{"list":"other","total":55,"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":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"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":"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":"2010.05646","title":"HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis","created":"2020-10-12","cited_by_count":1154},{"id":"1511.06709","title":"Improving Neural Machine Translation Models with Monolingual Data","created":"2015-11-20","cited_by_count":788},{"id":"2006.04558","title":"FastSpeech 2: Fast and High-Quality End-to-End Text to Speech","created":"2020-06-08","cited_by_count":717},{"id":"2209.03143","title":"AudioLM: a Language Modeling Approach to Audio Generation","created":"2022-09-07","cited_by_count":616},{"id":"2102.01192","title":"Generative Spoken Language Modeling from Raw Audio","created":"2021-02-01","cited_by_count":340},{"id":"1710.10467","title":"Generalized End-to-End Loss for Speaker Verification","created":"2017-10-28","cited_by_count":293},{"id":"2104.00355","title":"Speech Resynthesis from Discrete Disentangled Self-Supervised Representations","created":"2021-04-01","cited_by_count":243},{"id":"2110.07205","title":"SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing","created":"2021-10-14","cited_by_count":180},{"id":"2107.05604","title":"Direct speech-to-speech translation with discrete units","created":"2021-07-12","cited_by_count":149},{"id":"2203.16502","title":"Generative Spoken Dialogue Language Modeling","created":"2022-03-30","cited_by_count":126},{"id":"2112.08352","title":"Textless Speech-to-Speech Translation on Real Data","created":"2021-12-15","cited_by_count":121},{"id":"2109.03264","title":"Text-Free Prosody-Aware Generative Spoken Language Modeling","created":"2021-09-07","cited_by_count":119},{"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":"2103.00993","title":"AdaSpeech: Adaptive Text to Speech for Custom Voice","created":"2021-03-01","cited_by_count":98},{"id":"2204.03409","title":"MAESTRO: Matched Speech Text Representations through Modality Matching","created":"2022-04-07","cited_by_count":79},{"id":"1906.06442","title":"Tagged Back-Translation","created":"2019-06-15","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":"2110.10329","title":"SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training","created":"2021-10-20","cited_by_count":69},{"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":"2212.08055","title":"UnitY: Two-pass Direct Speech-to-speech Translation with Discrete Units","created":"2022-12-15","cited_by_count":60},{"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":"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":"2011.00747","title":"Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation","created":"2020-11-02","cited_by_count":54},{"id":"2106.01463","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":"2104.10380","title":"End-to-end Speech Translation via Cross-modal Progressive Training","created":"2021-04-21","cited_by_count":47},{"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},{"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":"1909.07575","title":"Bridging the Gap between Pre-Training and Fine-Tuning for End-to-End Speech Translation","created":"2019-09-17","cited_by_count":39},{"id":"2009.09737","title":"Consecutive Decoding for Speech-to-text Translation","created":"2020-09-21","cited_by_count":28},{"id":"1910.10762","title":"Analyzing ASR pretraining for low-resource speech-to-text translation","created":"2019-10-23","cited_by_count":27},{"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":"2206.04571","title":"Revisiting End-to-End Speech-to-Text Translation From Scratch","created":"2022-06-09","cited_by_count":26},{"id":"2004.03672","title":"Dynamic Data Selection and Weighting for Iterative Back-Translation","created":"2020-04-07","cited_by_count":25},{"id":"2211.00115","title":"Textless Direct Speech-to-Speech Translation with Discrete Speech Representation","created":"2022-10-31","cited_by_count":19},{"id":"2102.07847","title":"Meta Back-translation","created":"2021-02-15","cited_by_count":16},{"id":"2212.09730","title":"Speaking Style Conversion in the Waveform Domain Using Discrete Self-Supervised Units","created":"2022-12-19","cited_by_count":15},{"id":"2110.01811","title":"On the Complementarity between Pre-Training and Back-Translation for Neural Machine Translation","created":"2021-10-05","cited_by_count":14},{"id":"2210.14514","title":"Improving Speech-to-Speech Translation Through Unlabeled Text","created":"2022-10-26","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":"2109.04443","title":"HintedBT: Augmenting Back-Translation with Quality and Transliteration Hints","created":"2021-09-09","cited_by_count":3},{"id":"1912.10514","title":"Tag-less Back-Translation","created":"2019-12-22","cited_by_count":2}],"next_cursor":null}