{"total":92,"rows":[{"id":"2205.10643","title":"Self-Supervised Speech Representation Learning: A Review","created":"2022-05-21","cited_by_count":260,"area":null},{"id":"2410.17196","title":"VoiceBench: Benchmarking LLM-Based Voice Assistants","created":"2024-10-22","cited_by_count":200,"area":null},{"id":"2101.09624","title":"A Review of Speaker Diarization: Recent Advances with Deep Learning","created":"2021-01-24","cited_by_count":124,"area":null},{"id":"2202.00842","title":"Streaming Multi-Talker ASR with Token-Level Serialized Output Training","created":"2022-02-02","cited_by_count":37,"area":null},{"id":"2211.02397","title":"Analysing Diffusion-based Generative Approaches versus Discriminative Approaches for Speech Restoration","created":"2022-11-04","cited_by_count":34,"area":"diffusion"},{"id":"2107.04174","title":"EasyCom: An Augmented Reality Dataset to Support Algorithms for Easy Communication in Noisy Environments","created":"2021-07-09","cited_by_count":31,"area":null},{"id":"2302.14748","title":"Reducing the Prior Mismatch of Stochastic Differential Equations for Diffusion-based Speech Enhancement","created":"2023-02-28","cited_by_count":30,"area":"diffusion"},{"id":"2306.13734","title":"The CHiME-7 DASR Challenge: Distant Meeting Transcription with Multiple Devices in Diverse Scenarios","created":"2023-06-23","cited_by_count":22,"area":null},{"id":"2401.08887","title":"NOTSOFAR-1 Challenge: New Datasets, Baseline, and Tasks for Distant Meeting Transcription","created":"2024-01-16","cited_by_count":21,"area":null},{"id":"2403.07937","title":"Speech Robust Bench: A Robustness Benchmark For Speech Recognition","created":"2024-03-08","cited_by_count":21,"area":null},{"id":"2201.10207","title":"SPIRAL: Self-supervised Perturbation-Invariant Representation Learning for Speech Pre-Training","created":"2022-01-25","cited_by_count":19,"area":"distill"},{"id":"2102.03951","title":"End-to-End Multi-Channel Transformer for Speech Recognition","created":"2021-02-08","cited_by_count":17,"area":null},{"id":"2203.16104","title":"Improving Distortion Robustness of Self-supervised Speech Processing Tasks with Domain Adaptation","created":"2022-03-30","cited_by_count":17,"area":null},{"id":"2409.06656","title":"Sortformer: A Novel Approach for Permutation-Resolved Speaker Supervision in Speech-to-Text Systems","created":"2024-09-10","cited_by_count":15,"area":null},{"id":"2110.08583","title":"ASR4REAL: An extended benchmark for speech models","created":"2021-10-16","cited_by_count":14,"area":null},{"id":"2203.16685","title":"Streaming Speaker-Attributed ASR with Token-Level Speaker Embeddings","created":"2022-03-30","cited_by_count":14,"area":null},{"id":"2206.13310","title":"Insights Into Deep Non-linear Filters for Improved Multi-channel Speech Enhancement","created":"2022-06-27","cited_by_count":14,"area":null},{"id":"2212.09006","title":"A Review of Speech-centric Trustworthy Machine Learning: Privacy, Safety, and Fairness","created":"2022-12-18","cited_by_count":13,"area":null},{"id":"2310.01688","title":"One model to rule them all ? Towards End-to-End Joint Speaker Diarization and Speech Recognition","created":"2023-10-02","cited_by_count":12,"area":null},{"id":"2305.18747","title":"Adapting Multi-Lingual ASR Models for Handling Multiple Talkers","created":"2023-05-30","cited_by_count":11,"area":null},{"id":"2106.08468","title":"RyanSpeech: A Corpus for Conversational Text-to-Speech Synthesis","created":"2021-06-15","cited_by_count":10,"area":null},{"id":"2107.02852","title":"A Comparative Study of Modular and Joint Approaches for Speaker-Attributed ASR on Monaural Long-Form Audio","created":"2021-07-06","cited_by_count":10,"area":null},{"id":"2112.10200","title":"Multi-turn RNN-T for streaming recognition of multi-party speech","created":"2021-12-19","cited_by_count":10,"area":null},{"id":"2106.07843","title":"Teacher-Student MixIT for Unsupervised and Semi-supervised Speech