{"total":77,"rows":[{"id":"2110.13900","title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","created":"2021-10-26","cited_by_count":1657,"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":"2107.08661","title":"Translatotron 2: High-quality direct speech-to-speech translation with voice preservation","created":"2021-07-19","cited_by_count":71,"area":null},{"id":"2109.07513","title":"Tied & Reduced RNN-T Decoder","created":"2021-09-15","cited_by_count":36,"area":null},{"id":"2109.06952","title":"Residual Adapters for Parameter-Efficient ASR Adaptation to Atypical and Accented Speech","created":"2021-09-14","cited_by_count":31,"area":null},{"id":"2101.11577","title":"Transformer Based Deliberation for Two-Pass Speech Recognition","created":"2021-01-27","cited_by_count":29,"area":null},{"id":"2110.00165","title":"Large-scale ASR Domain Adaptation using Self- and Semi-supervised Learning","created":"2021-10-01","cited_by_count":26,"area":null},{"id":"2104.09426","title":"Advanced Long-context End-to-end Speech Recognition Using Context-expanded Transformers","created":"2021-04-19","cited_by_count":25,"area":null},{"id":"2203.12668","title":"Pseudo Label Is Better Than Human Label","created":"2022-03-22","cited_by_count":25,"area":null},{"id":"2203.15952","title":"4-bit Conformer with Native Quantization Aware Training for Speech Recognition","created":"2022-03-29","cited_by_count":24,"area":null},{"id":"2210.07353","title":"JOIST: A Joint Speech and Text Streaming Model For ASR","created":"2022-10-13","cited_by_count":24,"area":null},{"id":"2404.09173","title":"TransformerFAM: Feedback attention is working memory","created":"2024-04-14","cited_by_count":22,"area":null},{"id":"2404.10690","title":"MathWriting: A Dataset For Handwritten Mathematical Expression Recognition","created":"2024-04-16","cited_by_count":21,"area":null},{"id":"2309.07414","title":"PromptASR for contextualized ASR with controllable style","created":"2023-09-14","cited_by_count":19,"area":null},{"id":"2204.10749","title":"E2E Segmenter: Joint Segmenting and Decoding for Long-Form ASR","created":"2022-04-22","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":"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":"2306.16009","title":"Accelerating Transducers through Adjacent Token Merging","created":"2023-06-28","cited_by_count":15,"area":"inference"},{"id":"2110.04612","title":"Personalized Automatic Speech Recognition Trained on Small Disordered Speech Datasets","created":"2021-10-09","cited_by_count":14,"area":null},{"id":"2110.05607","title":"Partial Variable Training for Efficient On-Device Federated Learning","created":"2021-10-11","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":"2112.11442","title":"Deliberation of Streaming RNN-Transducer by Non-autoregressive Decoding","created":"2021-12-01","cited_by_count":13,"area":null},{"id":"2302.01496","title":"Efficient Domain Adaptation for Speech Foundation Models","created":"2023-02-03","cited_by_count":13,"area":null},{"id":"2110.03634","title":"Enabling On-Device Training of Speech Recognition Models with Federated Dropout","created":"2021-10-07","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":"2204.06164","title":"A Unified Cascaded Encoder ASR Model for Dynamic Model Sizes","created":"2022-04-13","cited_by_count":11,"area":null},{"id":"2506.17525","title":"Data Quality Issues in Multilingual Speech Datasets: The Need for Sociolinguistic Awareness and Proactive Language Planning","created":"2025-06-21","cited_by_count":11,"area":null},{"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,"area":null},{"id":"2203.05008","title":"Sentence-Select: Large-Scale Language Model Data Selection for Rare-Word Speech