{"total":150,"rows":[{"id":"2205.10643","title":"Self-Supervised Speech Representation Learning: A Review","created":"2022-05-21","cited_by_count":260,"area":null},{"id":"2205.05124","title":"Extracting Latent Steering Vectors from Pretrained Language Models","created":"2022-05-10","cited_by_count":225,"area":"mechinterp"},{"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":"2105.12397","title":"Improving Sign Language Translation with Monolingual Data by Sign Back-Translation","created":"2021-05-26","cited_by_count":179,"area":null},{"id":"2111.01690","title":"Recent Advances in End-to-End Automatic Speech Recognition","created":"2021-11-02","cited_by_count":140,"area":null},{"id":"2303.03329","title":"End-to-End Speech Recognition: A Survey","created":"2023-03-03","cited_by_count":129,"area":null},{"id":"2106.15115","title":"Neural Machine Translation for Low-Resource Languages: A Survey","created":"2021-06-29","cited_by_count":109,"area":null},{"id":"2104.02194","title":"Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion","created":"2021-04-05","cited_by_count":101,"area":null},{"id":"2109.00486","title":"Survey of Low-Resource Machine Translation","created":"2021-09-01","cited_by_count":92,"area":null},{"id":"2109.13226","title":"BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition","created":"2021-09-27","cited_by_count":88,"area":null},{"id":"2402.02992","title":"Decoding-time Realignment of Language Models","created":"2024-02-05","cited_by_count":67,"area":"alignment"},{"id":"2105.11269","title":"Neural Machine Translation with Monolingual Translation Memory","created":"2021-05-24","cited_by_count":61,"area":null},{"id":"2105.04949","title":"BERT is to NLP what AlexNet is to CV: Can Pre-Trained Language Models Identify Analogies?","created":"2021-05-11","cited_by_count":56,"area":null},{"id":"2111.03250","title":"Context-Aware Transformer Transducer for Speech Recognition","created":"2021-11-05","cited_by_count":56,"area":null},{"id":"2306.16007","title":"Prompting Large Language Models for Zero-Shot Domain Adaptation in Speech Recognition","created":"2023-06-28","cited_by_count":48,"area":null},{"id":"2104.06951","title":"Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey","created":"2021-04-14","cited_by_count":46,"area":null},{"id":"2210.03730","title":"SpeechUT: Bridging Speech and Text with Hidden-Unit for Encoder-Decoder Based Speech-Text Pre-training","created":"2022-10-07","cited_by_count":40,"area":null},{"id":"2103.08647","title":"The Effect of Domain and Diacritics in Yor\\`ub\\'a-English Neural Machine Translation","created":"2021-03-15","cited_by_count":38,"area":null},{"id":"2102.01380","title":"Internal Language Model Training for Domain-Adaptive End-to-End Speech Recognition","created":"2021-02-02","cited_by_count":37,"area":null},{"id":"2104.06678","title":"Large-Scale Self- and Semi-Supervised Learning for Speech Translation","created":"2021-04-14","cited_by_count":36,"area":null},{"id":"2105.11098","title":"Prevent the Language Model from being Overconfident in Neural Machine Translation","created":"2021-05-24","cited_by_count":34,"area":null},{"id":"2202.01094","title":"RescoreBERT: Discriminative Speech Recognition Rescoring with BERT","created":"2022-02-02","cited_by_count":34,"area":null},{"id":"2102.07594","title":"Fast End-to-End Speech Recognition via Non-Autoregressive Models and Cross-Modal Knowledge Transferring from BERT","created":"2021-02-15","cited_by_count":31,"area":null},{"id":"2105.00982","title":"On the limit of English conversational speech recognition","created":"2021-05-03","cited_by_count":30,"area":null},{"id":"2104.03006","title":"Librispeech Transducer Model with Internal Language Model Prior Correction","created":"2021-04-07","cited_by_count":26,"area":null},{"id":"2104.05544","title":"Investigating Methods to Improve Language Model Integration for Attention-based Encoder-Decoder ASR