Separation","created":"2021-06-15","cited_by_count":9,"area":"distill"},{"id":"2108.13048","title":"ASR-GLUE: A New Multi-task Benchmark for ASR-Robust Natural Language Understanding","created":"2021-08-30","cited_by_count":9,"area":null},{"id":"2307.15493","title":"The timing bottleneck: Why timing and overlap are mission-critical for conversational user interfaces, speech recognition and dialogue systems","created":"2023-07-28","cited_by_count":9,"area":null},{"id":"2505.19314","title":"SoloSpeech: Enhancing Intelligibility and Quality in Target Speech Extraction through a Cascaded Generative Pipeline","created":"2025-05-25","cited_by_count":9,"area":null},{"id":"2108.12953","title":"Multi-Channel Transformer Transducer for Speech Recognition","created":"2021-08-30","cited_by_count":8,"area":null},{"id":"2206.02432","title":"Online Neural Diarization of Unlimited Numbers of Speakers Using Global and Local Attractors","created":"2022-06-06","cited_by_count":8,"area":null},{"id":"2204.11232","title":"Improving the Naturalness of Simulated Conversations for End-to-End Neural Diarization","created":"2022-04-24","cited_by_count":7,"area":null},{"id":"2210.07978","title":"Improving generalizability of distilled self-supervised speech processing models under distorted settings","created":"2022-10-14","cited_by_count":7,"area":null},{"id":"2305.13796","title":"SE-Bridge: Speech Enhancement with Consistent Brownian Bridge","created":"2023-05-23","cited_by_count":7,"area":"diffusion"},{"id":"2502.13645","title":"Measuring the Effect of Transcription Noise on Downstream Language Understanding Tasks","created":"2025-02-19","cited_by_count":7,"area":null},{"id":"2608.25218","title":"TurnBench: A Multi-Domain Benchmark for Turn-Taking Dynamics in Spoken Dialogue","created":"2026-08-25","cited_by_count":7,"area":null},{"id":"2203.00725","title":"A Conformer Based Acoustic Model for Robust Automatic Speech Recognition","created":"2022-03-01","cited_by_count":6,"area":null},{"id":"2306.03014","title":"On the Behavior of Intrusive and Non-intrusive Speech Enhancement Metrics in Predictive and Generative Settings","created":"2023-06-05","cited_by_count":6,"area":null},{"id":"2102.09666","title":"Dynamic curriculum learning via data parameters for noise robust keyword spotting","created":"2021-02-18","cited_by_count":5,"area":null},{"id":"2112.05863","title":"Directed Speech Separation for Automatic Speech Recognition of Long Form Conversational Speech","created":"2021-12-10","cited_by_count":5,"area":null},{"id":"2203.12369","title":"MetricGAN+/-: Increasing Robustness of Noise Reduction on Unseen Data","created":"2022-03-23","cited_by_count":5,"area":null},{"id":"2203.16834","title":"A Comparative Study on Speaker-attributed Automatic Speech Recognition in Multi-party Meetings","created":"2022-03-31","cited_by_count":5,"area":null},{"id":"2304.11408","title":"Lightweight Toxicity Detection in Spoken Language: A Transformer-based Approach for Edge Devices","created":"2023-04-22","cited_by_count":5,"area":"distill"},{"id":"2305.13716","title":"BA-SOT: Boundary-Aware Serialized Output Training for Multi-Talker ASR","created":"2023-05-23","cited_by_count":5,"area":null},{"id":"2505.00059","title":"BERSting at the Screams: A Benchmark for Distanced, Emotional and Shouted Speech Recognition","created":"2025-04-30","cited_by_count":5,"area":null},{"id":"2107.08273","title":"STRODE: Stochastic Boundary Ordinary Differential Equation","created":"2021-07-17","cited_by_count":4,"area":null},{"id":"2203.02288","title":"Integrating Statistical Uncertainty into Neural Network-Based Speech Enhancement","created":"2022-03-04","cited_by_count":4,"area":null},{"id":"2311.12564","title":"Summary of the DISPLACE Challenge 2023 - DIarization of SPeaker and LAnguage in Conversational Environments","created":"2023-11-21","cited_by_count":4,"area":null},{"id":"2505.14517","title":"Steering Deep Non-Linear Spatially Selective Filters for Weakly Guided Extraction of Moving Speakers in Dynamic