{"total":93,"rows":[{"id":"2409.06666","title":"LLaMA-Omni: Seamless Speech Interaction with Large Language Models","created":"2024-09-10","cited_by_count":173,"area":null},{"id":"2110.00966","title":"Translating Images into Maps","created":"2021-10-03","cited_by_count":115,"area":null},{"id":"2210.12357","title":"Information-Transport-based Policy for Simultaneous Translation","created":"2022-10-22","cited_by_count":40,"area":null},{"id":"2402.04636","title":"TransLLaMa: LLM-based Simultaneous Translation System","created":"2024-02-07","cited_by_count":34,"area":null},{"id":"2109.05238","title":"Universal Simultaneous Machine Translation with Mixture-of-Experts Wait-k Policy","created":"2021-09-11","cited_by_count":32,"area":"moe"},{"id":"2212.07850","title":"Attention as a Guide for Simultaneous Speech Translation","created":"2022-12-15","cited_by_count":32,"area":null},{"id":"2204.05352","title":"Large-Scale Streaming End-to-End Speech Translation with Neural Transducers","created":"2022-04-11","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":"2103.13597","title":"Mask Attention Networks: Rethinking and Strengthen Transformer","created":"2021-03-25","cited_by_count":28,"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":"2303.00257","title":"Hidden Markov Transformer for Simultaneous Machine Translation","created":"2023-03-01","cited_by_count":25,"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":"2203.09163","title":"Modeling Dual Read/Write Paths for Simultaneous Machine Translation","created":"2022-03-17","cited_by_count":21,"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":"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":"2203.09072","title":"Gaussian Multi-head Attention for Simultaneous Machine Translation","created":"2022-03-17","cited_by_count":17,"area":null},{"id":"2203.09053","title":"Reducing Position Bias in Simultaneous Machine Translation with Length-Aware Framework","created":"2022-03-17","cited_by_count":16,"area":null},{"id":"2210.11220","title":"Wait-info Policy: Balancing Source and Target at Information Level for Simultaneous Machine Translation","created":"2022-10-20","cited_by_count":16,"area":null},{"id":"2305.12774","title":"Learning Optimal Policy for Simultaneous Machine Translation via Binary Search","created":"2023-05-22","cited_by_count":15,"area":null},{"id":"2103.03233","title":"An Empirical Study of End-to-end Simultaneous Speech Translation Decoding Strategies","created":"2021-03-04","cited_by_count":14,"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":"2210.11900","title":"Turning Fixed to Adaptive: Integrating Post-Evaluation into Simultaneous Machine Translation","created":"2022-10-21","cited_by_count":14,"area":null},{"id":"2510.05150","title":"Chronological Thinking in Full-Duplex Spoken Dialogue Language Models","created":"2025-10-02","cited_by_count":14,"area":"lr"},{"id":"2107.00279","title":"The USTC-NELSLIP Systems for Simultaneous Speech Translation Task at IWSLT 2021","created":"2021-07-01","cited_by_count":13,"area":null},{"id":"2402.13036","title":"SiLLM: Large Language Models for Simultaneous Machine Translation","created":"2024-02-20","cited_by_count":13,"area":null},{"id":"2211.02499","title":"A Weakly-Supervised Streaming Multilingual Speech Model with Truly Zero-Shot Capability","created":"2022-11-04","cited_by_count":12,"area":null},{"id":"2310.14883","title":"Non-autoregressive Streaming Transformer for Simultaneous Translation","created":"2023-10-23","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":"2406.03878","title":"Decoder-only Streaming Transformer for Simultaneous Translation","created":"2024-06-06","cited_by_count":11,"area":null},{"id":"2309.06179","title":"Glancing Future for Simultaneous Machine Translation","created":"2023-09-12","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":"2203.02459","title":"From Simultaneous to Streaming Machine Translation by Leveraging Streaming History","created":"2022-03-04","cited_by_count":9,"area":null},{"id":"2309.06706","title":"Simultaneous Machine Translation with Large Language Models","created":"2023-09-13","cited_by_count":9,"area":null},{"id":"2310.13588","title":"Simultaneous Machine Translation with Tailored Reference","created":"2023-10-20","cited_by_count":9,"area":null},{"id":"2310.14853","title":"Adaptive Policy with Wait-$k$ Model for Simultaneous Translation","created":"2023-10-23","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":"2502.00634","title":"SimulPL: Aligning Human Preferences in Simultaneous Machine Translation","created":"2025-02-02","cited_by_count":7,"area":"alignment"},{"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":"2310.17940","title":"Unified Segment-to-Segment Framework for Simultaneous Sequence Generation","created":"2023-10-27","cited_by_count":6,"area":null},{"id":"2102.07259","title":"Thank you for Attention: A survey on Attention-based Artificial Neural Networks for Automatic Speech Recognition","created":"2021-02-14","cited_by_count":5,"area":null},{"id":"2104.03945","title":"On Biasing Transformer Attention Towards Monotonicity","created":"2021-04-08","cited_by_count":5,"area":null},{"id":"2201.12868","title":"Anticipation-Free Training for Simultaneous Machine Translation","created":"2022-01-30","cited_by_count":5,"area":null},{"id":"2305.10845","title":"TAPIR: Learning Adaptive Revision for Incremental Natural Language Understanding with a Two-Pass Model","created":"2023-05-18","cited_by_count":5,"area":null},{"id":"2406.02237","title":"Self-Modifying State Modeling for Simultaneous Machine Translation","created":"2024-06-04","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":"2104.14470","title":"Impact of Encoding and Segmentation Strategies on End-to-End Simultaneous Speech Translation","created":"2021-04-29","cited_by_count":4,"area":null},{"id":"2110.09646","title":"Monotonic