Models","created":"2021-04-12","cited_by_count":25,"area":null},{"id":"2107.12090","title":"Joint Visual Semantic Reasoning: Multi-Stage Decoder for Text Recognition","created":"2021-07-26","cited_by_count":24,"area":null},{"id":"2108.12226","title":"Injecting Text in Self-Supervised Speech Pretraining","created":"2021-08-27","cited_by_count":24,"area":null},{"id":"2206.02093","title":"LAE: Language-Aware Encoder for Monolingual and Multilingual ASR","created":"2022-06-05","cited_by_count":22,"area":null},{"id":"2303.05759","title":"An Overview on Language Models: Recent Developments and Outlook","created":"2023-03-10","cited_by_count":22,"area":null},{"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,"area":null},{"id":"2109.01396","title":"Language Modeling, Lexical Translation, Reordering: The Training Process of NMT through the Lens of Classical SMT","created":"2021-09-03","cited_by_count":21,"area":null},{"id":"2110.03618","title":"Causal Direction of Data Collection Matters: Implications of Causal and Anticausal Learning for NLP","created":"2021-10-07","cited_by_count":21,"area":null},{"id":"2106.02302","title":"Minimum Word Error Rate Training with Language Model Fusion for End-to-End Speech Recognition","created":"2021-06-04","cited_by_count":19,"area":null},{"id":"2110.05354","title":"Internal Language Model Adaptation with Text-Only Data for End-to-End Speech Recognition","created":"2021-10-06","cited_by_count":17,"area":null},{"id":"2110.06841","title":"On Language Model Integration for RNN Transducer based Speech Recognition","created":"2021-10-13","cited_by_count":17,"area":null},{"id":"2210.17049","title":"Modular Hybrid Autoregressive Transducer","created":"2022-10-31","cited_by_count":17,"area":null},{"id":"2102.07847","title":"Meta Back-translation","created":"2021-02-15","cited_by_count":16,"area":null},{"id":"2111.07393","title":"DEEP: DEnoising Entity Pre-training for Neural Machine Translation","created":"2021-11-14","cited_by_count":15,"area":null},{"id":"2204.10586","title":"Efficient Training of Neural Transducer for Speech Recognition","created":"2022-04-22","cited_by_count":14,"area":null},{"id":"2306.08133","title":"Large-scale Language Model Rescoring on Long-form Data","created":"2023-06-13","cited_by_count":14,"area":null},{"id":"2107.12081","title":"Towards the Unseen: Iterative Text Recognition by Distilling from Errors","created":"2021-07-26","cited_by_count":12,"area":null},{"id":"2203.17113","title":"Pre-Training Transformer Decoder for End-to-End ASR Model with Unpaired Speech Data","created":"2022-03-31","cited_by_count":12,"area":null},{"id":"2204.07553","title":"Improving Rare Word Recognition with LM-aware MWER Training","created":"2022-04-15","cited_by_count":12,"area":null},{"id":"2205.11116","title":"Summarize and Generate to Back-translate: Unsupervised Translation of Programming Languages","created":"2022-05-23","cited_by_count":12,"area":null},{"id":"2205.11211","title":"Non-Parametric Domain Adaptation for End-to-End Speech Translation","created":"2022-05-23","cited_by_count":12,"area":null},{"id":"2301.06735","title":"Two Stage Contextual Word Filtering for Context bias in Unified Streaming and Non-streaming Transducer","created":"2023-01-17","cited_by_count":12,"area":null},{"id":"2310.12303","title":"Document-Level Language Models for Machine Translation","created":"2023-10-18","cited_by_count":12,"area":null},{"id":"2210.16663","title":"BERT Meets CTC: New Formulation of End-to-End Speech Recognition with Pre-trained Masked Language Model","created":"2022-10-29","cited_by_count":11,"area":null},{"id":"2301.13003","title":"Knowledge Transfer from Pre-trained Language Models to Cif-based Speech Recognizers via Hierarchical Distillation","created":"2023-01-30","cited_by_count":11,"area":"distill"},{"id":"2102.01013","title":"End2End Acoustic to Semantic Transduction","created":"2021-02-01","cited_by_count":10,"area":null},{"id":"2110.02791","title":"Spell