{"total":82,"rows":[{"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":"2111.02813","title":"WaveFake: A Data Set to Facilitate Audio Deepfake Detection","created":"2021-11-04","cited_by_count":78,"area":null},{"id":"2204.05409","title":"Unified Speech-Text Pre-training for Speech Translation and Recognition","created":"2022-04-11","cited_by_count":64,"area":null},{"id":"2205.02444","title":"Cross-modal Contrastive Learning for Speech Translation","created":"2022-05-05","cited_by_count":61,"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":"2106.01045","title":"Cascade versus Direct Speech Translation: Do the Differences Still Make a Difference?","created":"2021-06-02","cited_by_count":54,"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":"2111.14706","title":"ESPnet-SLU: Advancing Spoken Language Understanding through ESPnet","created":"2021-11-29","cited_by_count":53,"area":null},{"id":"2105.03095","title":"Learning Shared Semantic Space for Speech-to-Text Translation","created":"2021-05-07","cited_by_count":49,"area":null},{"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,"area":null},{"id":"2102.05766","title":"Fused Acoustic and Text Encoding for Multimodal Bilingual Pretraining and Speech Translation","created":"2021-02-10","cited_by_count":47,"area":null},{"id":"2104.10380","title":"End-to-end Speech Translation via Cross-modal Progressive Training","created":"2021-04-21","cited_by_count":47,"area":null},{"id":"2102.01578","title":"CTC-based Compression for Direct Speech Translation","created":"2021-02-02","cited_by_count":45,"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":"2203.09690","title":"A$^3$T: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and Editing","created":"2022-03-18","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":"2110.04590","title":"An Exploration of Self-Supervised Pretrained Representations for End-to-End Speech Recognition","created":"2021-10-09","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":"2109.07368","title":"Learning When to Translate for Streaming Speech","created":"2021-09-15","cited_by_count":30,"area":null},{"id":"2104.06457","title":"Source and Target Bidirectional Knowledge Distillation for End-to-end Speech Translation","created":"2021-04-13","cited_by_count":28,"area":"distill"},{"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":"2210.05200","title":"CTC Alignments Improve Autoregressive Translation","created":"2022-10-11","cited_by_count":25,"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":"2204.03783","title":"Does Simultaneous Speech Translation need Simultaneous Models?","created":"2022-04-08","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":"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":"2409.19510","title":"Making LLMs Better Many-to-Many Speech-to-Text Translators with Curriculum Learning","created":"2024-09-29","cited_by_count":20,"area":"mllm"},{"id":"2305.11411","title":"DUB: Discrete Unit Back-translation for Speech Translation","created":"2023-05-19","cited_by_count":18,"area":null},{"id":"2104.03575","title":"BSTC: A Large-Scale Chinese-English Speech Translation Dataset","created":"2021-04-08","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":"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":"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":"2305.11073","title":"A Comparative Study on E-Branchformer vs Conformer in Speech Recognition, Translation, and Understanding Tasks","created":"2023-05-18","cited_by_count":14,"area":null},{"id":"2205.08993","title":"Leveraging Pseudo-labeled Data to Improve Direct Speech-to-Speech Translation","created":"2022-05-18","cited_by_count":12,"area":null},{"id":"2204.08920","title":"Blockwise Streaming Transformer for Spoken Language Understanding and Simultaneous Speech Translation","created":"2022-04-19","cited_by_count":11,"area":null},{"id":"2206.09507","title":"Resource-Efficient Separation Transformer","created":"2022-06-19","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":"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":"2111.08201","title":"Attention-based Multi-hypothesis Fusion for Speech Summarization","created":"2021-11-16","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":"2312.01053","title":"End-to-End Speech-to-Text Translation: A Survey","created":"2023-12-02","cited_by_count":9,"area":null},{"id":"2309.11379","title":"Incremental Blockwise Beam Search for Simultaneous Speech Translation with Controllable Quality-Latency Tradeoff","created":"2023-09-20","cited_by_count":8,"area":null},{"id":"2312.04515","title":"Efficient Monotonic Multihead Attention","created":"2023-12-07","cited_by_count":8,"area":null},{"id":"2110.00046","title":"SpliceOut: A Simple and Efficient Audio Augmentation Method","created":"2021-09-30","cited_by_count":7,"area":null},{"id":"2203.15479","title":"Speech