Recognition","created":"2022-03-09","cited_by_count":10,"area":null},{"id":"2206.14716","title":"Improving Deliberation by Text-Only and Semi-Supervised Training","created":"2022-06-29","cited_by_count":10,"area":null},{"id":"2210.05793","title":"Comparison of Soft and Hard Target RNN-T Distillation for Large-scale ASR","created":"2022-10-11","cited_by_count":10,"area":"distill"},{"id":"2306.04530","title":"Lenient Evaluation of Japanese Speech Recognition: Modeling Naturally Occurring Spelling Inconsistency","created":"2023-06-07","cited_by_count":10,"area":null},{"id":"2309.15013","title":"Updated Corpora and Benchmarks for Long-Form Speech Recognition","created":"2023-09-26","cited_by_count":10,"area":null},{"id":"2104.04552","title":"Lookup-Table Recurrent Language Models for Long Tail Speech Recognition","created":"2021-04-09","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":"2104.13970","title":"Personalized Keyphrase Detection using Speaker and Environment Information","created":"2021-04-28","cited_by_count":8,"area":null},{"id":"2209.06359","title":"Federated Pruning: Improving Neural Network Efficiency with Federated Learning","created":"2022-09-14","cited_by_count":8,"area":null},{"id":"2101.01853","title":"Hypothesis Stitcher for End-to-End Speaker-attributed ASR on Long-form Multi-talker Recordings","created":"2021-01-06","cited_by_count":7,"area":null},{"id":"2203.12906","title":"Lahjoita puhetta -- a large-scale corpus of spoken Finnish with some benchmarks","created":"2022-03-24","cited_by_count":7,"area":null},{"id":"2205.03494","title":"Online Model Compression for Federated Learning with Large Models","created":"2022-05-06","cited_by_count":7,"area":null},{"id":"2309.08436","title":"Chunked Attention-based Encoder-Decoder Model for Streaming Speech Recognition","created":"2023-09-15","cited_by_count":7,"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":"2202.12163","title":"Attentive Temporal Pooling for Conformer-based Streaming Language Identification in Long-form Speech","created":"2022-02-24","cited_by_count":6,"area":null},{"id":"2211.09412","title":"LongFNT: Long-form Speech Recognition with Factorized Neural Transducer","created":"2022-11-17","cited_by_count":6,"area":null},{"id":"2107.03985","title":"Comparing Supervised Models And Learned Speech Representations For Classifying Intelligibility Of Disordered Speech On Selected Phrases","created":"2021-07-08","cited_by_count":5,"area":null},{"id":"2201.03655","title":"A Likelihood Ratio based Domain Adaptation Method for E2E Models","created":"2022-01-10","cited_by_count":5,"area":null},{"id":"2107.01201","title":"Multi-user VoiceFilter-Lite via Attentive Speaker Embedding","created":"2021-07-02","cited_by_count":4,"area":null},{"id":"2210.14742","title":"Monotonic segmental attention for automatic speech recognition","created":"2022-10-26","cited_by_count":4,"area":null},{"id":"2307.08217","title":"BASS: Block-wise Adaptation for Speech Summarization","created":"2023-07-17","cited_by_count":4,"area":null},{"id":"2309.09996","title":"Improving Speech Recognition for African American English With Audio Classification","created":"2023-09-16","cited_by_count":4,"area":null},{"id":"2104.14346","title":"Bridging the gap between streaming and non-streaming ASR systems bydistilling ensembles of CTC and RNN-T models","created":"2021-04-25","cited_by_count":3,"area":null},{"id":"2110.00155","title":"Incremental Layer-wise Self-Supervised Learning for Efficient Speech Domain Adaptation On Device","created":"2021-10-01","cited_by_count":3,"area":null},{"id":"2210.14446","title":"Smart Speech Segmentation using Acousto-Linguistic Features with look-ahead","created":"2022-10-26","cited_by_count":3,"area":null},{"id":"2210.15876","title":"Random Utterance Concatenation