my name: keyword boosted speech recognition","created":"2021-10-06","cited_by_count":10,"area":null},{"id":"2309.13426","title":"A Chat About Boring Problems: Studying GPT-based text normalization","created":"2023-09-23","cited_by_count":10,"area":null},{"id":"2103.14152","title":"Residual Energy-Based Models for End-to-End Speech Recognition","created":"2021-03-25","cited_by_count":9,"area":null},{"id":"2201.11627","title":"Internal Language Model Estimation Through Explicit Context Vector Learning for Attention-based Encoder-decoder ASR","created":"2022-01-26","cited_by_count":9,"area":null},{"id":"2212.00500","title":"MMSpeech: Multi-modal Multi-task Encoder-Decoder Pre-training for Speech Recognition","created":"2022-11-29","cited_by_count":9,"area":null},{"id":"2302.08583","title":"JEIT: Joint End-to-End Model and Internal Language Model Training for Speech Recognition","created":"2023-02-16","cited_by_count":9,"area":null},{"id":"2310.00178","title":"Contextual Biasing with the Knuth-Morris-Pratt Matching Algorithm","created":"2023-09-29","cited_by_count":9,"area":null},{"id":"2310.10125","title":"Few-shot Action Recognition with Captioning Foundation Models","created":"2023-10-16","cited_by_count":9,"area":null},{"id":"2104.04487","title":"Language model fusion for streaming end to end speech recognition","created":"2021-04-09","cited_by_count":8,"area":null},{"id":"2111.08634","title":"NVIDIA NeMo Neural Machine Translation Systems for English-German and English-Russian News and Biomedical Tasks at WMT21","created":"2021-11-16","cited_by_count":8,"area":null},{"id":"2203.15917","title":"Shallow Fusion of Weighted Finite-State Transducer and Language Model for Text Normalization","created":"2022-03-29","cited_by_count":8,"area":null},{"id":"2205.12986","title":"Transcormer: Transformer for Sentence Scoring with Sliding Language Modeling","created":"2022-05-25","cited_by_count":8,"area":null},{"id":"2310.14534","title":"Improving Seq2Seq Grammatical Error Correction via Decoding Interventions","created":"2023-10-23","cited_by_count":8,"area":null},{"id":"2109.14934","title":"Prose2Poem: The Blessing of Transformers in Translating Prose to Persian Poetry","created":"2021-09-30","cited_by_count":7,"area":null},{"id":"2202.06045","title":"USTED: Improving ASR with a Unified Speech and Text Encoder-Decoder","created":"2022-02-12","cited_by_count":7,"area":null},{"id":"2306.06804","title":"Neural Machine Translation for the Indigenous Languages of the Americas: An Introduction","created":"2023-06-11","cited_by_count":7,"area":null},{"id":"2101.00259","title":"Code Generation from Natural Language with Less Prior and More Monolingual Data","created":"2021-01-01","cited_by_count":6,"area":null},{"id":"2104.00120","title":"Multi-Encoder Learning and Stream Fusion for Transformer-Based End-to-End Automatic Speech Recognition","created":"2021-03-31","cited_by_count":6,"area":null},{"id":"2109.01229","title":"Multimodal Conditionality for Natural Language Generation","created":"2021-09-02","cited_by_count":6,"area":null},{"id":"2201.01995","title":"Improving Mandarin End-to-End Speech Recognition with Word N-gram Language Model","created":"2022-01-06","cited_by_count":6,"area":null},{"id":"2201.11867","title":"Neural-FST Class Language Model for End-to-End Speech Recognition","created":"2022-01-28","cited_by_count":6,"area":null},{"id":"2203.02951","title":"Conditional Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation","created":"2022-03-06","cited_by_count":6,"area":null},{"id":"2207.00706","title":"UserLibri: A Dataset for ASR Personalization Using Only Text","created":"2022-07-02","cited_by_count":6,"area":null},{"id":"2310.07062","title":"Acoustic Model Fusion for End-to-end Speech Recognition","created":"2023-10-10","cited_by_count":6,"area":null},{"id":"2106.10259","title":"On-Device Personalization of