{"list":"other","total":61,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2006.11477","title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","created":"2020-06-20","cited_by_count":3905},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"1804.08771","title":"A Call for Clarity in Reporting BLEU Scores","created":"2018-04-23","cited_by_count":1799},{"id":"2112.09332","title":"WebGPT: Browser-assisted question-answering with human feedback","created":"2021-12-17","cited_by_count":1745},{"id":"1912.06670","title":"Common Voice: A Massively-Multilingual Speech Corpus","created":"2019-12-13","cited_by_count":1384},{"id":"2004.04696","title":"BLEURT: Learning Robust Metrics for Text Generation","created":"2020-04-09","cited_by_count":1203},{"id":"2004.09813","title":"Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation","created":"2020-04-21","cited_by_count":593},{"id":"2205.12446","title":"FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech","created":"2022-05-25","cited_by_count":469},{"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},{"id":"1510.08484","title":"MUSAN: A Music, Speech, and Noise Corpus","created":"2015-10-28","cited_by_count":425},{"id":"1609.06773","title":"Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learning","created":"2016-09-21","cited_by_count":257},{"id":"1707.08052","title":"Challenges in Data-to-Document Generation","created":"2017-07-25","cited_by_count":226},{"id":"2010.05171","title":"fairseq S2T: Fast Speech-to-Text Modeling with fairseq","created":"2020-10-11","cited_by_count":176},{"id":"2005.10283","title":"Is MAP Decoding All You Need? The Inadequacy of the Mode in Neural Machine Translation","created":"2020-05-20","cited_by_count":138},{"id":"2303.03329","title":"End-to-End Speech Recognition: A Survey","created":"2023-03-03","cited_by_count":129},{"id":"2210.15191","title":"Truncation Sampling as Language Model Desmoothing","created":"2022-10-27","cited_by_count":123},{"id":"2111.09388","title":"High Quality Rather than High Model Probability: Minimum Bayes Risk Decoding with Neural Metrics","created":"2021-11-17","cited_by_count":104},{"id":"2311.00430","title":"Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labelling","created":"2023-11-01","cited_by_count":90},{"id":"1910.11455","title":"Recognizing long-form speech using streaming end-to-end models","created":"2019-10-24","cited_by_count":77},{"id":"2309.15649","title":"Generative Speech Recognition Error Correction with Large Language Models and Task-Activating Prompting","created":"2023-09-27","cited_by_count":72},{"id":"1803.06971","title":"What Doubling Tricks Can and Can't Do for Multi-Armed Bandits","created":"2018-03-19","cited_by_count":71},{"id":"2108.04718","title":"Sampling-Based Approximations to Minimum Bayes Risk Decoding for Neural Machine Translation","created":"2021-08-10","cited_by_count":65},{"id":"1902.07178","title":"A spelling correction model for end-to-end speech recognition","created":"2019-02-19","cited_by_count":63},{"id":"1711.00354","title":"JSUT corpus: free large-scale Japanese speech corpus for end-to-end speech synthesis","created":"2017-10-28","cited_by_count":58},{"id":"2305.09860","title":"Epsilon Sampling Rocks: Investigating Sampling Strategies for Minimum Bayes Risk Decoding for Machine Translation","created":"2023-05-17","cited_by_count":58},{"id":"2003.07962","title":"Deliberation Model Based Two-Pass End-to-End Speech Recognition","created":"2020-03-17","cited_by_count":57},{"id":"2307.04172","title":"Can Generative Large Language Models Perform ASR Error Correction?","created":"2023-07-09","cited_by_count":57},{"id":"2310.06434","title":"Whispering LLaMA: A Cross-Modal Generative Error Correction Framework for Speech Recognition","created":"2023-10-10","cited_by_count":56},{"id":"2211.07634","title":"Follow the Wisdom of the Crowd: Effective Text Generation via Minimum Bayes Risk