{"total":167,"rows":[{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057,"area":null},{"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,"area":null},{"id":"2110.07205","title":"SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing","created":"2021-10-14","cited_by_count":180,"area":null},{"id":"2107.05604","title":"Direct speech-to-speech translation with discrete units","created":"2021-07-12","cited_by_count":149,"area":null},{"id":"2108.08827","title":"ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis","created":"2021-08-19","cited_by_count":122,"area":null},{"id":"2112.08352","title":"Textless Speech-to-Speech Translation on Real Data","created":"2021-12-15","cited_by_count":121,"area":null},{"id":"2102.01757","title":"The Multilingual TEDx Corpus for Speech Recognition and Translation","created":"2021-02-02","cited_by_count":101,"area":null},{"id":"2104.06022","title":"Lessons on Parameter Sharing across Layers in Transformers","created":"2021-04-13","cited_by_count":85,"area":null},{"id":"2304.14407","title":"ChatVideo: A Tracklet-centric Multimodal and Versatile Video Understanding System","created":"2023-04-27","cited_by_count":65,"area":null},{"id":"2205.02444","title":"Cross-modal Contrastive Learning for Speech Translation","created":"2022-05-05","cited_by_count":61,"area":null},{"id":"2212.08055","title":"UnitY: Two-pass Direct Speech-to-speech Translation with Discrete Units","created":"2022-12-15","cited_by_count":60,"area":null},{"id":"2203.10426","title":"STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translation","created":"2022-03-20","cited_by_count":57,"area":null},{"id":"2106.01463","title":"Lightweight Adapter Tuning for Multilingual Speech Translation","created":"2021-06-02","cited_by_count":54,"area":null},{"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,"area":null},{"id":"2407.00837","title":"Towards Robust Speech Representation Learning for Thousands of Languages","created":"2024-06-30","cited_by_count":50,"area":null},{"id":"2104.11462","title":"LeBenchmark: A Reproducible Framework for Assessing Self-Supervised Representation Learning from Speech","created":"2021-04-23","cited_by_count":47,"area":null},{"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,"area":null},{"id":"2305.11095","title":"Prompting the Hidden Talent of Web-Scale Speech Models for Zero-Shot Task Generalization","created":"2023-05-18","cited_by_count":43,"area":null},{"id":"2106.04833","title":"RealTranS: End-to-End Simultaneous Speech Translation with Convolutional Weighted-Shrinking Transformer","created":"2021-06-09","cited_by_count":40,"area":null},{"id":"2210.12357","title":"Information-Transport-based Policy for Simultaneous Translation","created":"2022-10-22","cited_by_count":40,"area":null},{"id":"2303.00628","title":"MuAViC: A Multilingual Audio-Visual Corpus for Robust Speech Recognition and Robust Speech-to-Text Translation","created":"2023-03-01","cited_by_count":39,"area":null},{"id":"2303.11607","title":"Transformers in Speech Processing: A Survey","created":"2023-03-21","cited_by_count":39,"area":null},{"id":"2305.11408","title":"AlignAtt: Using Attention-based Audio-Translation Alignments as a Guide for Simultaneous Speech Translation","created":"2023-05-19","cited_by_count":35,"area":null},{"id":"2205.12523","title":"TranSpeech: Speech-to-Speech Translation With Bilateral Perturbation","created":"2022-05-25","cited_by_count":34,"area":null},{"id":"2212.07850","title":"Attention as a Guide for Simultaneous Speech Translation","created":"2022-12-15","cited_by_count":32,"area":null},{"id":"2210.11723","title":"Evidence of Vocal Tract Articulation in Self-Supervised Learning of Speech","created":"2022-10-21","cited_by_count":31,"area":null},{"id":"2109.07368","title":"Learning