2022-10-21","cited_by_count":5}],"next_cursor":null}