Decoding","created":"2022-11-14","cited_by_count":54},{"id":"1910.10697","title":"Correction of Automatic Speech Recognition with Transformer Sequence-to-sequence Model","created":"2019-10-23","cited_by_count":52},{"id":"2105.03842","title":"FastCorrect: Fast Error Correction with Edit Alignment for Automatic Speech Recognition","created":"2021-05-09","cited_by_count":43},{"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":"2104.02138","title":"Semantic Distance: A New Metric for ASR Performance Analysis Towards Spoken Language Understanding","created":"2021-04-05","cited_by_count":42},{"id":"2309.15701","title":"HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models","created":"2023-09-27","cited_by_count":42},{"id":"2502.12668","title":"Evaluation of Best-of-N Sampling Strategies for Language Model Alignment","created":"2025-02-18","cited_by_count":39},{"id":"2202.01094","title":"RescoreBERT: Discriminative Speech Recognition Rescoring with BERT","created":"2022-02-02","cited_by_count":34},{"id":"2311.14919","title":"Faster Minimum Bayes Risk Decoding with Confidence-based Pruning","created":"2023-11-25","cited_by_count":34},{"id":"2401.10446","title":"Large Language Models are Efficient Learners of Noise-Robust Speech Recognition","created":"2024-01-19","cited_by_count":31},{"id":"2104.04950","title":"Innovative Bert-based Reranking Language Models for Speech Recognition","created":"2021-04-11","cited_by_count":23},{"id":"2402.05457","title":"It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition","created":"2024-02-08","cited_by_count":22},{"id":"2410.02902","title":"Better Instruction-Following Through Minimum Bayes Risk","created":"2024-10-03","cited_by_count":19},{"id":"2411.05088","title":"Findings of the IWSLT 2024 Evaluation Campaign","created":"2024-11-07","cited_by_count":19},{"id":"2411.03524","title":"Mitigating Metric Bias in Minimum Bayes Risk Decoding","created":"2024-11-05","cited_by_count":16},{"id":"2401.02749","title":"Hyperparameter-Free Approach for Faster Minimum Bayes Risk Decoding","created":"2024-01-05","cited_by_count":15},{"id":"2406.02832","title":"Efficient Minimum Bayes Risk Decoding using Low-Rank Matrix Completion Algorithms","created":"2024-06-05","cited_by_count":13},{"id":"2402.11197","title":"Centroid-Based Efficient Minimum Bayes Risk Decoding","created":"2024-02-17","cited_by_count":12},{"id":"2309.09950","title":"Investigating End-to-End ASR Architectures for Long Form Audio Transcription","created":"2023-09-18","cited_by_count":11},{"id":"2311.05263","title":"Model-Based Minimum Bayes Risk Decoding for Text Generation","created":"2023-11-09","cited_by_count":11},{"id":"2005.12143","title":"Adapting End-to-End Speech Recognition for Readable Subtitles","created":"2020-05-25","cited_by_count":10},{"id":"2306.13114","title":"A Reference-less Quality Metric for Automatic Speech Recognition via Contrastive-Learning of a Multi-Language Model with Self-Supervision","created":"2023-06-21","cited_by_count":6},{"id":"2310.07062","title":"Acoustic Model Fusion for End-to-end Speech Recognition","created":"2023-10-10","cited_by_count":6},{"id":"2409.00217","title":"ProGRes: Prompted Generative Rescoring on ASR n-Best","created":"2024-08-30","cited_by_count":6},{"id":"2502.12685","title":"Theoretical Guarantees for Minimum Bayes Risk Decoding","created":"2025-02-18","cited_by_count":3},{"id":"2404.00752","title":"On the True Distribution Approximation of Minimum Bayes-Risk Decoding","created":"2024-03-31","cited_by_count":2},{"id":"2409.16654","title":"Speech Recognition Rescoring with Large Speech-Text Foundation Models","created":"2024-09-25","cited_by_count":2},{"id":"2502.12408","title":"On the Robust Approximation of ASR Metrics","created":"2025-02-18","cited_by_count":2},{"id":"2508.05055","title":"MOVER: Combining Multiple Meeting Recognition Systems","created":"2025-08-07","cited_by_count":2}],"next_cursor":null}