{"list":"other","total":55,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"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":"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":"2110.13900","title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","created":"2021-10-26","cited_by_count":1657},{"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":"2010.05646","title":"HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis","created":"2020-10-12","cited_by_count":1154},{"id":"2001.08210","title":"Multilingual Denoising Pre-training for Neural Machine Translation","created":"2020-01-22","cited_by_count":1035},{"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":"2111.09296","title":"XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale","created":"2021-11-17","cited_by_count":601},{"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":"2108.06209","title":"W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training","created":"2021-08-07","cited_by_count":347},{"id":"1910.05453","title":"vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations","created":"2019-10-12","cited_by_count":340},{"id":"2102.01192","title":"Generative Spoken Language Modeling from Raw Audio","created":"2021-02-01","cited_by_count":340},{"id":"2008.00401","title":"Multilingual Translation with Extensible Multilingual Pretraining and Finetuning","created":"2020-08-02","cited_by_count":287},{"id":"2110.07205","title":"SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing","created":"2021-10-14","cited_by_count":180},{"id":"1911.04944","title":"CCMatrix: Mining Billions of High-Quality Parallel Sentences on the WEB","created":"2019-11-10","cited_by_count":177},{"id":"2010.05171","title":"fairseq S2T: Fast Speech-to-Text Modeling with fairseq","created":"2020-10-11","cited_by_count":176},{"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":"2004.10234","title":"ESPnet-ST: All-in-One Speech Translation Toolkit","created":"2020-04-21","cited_by_count":82},{"id":"1906.06442","title":"Tagged Back-Translation","created":"2019-06-15","cited_by_count":77},{"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":"1904.08075","title":"End-to-End Speech Translation with Knowledge Distillation","created":"2019-04-17","cited_by_count":58},{"id":"2203.10426","title":"STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translation","created":"2022-03-20","cited_by_count":57},{"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":"1906.03785","title":"Generalized Data Augmentation for Low-Resource Translation","created":"2019-06-10","cited_by_count":53},{"id":"2105.03095","title":"Learning Shared Semantic Space for Speech-to-Text Translation","created":"2021-05-07","cited_by_count":49},{"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":"2301.00591","title":"Analysing Discrete Self Supervised Speech Representation for Spoken Language Modeling","created":"2023-01-02","cited_by_count":47},{"id":"1707.04879","title":"Listening while Speaking: Speech Chain by Deep Learning","created":"2017-07-16","cited_by_count":46},{"id":"1712.04313","title":"The Zero Resource Speech Challenge 2017","created":"2017-12-12","cited_by_count":45},{"id":"2006.07926","title":"UWSpeech: Speech to Speech Translation for Unwritten Languages","created":"2020-06-14","cited_by_count":43},{"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":"1904.11469","title":"The Zero Resource Speech Challenge 2019: TTS without T","created":"2019-04-25","cited_by_count":38},{"id":"2006.02490","title":"Self-Training for End-to-End Speech Translation","created":"2020-06-03","cited_by_count":36},{"id":"1807.10893","title":"Back-Translation-Style Data Augmentation for End-to-End ASR","created":"2018-07-28","cited_by_count":28},{"id":"2009.09737","title":"Consecutive Decoding for Speech-to-text Translation","created":"2020-09-21","cited_by_count":28},{"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":"2206.04571","title":"Revisiting End-to-End Speech-to-Text Translation From Scratch","created":"2022-06-09","cited_by_count":26},{"id":"2012.10018","title":"NeurST: Neural Speech Translation Toolkit","created":"2020-12-18","cited_by_count":23},{"id":"2212.03657","title":"M3ST: Mix at Three Levels for Speech Translation","created":"2022-12-07","cited_by_count":21},{"id":"2011.08298","title":"Facebook AI's WMT20 News Translation Task Submission","created":"2020-11-16","cited_by_count":17},{"id":"2112.10991","title":"Regularizing End-to-End Speech Translation with Triangular Decomposition Agreement","created":"2021-12-21","cited_by_count":16},{"id":"2109.04574","title":"Speechformer: Reducing Information Loss in Direct Speech Translation","created":"2021-09-09","cited_by_count":15},{"id":"2210.14514","title":"Improving Speech-to-Speech Translation Through Unlabeled Text","created":"2022-10-26","cited_by_count":8},{"id":"2210.04062","title":"CoBERT: Self-Supervised Speech Representation Learning Through Code Representation Learning","created":"2022-10-08","cited_by_count":7}],"next_cursor":null}