{"total":76,"rows":[{"id":"2206.05807","title":"Over-Generation Cannot Be Rewarded: Length-Adaptive Average Lagging for Simultaneous Speech Translation","created":"2022-06-12","cited_by_count":57,"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":"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":"2212.07850","title":"Attention as a Guide for Simultaneous Speech Translation","created":"2022-12-15","cited_by_count":32,"area":null},{"id":"2106.06636","title":"Direct Simultaneous Speech-to-Text Translation Assisted by Synchronized Streaming ASR","created":"2021-06-11","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":"2112.04228","title":"SimulSLT: End-to-End Simultaneous Sign Language Translation","created":"2021-12-08","cited_by_count":27,"area":null},{"id":"2402.12025","title":"Speech Translation with Speech Foundation Models and Large Language Models: What is There and What is Missing?","created":"2024-02-19","cited_by_count":23,"area":null},{"id":"2204.03783","title":"Does Simultaneous Speech Translation need Simultaneous Models?","created":"2022-04-08","cited_by_count":22,"area":null},{"id":"2305.16093","title":"End-to-End Simultaneous Speech Translation with Differentiable Segmentation","created":"2023-05-25","cited_by_count":22,"area":null},{"id":"2406.03049","title":"StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learning","created":"2024-06-05","cited_by_count":21,"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":"2406.19954","title":"BESTOW: Efficient and Streamable Speech Language Model with the Best of Two Worlds in GPT and T5","created":"2024-06-28","cited_by_count":19,"area":null},{"id":"2412.18495","title":"How \"Real\" is Your Real-Time Simultaneous Speech-to-Text Translation System?","created":"2024-12-24","cited_by_count":17,"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":"2504.11809","title":"Efficient and Adaptive Simultaneous Speech Translation with Fully Unidirectional Architecture","created":"2025-04-16","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":"2405.10443","title":"Simultaneous Masking, Not Prompting Optimization: A Paradigm Shift in Fine-tuning LLMs for Simultaneous Translation","created":"2024-05-16","cited_by_count":11,"area":null},{"id":"2406.03878","title":"Decoder-only Streaming Transformer for Simultaneous Translation","created":"2024-06-06","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":"2406.06937","title":"A Non-autoregressive Generation Framework for End-to-End Simultaneous Speech-to-Speech Translation","created":"2024-06-11","cited_by_count":10,"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":"2107.08807","title":"Simultaneous Speech Translation for Live Subtitling: from Delay to Display","created":"2021-07-19","cited_by_count":8,"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":"2503.02969","title":"InfiniSST: Simultaneous Translation of Unbounded Speech with Large Language Model","created":"2025-03-04","cited_by_count":8,"area":null},{"id":"2108.13630","title":"SimulLR: Simultaneous Lip Reading Transducer with Attention-Guided Adaptive Memory","created":"2021-08-31","cited_by_count":7,"area":null},{"id":"2408.09430","title":"FASST: Fast LLM-based Simultaneous Speech Translation","created":"2024-08-18","cited_by_count":7,"area":null},{"id":"2110.15729","title":"Decision Attentive Regularization to Improve Simultaneous Speech Translation Systems","created":"2021-10-13","cited_by_count":6,"area":null},{"id":"2303.07914","title":"Adapting Offline Speech Translation Models for Streaming with Future-Aware Distillation and Inference","created":"2023-03-14","cited_by_count":6,"area":null},{"id":"2306.08582","title":"Tagged End-to-End Simultaneous Speech Translation Training using Simultaneous Interpretation Data","created":"2023-06-14","cited_by_count":6,"area":null},{"id":"2307.03354","title":"Token-Level Serialized Output Training for Joint Streaming ASR and ST Leveraging Textual Alignments","created":"2023-07-07","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":"2310.17940","title":"Unified Segment-to-Segment Framework for Simultaneous Sequence Generation","created":"2023-10-27","cited_by_count":6,"area":null},{"id":"2507.07803","title":"StreamUni: Achieving Streaming Speech Translation with a Unified Large Speech-Language Model","created":"2025-07-10","cited_by_count":6,"area":null},{"id":"2201.12868","title":"Anticipation-Free Training for Simultaneous Machine Translation","created":"2022-01-30","cited_by_count":5,"area":null},{"id":"2210.11987","title":"Joint Speech Translation and Named Entity Recognition","created":"2022-10-21","cited_by_count":5,"area":null},{"id":"2406.00497","title":"Recent Advances in End-to-End Simultaneous Speech Translation","created":"2024-06-01","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":"2501.00868","title":"Large Language Models Are Read/Write Policy-Makers for Simultaneous Generation","created":"2025-01-01","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":"2303.11750","title":"LEAPT: Learning Adaptive Prefix-to-prefix Translation For Simultaneous Machine