Scenarios","created":"2025-05-20","cited_by_count":4,"area":null},{"id":"2510.23276","title":"A Cocktail-Party Benchmark: Multi-Modal dataset and Comparative Evaluation Results","created":"2025-10-27","cited_by_count":4,"area":null},{"id":"2604.15037","title":"From Reactive to Proactive: Assessing the Proactivity of Voice Agents via ProVoice-Bench","created":"2026-04-16","cited_by_count":4,"area":"agents"},{"id":"2111.06458","title":"MultiSV: Dataset for Far-Field Multi-Channel Speaker Verification","created":"2021-11-11","cited_by_count":3,"area":null},{"id":"2205.05199","title":"Separator-Transducer-Segmenter: Streaming Recognition and Segmentation of Multi-party Speech","created":"2022-05-10","cited_by_count":3,"area":null},{"id":"2305.15971","title":"Knowledge Distillation for Neural Transducer-based Target-Speaker ASR: Exploiting Parallel Mixture/Single-Talker Speech Data","created":"2023-05-25","cited_by_count":3,"area":"distill"},{"id":"2506.11074","title":"Challenges in Automated Processing of Speech from Child Wearables: The Case of Voice Type Classifier","created":"2025-06-04","cited_by_count":3,"area":null},{"id":"2510.12827","title":"Automatic Speech Recognition in the Modern Era: Architectures, Training, and Evaluation","created":"2025-10-11","cited_by_count":3,"area":null},{"id":"2111.00320","title":"Speaker conditioning of acoustic models using affine transformation for multi-speaker speech recognition","created":"2021-10-30","cited_by_count":2,"area":null},{"id":"2112.09060","title":"Towards Robust Real-time Audio-Visual Speech Enhancement","created":"2021-12-16","cited_by_count":2,"area":null},{"id":"2203.09767","title":"Speaker Embedding-aware Neural Diarization: an Efficient Framework for Overlapping Speech Diarization in Meeting Scenarios","created":"2022-03-18","cited_by_count":2,"area":null},{"id":"2304.07142","title":"On Data Sampling Strategies for Training Neural Network Speech Separation Models","created":"2023-04-14","cited_by_count":2,"area":null},{"id":"2307.13012","title":"Joint speech and overlap detection: a benchmark over multiple audio setup and speech domains","created":"2023-07-24","cited_by_count":2,"area":null},{"id":"2308.11380","title":"Convoifilter: A case study of doing cocktail party speech recognition","created":"2023-08-22","cited_by_count":2,"area":null},{"id":"2501.17304","title":"Summary of the NOTSOFAR-1 Challenge: Highlights and Learnings","created":"2025-01-28","cited_by_count":2,"area":null},{"id":"2507.02791","title":"Self-Steering Deep Non-Linear Spatially Selective Filters for Efficient Extraction of Moving Speakers under Weak Guidance","created":"2025-07-03","cited_by_count":2,"area":null},{"id":"2507.18161","title":"Recent Trends in Distant Conversational Speech Recognition: A Review of CHiME-7 and 8 DASR Challenges","created":"2025-07-24","cited_by_count":2,"area":null},{"id":"2601.12345","title":"Adaptive Rotary Steering with Joint Autoregression for Robust Extraction of Closely Moving Speakers in Dynamic Scenarios","created":"2026-01-18","cited_by_count":2,"area":null},{"id":"2604.13776","title":"Who Gets Flagged? The Pluralistic Evaluation Gap in AI Content Watermarking","created":"2026-04-15","cited_by_count":2,"area":"safety"},{"id":"2111.13694","title":"Speaker Embedding-aware Neural Diarization for Flexible Number of Speakers with Textual Information","created":"2021-11-28","cited_by_count":1,"area":null},{"id":"2112.12522","title":"Multi-Variant Consistency based Self-supervised Learning for Robust Automatic Speech Recognition","created":"2021-12-23","cited_by_count":1,"area":null},{"id":"2202.05756","title":"A Novel Speech Intelligibility Enhancement Model based on CanonicalCorrelation and Deep Learning","created":"2022-02-11","cited_by_count":1,"area":null},{"id":"2204.00218","title":"End-to-End Multi-speaker ASR with Independent Vector Analysis","created":"2022-04-01","cited_by_count":1,"area":null},{"id":"2205.01751","title":"On monoaural speech enhancement for automatic