Segmentation Optimization using Segmented Bilingual Speech Corpus for End-to-end Speech Translation","created":"2022-03-29","cited_by_count":7,"area":null},{"id":"2304.10309","title":"Improving Speech Translation by Cross-Modal Multi-Grained Contrastive Learning","created":"2023-04-20","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":"2206.13756","title":"On the Impact of Noises in Crowd-Sourced Data for Speech Translation","created":"2022-06-28","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":"2402.16021","title":"TMT: Tri-Modal Translation between Speech, Image, and Text by Processing Different Modalities as Different Languages","created":"2024-02-25","cited_by_count":5,"area":null},{"id":"2406.04541","title":"Label-Synchronous Neural Transducer for E2E Simultaneous Speech Translation","created":"2024-06-06","cited_by_count":5,"area":null},{"id":"2211.05967","title":"Align, Write, Re-order: Explainable End-to-End Speech Translation via Operation Sequence Generation","created":"2022-11-11","cited_by_count":4,"area":null},{"id":"2406.10993","title":"CoSTA: Code-Switched Speech Translation using Aligned Speech-Text Interleaving","created":"2024-06-16","cited_by_count":4,"area":null},{"id":"2211.03025","title":"Bridging Speech and Textual Pre-trained Models with Unsupervised ASR","created":"2022-11-06","cited_by_count":3,"area":null},{"id":"2304.10295","title":"Decouple Non-parametric Knowledge Distillation For End-to-end Speech Translation","created":"2023-04-20","cited_by_count":3,"area":"distill"},{"id":"2306.00208","title":"Strategies for improving low resource speech to text translation relying on pre-trained ASR models","created":"2023-05-31","cited_by_count":3,"area":null},{"id":"2308.13345","title":"Decoupled Structure for Improved Adaptability of End-to-End Models","created":"2023-08-25","cited_by_count":3,"area":null},{"id":"2309.15826","title":"Cross-Modal Multi-Tasking for Speech-to-Text Translation via Hard Parameter Sharing","created":"2023-09-27","cited_by_count":3,"area":null},{"id":"2412.04266","title":"Representation Purification for End-to-End Speech Translation","created":"2024-12-05","cited_by_count":3,"area":null},{"id":"2504.15509","title":"SimulS2S-LLM: Unlocking Simultaneous Inference of Speech LLMs for Speech-to-Speech Translation","created":"2025-04-22","cited_by_count":3,"area":null},{"id":"2105.00171","title":"AlloST: Low-resource Speech Translation without Source Transcription","created":"2021-05-01","cited_by_count":2,"area":null},{"id":"2209.06913","title":"ESSumm: Extractive Speech Summarization from Untranscribed Meeting","created":"2022-09-14","cited_by_count":2,"area":null},{"id":"2405.13046","title":"LeaPformer: Enabling Linear Transformers for Autoregressive and Simultaneous Tasks via Learned Proportions","created":"2024-05-18","cited_by_count":2,"area":null},{"id":"2407.03026","title":"Qifusion-Net: Layer-adapted Stream/Non-stream Model for End-to-End Multi-Accent Speech Recognition","created":"2024-07-03","cited_by_count":2,"area":null},{"id":"2302.10871","title":"Efficient CTC Regularization via Coarse Labels for End-to-End Speech Translation","created":"2023-02-21","cited_by_count":1,"area":null},{"id":"2304.10321","title":"DropDim: A Regularization Method for Transformer Networks","created":"2023-04-20","cited_by_count":1,"area":null},{"id":"2310.05919","title":"Few-Shot Spoken Language Understanding via Joint Speech-Text Models","created":"2023-10-09","cited_by_count":1,"area":null},{"id":"2502.09284","title":"SparQLe: Speech Queries to Text Translation Through LLMs","created":"2025-02-13","cited_by_count":1,"area":null},{"id":"2503.00957","title":"Exploiting Vulnerabilities in Speech Translation Systems through Targeted Adversarial Attacks","created":"2025-03-02","cited_by_count":1,"area":null},{"id":"2506.16251","title":"End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data","created":"2025-06-19","cited_by_count":1,"area":null},{"id":"2107.00636","title":"ESPnet-ST IWSLT 2021 Offline Speech Translation System","created":"2021-07-01","cited_by_count":0,"area":null},{"id":"2107.06155","title":"The IWSLT 2021 BUT Speech Translation Systems","created":"2021-07-13","cited_by_count":0,"area":null},{"id":"2210.02545","title":"JoeyS2T: Minimalistic Speech-to-Text Modeling with JoeyNMT","created":"2022-10-05","cited_by_count":0,"area":null},{"id":"2304.03169","title":"Selective Data Augmentation for Robust Speech Translation","created":"2023-03-22","cited_by_count":0,"area":null},{"id":"2409.09506","title":"ESPnet-EZ: Python-only ESPnet for Easy Fine-tuning and Integration","created":"2024-09-14","cited_by_count":0,"area":null},{"id":"2503.14185","title":"AdaST: Dynamically Adapting Encoder States in the Decoder for End-to-End Speech-to-Text Translation","created":"2025-03-18","cited_by_count":0,"area":null}],"next_cursor":null}