Automatic Speech Recognition Models for Disordered Speech","created":"2021-06-18","cited_by_count":5,"area":null},{"id":"2110.01384","title":"Simulated annealing for optimization of graphs and sequences","created":"2021-10-01","cited_by_count":5,"area":null},{"id":"2112.08844","title":"Adapting Document-Grounded Dialog Systems to Spoken Conversations using Data Augmentation and a Noisy Channel Model","created":"2021-12-16","cited_by_count":5,"area":null},{"id":"2203.02317","title":"Adaptive Discounting of Implicit Language Models in RNN-Transducers","created":"2022-02-21","cited_by_count":5,"area":null},{"id":"2209.09735","title":"Relaxed Attention for Transformer Models","created":"2022-09-20","cited_by_count":5,"area":null},{"id":"2210.11807","title":"Is Encoder-Decoder Redundant for Neural Machine Translation?","created":"2022-10-21","cited_by_count":5,"area":null},{"id":"2211.00174","title":"Joint Audio/Text Training for Transformer Rescorer of Streaming Speech Recognition","created":"2022-10-31","cited_by_count":5,"area":null},{"id":"2306.04076","title":"Text-only Domain Adaptation using Unified Speech-Text Representation in Transducer","created":"2023-06-07","cited_by_count":5,"area":null},{"id":"2311.08306","title":"On-the-Fly Fusion of Large Language Models and Machine Translation","created":"2023-11-14","cited_by_count":5,"area":null},{"id":"2405.15216","title":"Revisiting ASR Error Correction with Specialized Models","created":"2024-05-24","cited_by_count":5,"area":null},{"id":"2107.01275","title":"Relaxed Attention: A Simple Method to Boost Performance of End-to-End Automatic Speech Recognition","created":"2021-07-02","cited_by_count":4,"area":null},{"id":"2107.01569","title":"Cross-Modal Transformer-Based Neural Correction Models for Automatic Speech Recognition","created":"2021-07-04","cited_by_count":4,"area":null},{"id":"2107.08772","title":"Integrating Unsupervised Data Generation into Self-Supervised Neural Machine Translation for Low-Resource Languages","created":"2021-07-19","cited_by_count":4,"area":null},{"id":"2107.14419","title":"USC: An Open-Source Uzbek Speech Corpus and Initial Speech Recognition Experiments","created":"2021-07-30","cited_by_count":4,"area":null},{"id":"2108.01280","title":"A Study of Multilingual End-to-End Speech Recognition for Kazakh, Russian, and English","created":"2021-08-03","cited_by_count":4,"area":null},{"id":"2108.10764","title":"Regularizing Transformers With Deep Probabilistic Layers","created":"2021-08-23","cited_by_count":4,"area":null},{"id":"2110.02267","title":"BERT Attends the Conversation: Improving Low-Resource Conversational ASR","created":"2021-10-05","cited_by_count":4,"area":null},{"id":"2205.09273","title":"Twist Decoding: Diverse Generators Guide Each Other","created":"2022-05-19","cited_by_count":4,"area":null},{"id":"2303.10942","title":"On-the-fly Text Retrieval for End-to-End ASR Adaptation","created":"2023-03-20","cited_by_count":4,"area":null},{"id":"2307.05006","title":"Improving RNN-Transducers with Acoustic LookAhead","created":"2023-07-11","cited_by_count":4,"area":null},{"id":"2308.04286","title":"Comparative Analysis of the wav2vec 2.0 Feature Extractor","created":"2023-08-08","cited_by_count":4,"area":null},{"id":"2310.13675","title":"On Synthetic Data for Back Translation","created":"2023-10-20","cited_by_count":4,"area":null},{"id":"2401.06795","title":"AI and Generative AI for Research Discovery and Summarization","created":"2024-01-08","cited_by_count":4,"area":null},{"id":"2405.14259","title":"Let's Fuse Step by Step: A Generative Fusion Decoding Algorithm with LLMs for Robust and Instruction-Aware ASR and OCR","created":"2024-05-23","cited_by_count":4,"area":null},{"id":"2105.05498","title":"Improving Lexically Constrained Neural Machine Translation with Source-Conditioned Masked Span Prediction","created":"2021-05-12","cited_by_count":3,"area":null}],"next_cursor":"100"}