Based Data Augmentation for Improving Short-video Speech Recognition","created":"2022-10-28","cited_by_count":3,"area":null},{"id":"2211.15432","title":"E2E Segmentation in a Two-Pass Cascaded Encoder ASR Model","created":"2022-11-28","cited_by_count":3,"area":null},{"id":"2304.00173","title":"Lego-Features: Exporting modular encoder features for streaming and deliberation ASR","created":"2023-03-31","cited_by_count":3,"area":null},{"id":"2308.07393","title":"Using Text Injection to Improve Recognition of Personal Identifiers in Speech","created":"2023-08-14","cited_by_count":3,"area":null},{"id":"2310.11141","title":"Long-form Simultaneous Speech Translation: Thesis Proposal","created":"2023-10-17","cited_by_count":3,"area":null},{"id":"2107.04677","title":"Noisy Training Improves E2E ASR for the Edge","created":"2021-07-09","cited_by_count":2,"area":null},{"id":"2310.00141","title":"The Gift of Feedback: Improving ASR Model Quality by Learning from User Corrections through Federated Learning","created":"2023-09-29","cited_by_count":2,"area":null},{"id":"2311.17786","title":"DSS: Synthesizing long Digital Ink using Data augmentation, Style encoding and Split generation","created":"2023-11-29","cited_by_count":2,"area":null},{"id":"2312.11123","title":"Improved Long-Form Speech Recognition by Jointly Modeling the Primary and Non-primary Speakers","created":"2023-12-18","cited_by_count":2,"area":null},{"id":"2510.19471","title":"Re-evaluating Minimum Bayes Risk Decoding for Automatic Speech Recognition","created":"2025-10-22","cited_by_count":2,"area":null},{"id":"2606.07473","title":"Whisper Hallucination Detection and Mitigation via Hidden Representation Steering and Sparse AutoEncoders","created":"2026-06-05","cited_by_count":2,"area":"mechinterp"},{"id":"2107.07509","title":"VAD-free Streaming Hybrid CTC/Attention ASR for Unsegmented Recording","created":"2021-07-15","cited_by_count":1,"area":null},{"id":"2110.04267","title":"Exploring Heterogeneous Characteristics of Layers in ASR Models for More Efficient Training","created":"2021-10-08","cited_by_count":1,"area":null},{"id":"2204.07556","title":"Streaming Align-Refine for Non-autoregressive Deliberation","created":"2022-04-15","cited_by_count":1,"area":null},{"id":"2303.15293","title":"A Deliberation-based Joint Acoustic and Text Decoder","created":"2023-03-23","cited_by_count":1,"area":null},{"id":"2304.00171","title":"Practical Conformer: Optimizing size, speed and flops of Conformer for on-Device and cloud ASR","created":"2023-03-31","cited_by_count":1,"area":null},{"id":"2308.07395","title":"Text Injection for Capitalization and Turn-Taking Prediction in Speech Models","created":"2023-08-14","cited_by_count":1,"area":null},{"id":"2306.01789","title":"Edit Distance based RL for RNNT decoding","created":"2023-05-31","cited_by_count":0,"area":null},{"id":"2308.07486","title":"O-1: Self-training with Oracle and 1-best Hypothesis","created":"2023-08-14","cited_by_count":0,"area":null},{"id":"2309.13029","title":"Memory-augmented conformer for improved end-to-end long-form ASR","created":"2023-09-22","cited_by_count":0,"area":null},{"id":"2312.09463","title":"Partial Rewriting for Multi-Stage ASR","created":"2023-12-08","cited_by_count":0,"area":null},{"id":"2408.10443","title":"Federated Learning of Large ASR Models in the Real World","created":"2024-08-19","cited_by_count":0,"area":null},{"id":"2506.06117","title":"Phonetically-Augmented Discriminative Rescoring for Voice Search Error Correction","created":"2025-06-06","cited_by_count":0,"area":null},{"id":"2607.29363","title":"Stable Autoregressive Speech Generation with Low-Frame-Rate High-Dimensional Continuous Tokens","created":"2026-07-31","cited_by_count":0,"area":null}],"next_cursor":null}