Translation","created":"2023-03-21","cited_by_count":4,"area":null},{"id":"2307.01377","title":"Shiftable Context: Addressing Training-Inference Context Mismatch in Simultaneous Speech Translation","created":"2023-07-03","cited_by_count":4,"area":null},{"id":"2307.01381","title":"Implicit Memory Transformer for Computationally Efficient Simultaneous Speech Translation","created":"2023-07-03","cited_by_count":4,"area":null},{"id":"2402.10552","title":"Conversational SimulMT: Efficient Simultaneous Translation with Large Language Models","created":"2024-02-16","cited_by_count":4,"area":null},{"id":"2411.17170","title":"Overcoming Non-monotonicity in Transducer-based Streaming Generation","created":"2024-11-26","cited_by_count":4,"area":null},{"id":"2412.16464","title":"Transducer-Llama: Integrating LLMs into Streamable Transducer-based Speech Recognition","created":"2024-12-21","cited_by_count":4,"area":null},{"id":"2110.08214","title":"From Start to Finish: Latency Reduction Strategies for Incremental Speech Synthesis in Simultaneous Speech-to-Speech Translation","created":"2021-10-15","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":"2111.00514","title":"Visualization: the missing factor in Simultaneous Speech Translation","created":"2021-10-31","cited_by_count":2,"area":null},{"id":"2304.08453","title":"Improving Autoregressive NLP Tasks via Modular Linearized Attention","created":"2023-04-17","cited_by_count":2,"area":null},{"id":"2306.01201","title":"Learning When to Speak: Latency and Quality Trade-offs for Simultaneous Speech-to-Speech Translation with Offline Models","created":"2023-06-01","cited_by_count":2,"area":null},{"id":"2402.01172","title":"Streaming Sequence Transduction through Dynamic Compression","created":"2024-02-02","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":"2109.03121","title":"Infusing Future Information into Monotonic Attention Through Language Models","created":"2021-09-07","cited_by_count":1,"area":null},{"id":"2401.05700","title":"R-BI: Regularized Batched Inputs enhance Incremental Decoding Framework for Low-Latency Simultaneous Speech Translation","created":"2024-01-11","cited_by_count":1,"area":null},{"id":"2407.00826","title":"NAIST Simultaneous Speech Translation System for IWSLT 2024","created":"2024-06-30","cited_by_count":1,"area":null},{"id":"2409.00965","title":"What does it take to get state of the art in simultaneous speech-to-speech translation?","created":"2024-09-02","cited_by_count":1,"area":null},{"id":"2508.04946","title":"REINA: Regularized Entropy Information-Based Loss for Efficient Simultaneous Speech Translation","created":"2025-08-07","cited_by_count":1,"area":null},{"id":"2604.21045","title":"Hierarchical Policy Optimization for Simultaneous Translation of Unbounded Speech","created":"2026-04-22","cited_by_count":1,"area":null},{"id":"2605.31432","title":"DOA: Training-Free Decoder-Only Attention Policy for Long-Form Simultaneous Translation with SpeechLLMs","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2204.12672","title":"Data-Driven Adaptive Simultaneous Machine Translation","created":"2022-04-27","cited_by_count":0,"area":null},{"id":"2306.14031","title":"Partitioning-Guided K-Means: Extreme Empty Cluster Resolution for Extreme Model Compression","created":"2023-06-24","cited_by_count":0,"area":null},{"id":"2410.16011","title":"CA*: Addressing Evaluation Pitfalls in Computation-Aware Latency for Simultaneous Speech Translation","created":"2024-10-21","cited_by_count":0,"area":null},{"id":"2411.07387","title":"Isochrony-Controlled Speech-to-Text Translation: A study on translating from Sino-Tibetan to Indo-European Languages","created":"2024-11-11","cited_by_count":0,"area":null},{"id":"2503.11080","title":"Joint Training And Decoding for Multilingual End-to-End Simultaneous Speech Translation","created":"2025-03-14","cited_by_count":0,"area":null},{"id":"2509.21932","title":"SimulSense: Sense-Driven Interpreting for Efficient Simultaneous Speech Translation","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2603.11273","title":"Duration Aware Scheduling for ASR Serving Under Workload Drift","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2604.09916","title":"Regularized Entropy Information Adaptation with Temporal-Awareness Networks for Simultaneous Speech Translation","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2607.13158","title":"Do LLMs Need Architectural Changes for Simultaneous Speech Translation? A Prefix-to-Prefix Data Driven Approach","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2609.30839","title":"Attention-Based Adaptive Policies for Simultaneous Speech-to-Text Translation","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.35608","title":"Simultaneous Translation between Sign Languages","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.38612","title":"StreamDecisionBench: Evaluating Decisions in Force on Evolving Language Streams","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.03022","title":"ReSCUE: Re-translation with Sentence Commitment for Unsegmented Long-Form Simultaneous Sign Language Translation","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}