When to Translate for Streaming Speech","created":"2021-09-15","cited_by_count":30,"area":null},{"id":"2202.04774","title":"SHAS: Approaching optimal Segmentation for End-to-End Speech Translation","created":"2022-02-09","cited_by_count":26,"area":null},{"id":"2205.01086","title":"Wav2Seq: Pre-training Speech-to-Text Encoder-Decoder Models Using Pseudo Languages","created":"2022-05-02","cited_by_count":26,"area":null},{"id":"2206.04571","title":"Revisiting End-to-End Speech-to-Text Translation From Scratch","created":"2022-06-09","cited_by_count":26,"area":null},{"id":"2301.11716","title":"Pre-training for Speech Translation: CTC Meets Optimal Transport","created":"2023-01-27","cited_by_count":25,"area":null},{"id":"2105.00573","title":"Searchable Hidden Intermediates for End-to-End Models of Decomposable Sequence Tasks","created":"2021-05-02","cited_by_count":24,"area":null},{"id":"2109.06912","title":"fairseq S^2: A Scalable and Integrable Speech Synthesis Toolkit","created":"2021-09-14","cited_by_count":24,"area":null},{"id":"2204.03783","title":"Does Simultaneous Speech Translation need Simultaneous Models?","created":"2022-04-08","cited_by_count":22,"area":null},{"id":"2205.09501","title":"SDS-200: A Swiss German Speech to Standard German Text Corpus","created":"2022-05-19","cited_by_count":22,"area":null},{"id":"2305.14635","title":"CMOT: Cross-modal Mixup via Optimal Transport for Speech Translation","created":"2023-05-24","cited_by_count":22,"area":null},{"id":"2305.16093","title":"End-to-End Simultaneous Speech Translation with Differentiable Segmentation","created":"2023-05-25","cited_by_count":22,"area":null},{"id":"2212.03657","title":"M3ST: Mix at Three Levels for Speech Translation","created":"2022-12-07","cited_by_count":21,"area":null},{"id":"2204.03939","title":"GigaST: A 10,000-hour Pseudo Speech Translation Corpus","created":"2022-04-08","cited_by_count":20,"area":null},{"id":"2305.03101","title":"Hybrid Transducer and Attention based Encoder-Decoder Modeling for Speech-to-Text Tasks","created":"2023-05-04","cited_by_count":20,"area":null},{"id":"2212.06385","title":"TencentPretrain: A Scalable and Flexible Toolkit for Pre-training Models of Different Modalities","created":"2022-12-13","cited_by_count":19,"area":null},{"id":"2406.06097","title":"StreamAtt: Direct Streaming Speech-to-Text Translation with Attention-based Audio History Selection","created":"2024-06-10","cited_by_count":19,"area":null},{"id":"2305.11411","title":"DUB: Discrete Unit Back-translation for Speech Translation","created":"2023-05-19","cited_by_count":18,"area":null},{"id":"2306.04428","title":"Zambezi Voice: A Multilingual Speech Corpus for Zambian Languages","created":"2023-06-07","cited_by_count":18,"area":null},{"id":"2309.05472","title":"LeBenchmark 2.0: a Standardized, Replicable and Enhanced Framework for Self-supervised Representations of French Speech","created":"2023-09-11","cited_by_count":18,"area":null},{"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,"area":null},{"id":"2112.10991","title":"Regularizing End-to-End Speech Translation with Triangular Decomposition Agreement","created":"2021-12-21","cited_by_count":16,"area":null},{"id":"2206.00330","title":"B2T Connection: Serving Stability and Performance in Deep Transformers","created":"2022-06-01","cited_by_count":16,"area":null},{"id":"2304.13689","title":"HeySQuAD: A Spoken Question Answering Dataset","created":"2023-04-26","cited_by_count":16,"area":null},{"id":"2401.12576","title":"LLMCheckup: Conversational Examination of Large Language Models via Interpretability Tools and Self-Explanations","created":"2024-01-23","cited_by_count":16,"area":null},{"id":"2109.04574","title":"Speechformer: Reducing Information Loss in Direct Speech