{"list":"other","total":61,"rows":[{"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":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"1306.0895","title":"Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances","created":"2013-06-04","cited_by_count":2316},{"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":"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":"1410.5401","title":"Neural Turing Machines","created":"2014-10-20","cited_by_count":644},{"id":"1711.00043","title":"Unsupervised Machine Translation Using Monolingual Corpora Only","created":"2017-10-31","cited_by_count":273},{"id":"1703.01541","title":"Soft-DTW: a Differentiable Loss Function for Time-Series","created":"2017-03-05","cited_by_count":271},{"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":"1909.06317","title":"A Comparative Study on Transformer vs RNN in Speech Applications","created":"2019-09-13","cited_by_count":211},{"id":"1506.05439","title":"Learning with a Wasserstein Loss","created":"2015-06-17","cited_by_count":196},{"id":"2110.07205","title":"SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing","created":"2021-10-14","cited_by_count":180},{"id":"2010.05171","title":"fairseq S2T: Fast Speech-to-Text Modeling with fairseq","created":"2020-10-11","cited_by_count":176},{"id":"1508.04395","title":"End-to-End Attention-based Large Vocabulary Speech Recognition","created":"2015-08-18","cited_by_count":151},{"id":"1809.00013","title":"Gromov-Wasserstein Alignment of Word Embedding Spaces","created":"2018-08-31","cited_by_count":122},{"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":"1805.11222","title":"Unsupervised Alignment of Embeddings with Wasserstein Procrustes","created":"2018-05-29","cited_by_count":97},{"id":"2004.10234","title":"ESPnet-ST: All-in-One Speech Translation Toolkit","created":"2020-04-21","cited_by_count":82},{"id":"2204.03409","title":"MAESTRO: Matched Speech Text Representations through Modality Matching","created":"2022-04-07","cited_by_count":79},{"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":"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":"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":"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":"1911.08870","title":"A Comparative Study on End-to-end Speech to Text Translation","created":"2019-11-20","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":"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":"1806.09277","title":"Towards Optimal Transport with Global Invariances","created":"2018-06-25","cited_by_count":33},{"id":"1901.06283","title":"Improving Sequence-to-Sequence Learning via Optimal Transport","created":"2019-01-18","cited_by_count":33},{"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":"2010.08518","title":"Adaptive Feature Selection for End-to-End Speech Translation","created":"2020-10-16","cited_by_count":25},{"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":"2111.06316","title":"Unsupervised Noise Adaptive Speech Enhancement by Discriminator-Constrained Optimal Transport","created":"2021-11-11","cited_by_count":16},{"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":"1811.09364","title":"Learning pronunciation from a foreign language in speech synthesis networks","created":"2018-11-23","cited_by_count":12},{"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":"2203.17113","title":"Pre-Training Transformer Decoder for End-to-End ASR Model with Unpaired Speech Data","created":"2022-03-31","cited_by_count":12}],"next_cursor":null}