recognition of real noisy speech using mixture invariant training","created":"2022-05-03","cited_by_count":1,"area":null},{"id":"2210.15368","title":"A Training and Inference Strategy Using Noisy and Enhanced Speech as Target for Speech Enhancement without Clean Speech","created":"2022-10-27","cited_by_count":1,"area":null},{"id":"2303.00510","title":"A Comparison of Speech Data Augmentation Methods Using S3PRL Toolkit","created":"2023-02-27","cited_by_count":1,"area":null},{"id":"2306.04054","title":"RescueSpeech: A German Corpus for Speech Recognition in Search and Rescue Domain","created":"2023-06-06","cited_by_count":1,"area":null},{"id":"2503.23848","title":"SpeechDialogueFactory: Generating High-Quality Speech Dialogue Data to Accelerate Your Speech-LLM Development","created":"2025-03-31","cited_by_count":1,"area":null},{"id":"2506.11344","title":"Do We Still Need Audio? Rethinking Speaker Diarization with a Text-Based Approach Using Multiple Prediction Models","created":"2025-06-12","cited_by_count":1,"area":null},{"id":"2509.18722","title":"LOTUSDIS: A Thai far-field meeting corpus for robust conversational ASR","created":"2025-09-23","cited_by_count":1,"area":null},{"id":"2601.19949","title":"RIR-Mega-Speech: A Reverberant Speech Corpus with Comprehensive Acoustic Metadata and Reproducible Evaluation","created":"2026-01-25","cited_by_count":1,"area":null},{"id":"2602.12783","title":"SQuTR: A Robustness Benchmark for Spoken Query to Text Retrieval under Acoustic Noise","created":"2026-02-13","cited_by_count":1,"area":null},{"id":"2603.12046","title":"Dr. SHAP-AV: Decoding Relative Modality Contributions via Shapley Attribution in Audio-Visual Speech Recognition","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2603.23723","title":"Autoregressive Guidance of Deep Spatially Selective Filters using Bayesian Tracking for Efficient Extraction of Moving Speakers","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"2101.04315","title":"Neural Network-based Virtual Microphone Estimator","created":"2021-01-12","cited_by_count":0,"area":null},{"id":"2103.07125","title":"Learning spectro-temporal representations of complex sounds with parameterized neural networks","created":"2021-03-12","cited_by_count":0,"area":null},{"id":"2103.13443","title":"Blind Speech Separation and Dereverberation using Neural Beamforming","created":"2021-03-24","cited_by_count":0,"area":null},{"id":"2111.00009","title":"Revisiting joint decoding based multi-talker speech recognition with DNN acoustic model","created":"2021-10-31","cited_by_count":0,"area":null},{"id":"2207.07273","title":"Direction-Aware Joint Adaptation of Neural Speech Enhancement and Recognition in Real Multiparty Conversational Environments","created":"2022-07-15","cited_by_count":0,"area":null},{"id":"2312.12764","title":"Lattice Rescoring Based on Large Ensemble of Complementary Neural Language Models","created":"2023-12-20","cited_by_count":0,"area":null},{"id":"2402.01413","title":"Objective and subjective evaluation of speech enhancement methods in the UDASE task of the 7th CHiME challenge","created":"2024-02-02","cited_by_count":0,"area":null},{"id":"2406.06438","title":"Multimodal Contextualized Semantic Parsing from Speech","created":"2024-06-10","cited_by_count":0,"area":null},{"id":"2601.18037","title":"SpatialEmb: Extract and Encode Spatial Information for 1-Stage Multi-channel Multi-speaker ASR on Arbitrary Microphone Arrays","created":"2026-01-25","cited_by_count":0,"area":null},{"id":"2607.08371","title":"On the Role of Conversational Timing in Synthetic Training Data for ASR","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2608.09288","title":"DAVE: A Decoupled Audio-Visual Enhancement Framework for Real-World Speech Separation","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.38897","title":"FFASR: Benchmarking Far-Field Automatic Speech Recognition using High-Fidelity Simulated RIRs","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}