{"list":"other","total":120,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"2009.09025","title":"COMET: A Neural Framework for MT Evaluation","created":"2020-09-18","cited_by_count":1033},{"id":"2009.06732","title":"Efficient Transformers: A Survey","created":"2020-09-14","cited_by_count":790},{"id":"2002.02562","title":"Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss","created":"2020-02-07","cited_by_count":235},{"id":"2303.01037","title":"Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages","created":"2023-03-02","cited_by_count":231},{"id":"2312.05187","title":"Seamless: Multilingual Expressive and Streaming Speech Translation","created":"2023-12-08","cited_by_count":192},{"id":"2101.09624","title":"A Review of Speaker Diarization: Recent Advances with Deep Learning","created":"2021-01-24","cited_by_count":124},{"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":"1708.05943","title":"Neural Machine Translation with Extended Context","created":"2017-08-20","cited_by_count":95},{"id":"1511.06114","title":"Multi-task Sequence to Sequence Learning","created":"2015-11-19","cited_by_count":94},{"id":"2007.16193","title":"SimulEval: An Evaluation Toolkit for Simultaneous Translation","created":"2020-07-31","cited_by_count":94},{"id":"1606.02012","title":"Can neural machine translation do simultaneous translation?","created":"2016-06-07","cited_by_count":86},{"id":"2011.02048","title":"SimulMT to SimulST: Adapting Simultaneous Text Translation to End-to-End Simultaneous Speech Translation","created":"2020-11-03","cited_by_count":81},{"id":"1910.11455","title":"Recognizing long-form speech using streaming end-to-end models","created":"2019-10-24","cited_by_count":77},{"id":"2004.06358","title":"Speech Translation and the End-to-End Promise: Taking Stock of Where We Are","created":"2020-04-14","cited_by_count":77},{"id":"2001.02674","title":"Streaming automatic speech recognition with the transformer model","created":"2020-01-08","cited_by_count":73},{"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":"2005.08595","title":"Efficient Wait-k Models for Simultaneous Machine Translation","created":"2020-05-18","cited_by_count":61},{"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},{"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":"1806.03661","title":"Incremental Decoding and Training Methods for Simultaneous Translation in Neural Machine Translation","created":"2018-06-10","cited_by_count":52},{"id":"2105.03482","title":"Measuring and Increasing Context Usage in Context-Aware Machine Translation","created":"2021-05-07","cited_by_count":48},{"id":"1910.00294","title":"When and Why is Document-level Context Useful in Neural Machine Translation?","created":"2019-10-01","cited_by_count":45},{"id":"1911.02242","title":"A comparison of end-to-end models for long-form speech recognition","created":"2019-11-06","cited_by_count":42},{"id":"2308.12792","title":"Sparks of Large Audio Models: A Survey and Outlook","created":"2023-08-24","cited_by_count":41},{"id":"1911.08870","title":"A Comparative Study on End-to-end Speech to Text Translation","created":"2019-11-20","cited_by_count":40},{"id":"2106.04833","title":"RealTranS: End-to-End Simultaneous Speech Translation with Convolutional Weighted-Shrinking Transformer","created":"2021-06-09","cited_by_count":40},{"id":"2210.12357","title":"Information-Transport-based Policy for Simultaneous Translation","created":"2022-10-22","cited_by_count":40},{"id":"2401.06760","title":"Navigating the Metrics Maze: Reconciling Score Magnitudes and Accuracies","created":"2024-01-12","cited_by_count":40},{"id":"1808.00491","title":"Low-Latency Neural Speech Translation","created":"2018-08-01","cited_by_count":37},{"id":"2005.08042","title":"Streaming Transformer-based Acoustic Models Using Self-attention with Augmented Memory","created":"2020-05-16","cited_by_count":35},{"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},{"id":"2212.07850","title":"Attention as a Guide for Simultaneous Speech Translation","created":"2022-12-15","cited_by_count":32},{"id":"2004.03643","title":"Re-translation versus Streaming for Simultaneous Translation","created":"2020-04-07","cited_by_count":31},{"id":"2106.06636","title":"Direct Simultaneous