Translation","created":"2021-09-09","cited_by_count":15,"area":null},{"id":"2204.01397","title":"A Study of Gender Impact in Self-supervised Models for Speech-to-Text Systems","created":"2022-04-04","cited_by_count":15,"area":null},{"id":"2207.00952","title":"M-Adapter: Modality Adaptation for End-to-End Speech-to-Text Translation","created":"2022-07-03","cited_by_count":15,"area":null},{"id":"2502.03382","title":"High-Fidelity Simultaneous Speech-To-Speech Translation","created":"2025-02-05","cited_by_count":15,"area":null},{"id":"2204.09595","title":"Exploring Continuous Integrate-and-Fire for Adaptive Simultaneous Speech Translation","created":"2022-03-22","cited_by_count":14,"area":null},{"id":"2205.02629","title":"Efficient yet Competitive Speech Translation: FBK@IWSLT2022","created":"2022-05-05","cited_by_count":14,"area":null},{"id":"2303.16166","title":"When Good and Reproducible Results are a Giant with Feet of Clay: The Importance of Software Quality in NLP","created":"2023-03-28","cited_by_count":14,"area":null},{"id":"2402.10422","title":"Pushing the Limits of Zero-shot End-to-End Speech Translation","created":"2024-02-16","cited_by_count":14,"area":null},{"id":"2406.02925","title":"Task Arithmetic can Mitigate Synthetic-to-Real Gap in Automatic Speech Recognition","created":"2024-06-05","cited_by_count":14,"area":null},{"id":"2201.05051","title":"Speech Resources in the Tamasheq Language","created":"2022-01-13","cited_by_count":13,"area":null},{"id":"2201.02419","title":"Automatic Speech Recognition Datasets in Cantonese: A Survey and New Dataset","created":"2022-01-07","cited_by_count":12,"area":null},{"id":"2205.11211","title":"Non-Parametric Domain Adaptation for End-to-End Speech Translation","created":"2022-05-23","cited_by_count":12,"area":null},{"id":"2210.10191","title":"Simple and Effective Unsupervised Speech Translation","created":"2022-10-18","cited_by_count":12,"area":null},{"id":"2407.15415","title":"LLaST: Improved End-to-end Speech Translation System Leveraged by Large Language Models","created":"2024-07-22","cited_by_count":12,"area":null},{"id":"2301.10606","title":"A Holistic Cascade System, benchmark, and Human Evaluation Protocol for Expressive Speech-to-Speech Translation","created":"2023-01-25","cited_by_count":11,"area":null},{"id":"2304.04596","title":"ESPnet-ST-v2: Multipurpose Spoken Language Translation Toolkit","created":"2023-04-10","cited_by_count":10,"area":null},{"id":"2306.00794","title":"SlothSpeech: Denial-of-service Attack Against Speech Recognition Models","created":"2023-06-01","cited_by_count":10,"area":null},{"id":"2410.21485","title":"SpeechQE: Estimating the Quality of Direct Speech Translation","created":"2024-10-28","cited_by_count":10,"area":null},{"id":"2104.01393","title":"On-the-Fly Aligned Data Augmentation for Sequence-to-Sequence ASR","created":"2021-04-03","cited_by_count":9,"area":null},{"id":"2109.04411","title":"Non-autoregressive End-to-end Speech Translation with Parallel Autoregressive Rescoring","created":"2021-09-09","cited_by_count":9,"area":null},{"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,"area":null},{"id":"2110.08250","title":"Direct Simultaneous Speech-to-Speech Translation with Variational Monotonic Multihead Attention","created":"2021-10-15","cited_by_count":9,"area":null},{"id":"2212.00500","title":"MMSpeech: Multi-modal Multi-task Encoder-Decoder Pre-training for Speech Recognition","created":"2022-11-29","cited_by_count":9,"area":null},{"id":"2212.01778","title":"Improving End-to-end Speech Translation by Leveraging Auxiliary Speech and Text Data","created":"2022-12-04","cited_by_count":9,"area":null},{"id":"2305.17202","title":"BIG-C: a Multimodal Multi-Purpose Dataset for Bemba","created":"2023-05-26","cited_by_count":9,"area":null},{"id":"2305.17358","title":"CTC-based