Simultaneous Translation with Chunk-wise Reordering and Refinement","created":"2021-10-18","cited_by_count":4,"area":null},{"id":"2301.09244","title":"Efficient Encoders for Streaming Sequence Tagging","created":"2023-01-23","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":"2406.02950","title":"Joint Beam Search Integrating CTC, Attention, and Transducer Decoders","created":"2024-06-05","cited_by_count":4,"area":null},{"id":"2110.13480","title":"Simultaneous Neural Machine Translation with Constituent Label Prediction","created":"2021-10-26","cited_by_count":3,"area":null},{"id":"2309.14823","title":"Segmentation-Free Streaming Machine Translation","created":"2023-09-26","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":"2504.18715","title":"Spatial Speech Translation: Translating Across Space With Binaural Hearables","created":"2025-04-25","cited_by_count":3,"area":null},{"id":"2201.09324","title":"Supervised Visual Attention for Simultaneous Multimodal Machine Translation","created":"2022-01-23","cited_by_count":2,"area":null},{"id":"2203.16224","title":"End to End Lip Synchronization with a Temporal AutoEncoder","created":"2022-03-30","cited_by_count":2,"area":null},{"id":"2209.15176","title":"Adaptive Sparse and Monotonic Attention for Transformer-based Automatic Speech Recognition","created":"2022-09-30","cited_by_count":2,"area":null},{"id":"2310.16417","title":"Enhanced Simultaneous Machine Translation with Word-level Policies","created":"2023-10-25","cited_by_count":2,"area":null},{"id":"2312.14488","title":"Language Model is a Branch Predictor for Simultaneous Machine Translation","created":"2023-12-22","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":"2406.06910","title":"Agent-SiMT: Agent-assisted Simultaneous Machine Translation with Large Language Models","created":"2024-06-11","cited_by_count":2,"area":"agents"},{"id":"2407.13469","title":"Fixed and Adaptive Simultaneous Machine Translation Strategies Using Adapters","created":"2024-07-18","cited_by_count":2,"area":null},{"id":"2410.04075","title":"PsFuture: A Pseudo-Future-based Zero-Shot Adaptive Policy for Simultaneous Machine Translation","created":"2024-10-05","cited_by_count":2,"area":null},{"id":"2509.01200","title":"SimulMEGA: MoE Routers are Advanced Policy Makers for Simultaneous Speech Translation","created":"2025-09-01","cited_by_count":2,"area":"moe"},{"id":"2603.14267","title":"DiFlowDubber: Discrete Flow Matching for Automated Video Dubbing via Cross-Modal Alignment and Synchronization","created":"2026-03-15","cited_by_count":2,"area":"diffusion"},{"id":"2109.03121","title":"Infusing Future Information into Monotonic Attention Through Language Models","created":"2021-09-07","cited_by_count":1,"area":null},{"id":"2311.03672","title":"CBSiMT: Mitigating Hallucination in Simultaneous Machine Translation with Weighted Prefix-to-Prefix Training","created":"2023-11-07","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":"2406.07239","title":"On the Hallucination in Simultaneous Machine Translation","created":"2024-06-11","cited_by_count":1,"area":null},{"id":"2410.05146","title":"CTC-GMM: CTC guided modality matching for fast and accurate streaming speech translation","created":"2024-10-07","cited_by_count":1,"area":null},{"id":"2410.22499","title":"Anticipating Future with Large Language Model for Simultaneous Machine Translation","created":"2024-10-29","cited_by_count":1,"area":null},{"id":"2503.22051","title":"Non-Monotonic Attention-based Read/Write Policy Learning for Simultaneous Translation","created":"2025-03-28","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":"2603.11578","title":"Streaming Translation and Transcription Through Speech-to-Text Causal Alignment","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2103.14302","title":"Mutually-Constrained Monotonic Multihead Attention for Online ASR","created":"2021-03-26","cited_by_count":0,"area":null},{"id":"2105.01893","title":"Full-Sentence Models Perform Better in Simultaneous Translation Using the Information Enhanced Decoding Strategy","created":"2021-05-05","cited_by_count":0,"area":null},{"id":"2204.12672","title":"Data-Driven Adaptive Simultaneous Machine Translation","created":"2022-04-27","cited_by_count":0,"area":null},{"id":"2303.00969","title":"Rethinking the Reasonability of the Test Set for Simultaneous Machine Translation","created":"2023-03-02","cited_by_count":0,"area":null},{"id":"2311.07066","title":"Context Consistency between Training and Testing in Simultaneous Machine Translation","created":"2023-11-13","cited_by_count":0,"area":null},{"id":"2508.13358","title":"Overcoming Latency Bottlenecks in On-Device Speech Translation: A Cascaded Approach with Alignment-Based Streaming MT","created":"2025-08-18","cited_by_count":0,"area":null},{"id":"2605.06582","title":"PairAlign: A Framework for Autoregressive Tokenization via Self-Alignment with Applications to Audio Tokenization","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2606.08486","title":"TRADE: Transducer-Augmented Decoder for Speech LLM","created":"2026-06-07","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":"2607.17544","title":"X-Translator: A Real-Time Multilingual Speaker-Aware Speech-to-Speech Translation System","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2608.18661","title":"X2Streaming-TTS: Causal Token-Level Text-to-Speech from Streaming Text with Speech-State Inheritance","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2609.05799","title":"Dynamic Lagging using Stable-Prefix Training for Simultaneous Translation","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.20845","title":"Reading Less While Writing: A Closed-Form Bandwidth Dial for Streaming Multimodal Decoders","created":"2026-08-05","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}