Speech-to-Text Translation Assisted by Synchronized Streaming ASR","created":"2021-06-11","cited_by_count":31},{"id":"2204.05352","title":"Large-Scale Streaming End-to-End Speech Translation with Neural Transducers","created":"2022-04-11","cited_by_count":31},{"id":"2011.00033","title":"Streaming Simultaneous Speech Translation with Augmented Memory Transformer","created":"2020-10-30","cited_by_count":30},{"id":"2109.07368","title":"Learning When to Translate for Streaming Speech","created":"2021-09-15","cited_by_count":30},{"id":"2203.15321","title":"Noise-robust Speech Recognition with 10 Minutes Unparalleled In-domain Data","created":"2022-03-29","cited_by_count":30},{"id":"2204.06028","title":"CUNI-KIT System for Simultaneous Speech Translation Task at IWSLT 2022","created":"2022-04-12","cited_by_count":30},{"id":"1906.00048","title":"Thinking Slow about Latency Evaluation for Simultaneous Machine Translation","created":"2019-05-31","cited_by_count":28},{"id":"2202.04774","title":"SHAS: Approaching optimal Segmentation for End-to-End Speech Translation","created":"2022-02-09","cited_by_count":26},{"id":"2204.05076","title":"End-to-End Speech Translation for Code Switched Speech","created":"2022-04-11","cited_by_count":26},{"id":"1912.03393","title":"Re-Translation Strategies For Long Form, Simultaneous, Spoken Language Translation","created":"2019-12-06","cited_by_count":25},{"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},{"id":"2204.03783","title":"Does Simultaneous Speech Translation need Simultaneous Models?","created":"2022-04-08","cited_by_count":22},{"id":"2305.16093","title":"End-to-End Simultaneous Speech Translation with Differentiable Segmentation","created":"2023-05-25","cited_by_count":22},{"id":"2006.01080","title":"Is 42 the Answer to Everything in Subtitling-oriented Speech Translation?","created":"2020-06-01","cited_by_count":21},{"id":"2406.03049","title":"StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learning","created":"2024-06-05","cited_by_count":21},{"id":"2002.00551","title":"End-to-End Automatic Speech Recognition Integrated With CTC-Based Voice Activity Detection","created":"2020-02-03","cited_by_count":20},{"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},{"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},{"id":"2411.05088","title":"Findings of the IWSLT 2024 Evaluation Campaign","created":"2024-11-07","cited_by_count":19},{"id":"2104.11710","title":"Beyond Voice Activity Detection: Hybrid Audio Segmentation for Direct Speech Translation","created":"2021-04-23","cited_by_count":17},{"id":"2204.10749","title":"E2E Segmenter: Joint Segmenting and Decoding for Long-Form ASR","created":"2022-04-22","cited_by_count":17},{"id":"2211.13173","title":"Average Token Delay: A Latency Metric for Simultaneous Translation","created":"2022-11-22","cited_by_count":15},{"id":"2103.03233","title":"An Empirical Study of End-to-end Simultaneous Speech Translation Decoding Strategies","created":"2021-03-04","cited_by_count":14},{"id":"2204.09595","title":"Exploring Continuous Integrate-and-Fire for Adaptive Simultaneous Speech Translation","created":"2022-03-22","cited_by_count":14},{"id":"2205.02629","title":"Efficient yet Competitive Speech Translation: FBK@IWSLT2022","created":"2022-05-05","cited_by_count":14},{"id":"2106.03717","title":"Diverse Pretrained Context Encodings Improve Document Translation","created":"2021-06-07","cited_by_count":13},{"id":"2107.00279","title":"The USTC-NELSLIP Systems for Simultaneous Speech Translation Task at IWSLT 2021","created":"2021-07-01","cited_by_count":13},{"id":"2210.01512","title":"Code-Switching without Switching: Language Agnostic End-to-End Speech Translation","created":"2022-10-04","cited_by_count":13},{"id":"1803.09164","title":"Low-Resource Speech-to-Text Translation","created":"2018-03-24","cited_by_count":12},{"id":"2008.02270","title":"Contextualized Translation of Automatically Segmented Speech","created":"2020-08-05","cited_by_count":12},{"id":"2211.02499","title":"A Weakly-Supervised Streaming Multilingual Speech Model with Truly Zero-Shot Capability","created":"2022-11-04","cited_by_count":12},{"id":"2204.08920","title":"Blockwise Streaming Transformer for Spoken Language Understanding and Simultaneous