Non-autoregressive Speech Translation","created":"2023-05-27","cited_by_count":9,"area":null},{"id":"2310.02050","title":"Tuning Large language model for End-to-end Speech Translation","created":"2023-10-03","cited_by_count":9,"area":null},{"id":"2312.01053","title":"End-to-End Speech-to-Text Translation: A Survey","created":"2023-12-02","cited_by_count":9,"area":null},{"id":"2107.08807","title":"Simultaneous Speech Translation for Live Subtitling: from Delay to Display","created":"2021-07-19","cited_by_count":8,"area":null},{"id":"2205.06755","title":"Who Are We Talking About? Handling Person Names in Speech Translation","created":"2022-05-13","cited_by_count":8,"area":null},{"id":"2307.12659","title":"A Model for Every User and Budget: Label-Free and Personalized Mixed-Precision Quantization","created":"2023-07-24","cited_by_count":8,"area":null},{"id":"2107.02875","title":"Kosp2e: Korean Speech to English Translation Corpus","created":"2021-07-06","cited_by_count":7,"area":null},{"id":"2204.03740","title":"Successes and critical failures of neural networks in capturing human-like speech recognition","created":"2022-04-06","cited_by_count":7,"area":null},{"id":"2207.00412","title":"Swiss German Speech to Text system evaluation","created":"2022-07-01","cited_by_count":7,"area":null},{"id":"2209.13192","title":"Direct Speech Translation for Automatic Subtitling","created":"2022-09-27","cited_by_count":7,"area":null},{"id":"2307.10652","title":"Exploring the Landscape of Natural Language Processing Research","created":"2023-07-20","cited_by_count":7,"area":null},{"id":"2310.09088","title":"Dialect Transfer for Swiss German Speech Translation","created":"2023-10-13","cited_by_count":7,"area":null},{"id":"2409.14672","title":"Speechworthy Instruction-tuned Language Models","created":"2024-09-23","cited_by_count":7,"area":null},{"id":"2205.01987","title":"ON-TRAC Consortium Systems for the IWSLT 2022 Dialect and Low-resource Speech Translation Tasks","created":"2022-05-04","cited_by_count":6,"area":null},{"id":"2210.09556","title":"Discrete Cross-Modal Alignment Enables Zero-Shot Speech Translation","created":"2022-10-18","cited_by_count":6,"area":null},{"id":"2210.15398","title":"Make More of Your Data: Minimal Effort Data Augmentation for Automatic Speech Recognition and Translation","created":"2022-10-27","cited_by_count":6,"area":null},{"id":"2212.09699","title":"SegAugment: Maximizing the Utility of Speech Translation Data with Segmentation-based Augmentations","created":"2022-12-19","cited_by_count":6,"area":null},{"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,"area":null},{"id":"2309.15554","title":"Direct Models for Simultaneous Translation and Automatic Subtitling: FBK@IWSLT2023","created":"2023-09-27","cited_by_count":6,"area":null},{"id":"2311.03810","title":"Rethinking and Improving Multi-task Learning for End-to-end Speech Translation","created":"2023-11-07","cited_by_count":6,"area":null},{"id":"2411.01710","title":"SPES: Spectrogram Perturbation for Explainable Speech-to-Text Generation","created":"2024-11-03","cited_by_count":6,"area":null},{"id":"2106.10840","title":"Pay Better Attention to Attention: Head Selection in Multilingual and Multi-Domain Sequence Modeling","created":"2021-06-21","cited_by_count":5,"area":null},{"id":"2107.03069","title":"Efficient Transformer for Direct Speech Translation","created":"2021-07-07","cited_by_count":5,"area":null},{"id":"2204.01235","title":"An Analysis of Semantically-Aligned Speech-Text Embeddings","created":"2022-04-04","cited_by_count":5,"area":null},{"id":"2204.09028","title":"On the Locality of Attention in Direct Speech Translation","created":"2022-04-19","cited_by_count":5,"area":null}],"next_cursor":"100"}