Speech Translation","created":"2022-04-19","cited_by_count":11},{"id":"2101.09149","title":"Streaming Models for Joint Speech Recognition and Translation","created":"2021-01-22","cited_by_count":10},{"id":"2110.03841","title":"Input Length Matters: Improving RNN-T and MWER Training for Long-form Telephony Speech Recognition","created":"2021-10-08","cited_by_count":10},{"id":"2211.02809","title":"LAMASSU: Streaming Language-Agnostic Multilingual Speech Recognition and Translation Using Neural Transducers","created":"2022-11-05","cited_by_count":10},{"id":"2308.03415","title":"End-to-End Evaluation for Low-Latency Simultaneous Speech Translation","created":"2023-08-07","cited_by_count":10},{"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},{"id":"2005.11861","title":"ON-TRAC Consortium for End-to-End and Simultaneous Speech Translation Challenge Tasks at IWSLT 2020","created":"2020-05-24","cited_by_count":9},{"id":"2211.08633","title":"MT Metrics Correlate with Human Ratings of Simultaneous Speech Translation","created":"2022-11-16","cited_by_count":9},{"id":"2005.00675","title":"Opportunistic Decoding with Timely Correction for Simultaneous Translation","created":"2020-05-02","cited_by_count":8},{"id":"2005.14489","title":"Neural Simultaneous Speech Translation Using Alignment-Based Chunking","created":"2020-05-29","cited_by_count":8},{"id":"2103.08364","title":"Towards the evaluation of automatic simultaneous speech translation from a communicative perspective","created":"2021-03-15","cited_by_count":8},{"id":"2107.08807","title":"Simultaneous Speech Translation for Live Subtitling: from Delay to Display","created":"2021-07-19","cited_by_count":8},{"id":"2210.13363","title":"Don't Discard Fixed-Window Audio Segmentation in Speech-to-Text Translation","created":"2022-10-24","cited_by_count":8},{"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},{"id":"2312.04515","title":"Efficient Monotonic Multihead Attention","created":"2023-12-07","cited_by_count":8},{"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},{"id":"1907.12984","title":"DuTongChuan: Context-aware Translation Model for Simultaneous Interpreting","created":"2019-07-30","cited_by_count":6},{"id":"2203.02458","title":"Continuous Rating as Reliable Human Evaluation of Simultaneous Speech Translation","created":"2022-03-04","cited_by_count":6},{"id":"2210.09754","title":"Simultaneous Translation for Unsegmented Input: A Sliding Window Approach","created":"2022-10-18","cited_by_count":6},{"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},{"id":"2306.08582","title":"Tagged End-to-End Simultaneous Speech Translation Training using Simultaneous Interpretation Data","created":"2023-06-14","cited_by_count":6},{"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},{"id":"2309.11384","title":"Long-Form End-to-End Speech Translation via Latent Alignment Segmentation","created":"2023-09-20","cited_by_count":6},{"id":"2309.15554","title":"Direct Models for Simultaneous Translation and Automatic Subtitling: FBK@IWSLT2023","created":"2023-09-27","cited_by_count":6},{"id":"2310.17940","title":"Unified Segment-to-Segment Framework for Simultaneous Sequence Generation","created":"2023-10-27","cited_by_count":6},{"id":"2006.03331","title":"ELITR Non-Native Speech Translation at IWSLT 2020","created":"2020-06-05","cited_by_count":5},{"id":"2209.10608","title":"Dodging the Data Bottleneck: Automatic Subtitling with Automatically Segmented ST Corpora","created":"2022-09-21","cited_by_count":5},{"id":"2210.11987","title":"Joint Speech Translation and Named Entity Recognition","created":"2022-10-21","cited_by_count":5},{"id":"2309.08007","title":"DiariST: Streaming Speech Translation with Speaker Diarization","created":"2023-09-14","cited_by_count":5},{"id":"2406.00497","title":"Recent Advances in End-to-End Simultaneous Speech Translation","created":"2024-06-01","cited_by_count":5},{"id":"2406.02733","title":"Textless Acoustic Model with Self-Supervised Distillation for Noise-Robust Expressive Speech-to-Speech Translation","created":"2024-06-04","cited_by_count":5},{"id":"2406.04541","title":"Label-Synchronous Neural Transducer for E2E Simultaneous Speech Translation","created":"2024-06-06","cited_by_count":5}],"next_cursor":"100"}