{"total":172,"rows":[{"id":"2111.01690","title":"Recent Advances in End-to-End Automatic Speech Recognition","created":"2021-11-02","cited_by_count":140,"area":null},{"id":"2101.03149","title":"VisualVoice: Audio-Visual Speech Separation with Cross-Modal Consistency","created":"2021-01-08","cited_by_count":114,"area":null},{"id":"2203.06849","title":"SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities","created":"2022-03-14","cited_by_count":77,"area":null},{"id":"2203.01205","title":"Audio Self-supervised Learning: A Survey","created":"2022-03-02","cited_by_count":65,"area":null},{"id":"2211.15058","title":"Mix and Localize: Localizing Sound Sources in Mixtures","created":"2022-11-28","cited_by_count":54,"area":null},{"id":"2109.03465","title":"A Survey of Sound Source Localization with Deep Learning Methods","created":"2021-09-08","cited_by_count":46,"area":null},{"id":"2308.05037","title":"Separate Anything You Describe","created":"2023-08-09","cited_by_count":43,"area":null},{"id":"2404.09385","title":"A Large-Scale Evaluation of Speech Foundation Models","created":"2024-04-15","cited_by_count":40,"area":null},{"id":"2209.15200","title":"An efficient encoder-decoder architecture with top-down attention for speech separation","created":"2022-09-30","cited_by_count":38,"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":"2103.16776","title":"Large-Scale Pre-Training of End-to-End Multi-Talker ASR for Meeting Transcription with Single Distant Microphone","created":"2021-03-31","cited_by_count":33,"area":null},{"id":"2109.11955","title":"Visual Scene Graphs for Audio Source Separation","created":"2021-09-24","cited_by_count":29,"area":null},{"id":"2212.03814","title":"iQuery: Instruments as Queries for Audio-Visual Sound Separation","created":"2022-12-07","cited_by_count":29,"area":null},{"id":"2104.02775","title":"Looking into Your Speech: Learning Cross-modal Affinity for Audio-visual Speech Separation","created":"2021-03-25","cited_by_count":27,"area":null},{"id":"2203.17263","title":"Audio-Visual Speech Codecs: Rethinking Audio-Visual Speech Enhancement by Re-Synthesis","created":"2022-03-31","cited_by_count":24,"area":null},{"id":"2212.07065","title":"CLIPSep: Learning Text-queried Sound Separation with Noisy Unlabeled Videos","created":"2022-12-14","cited_by_count":23,"area":null},{"id":"2211.02250","title":"Real-Time Target Sound Extraction","created":"2022-11-04","cited_by_count":22,"area":null},{"id":"2202.08862","title":"RemixIT: Continual self-training of speech enhancement models via bootstrapped remixing","created":"2022-02-17","cited_by_count":20,"area":null},{"id":"2303.11329","title":"Sound Localization from Motion: Jointly Learning Sound Direction and Camera Rotation","created":"2023-03-20","cited_by_count":18,"area":null},{"id":"2409.08596","title":"Large Language Model Can Transcribe Speech in Multi-Talker Scenarios with Versatile Instructions","created":"2024-09-13","cited_by_count":17,"area":null},{"id":"2103.02644","title":"Compute and memory efficient universal sound source separation","created":"2021-03-03","cited_by_count":15,"area":null},{"id":"2107.01545","title":"Towards Neural Diarization for Unlimited Numbers of Speakers Using Global and Local Attractors","created":"2021-07-04","cited_by_count":15,"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":"2312.08079","title":"Extending Whisper with prompt tuning to target-speaker ASR","created":"2023-12-13","cited_by_count":14,"area":null},{"id":"2104.02109","title":"Streaming Multi-talker Speech Recognition with Joint Speaker Identification","created":"2021-04-05","cited_by_count":13,"area":null},{"id":"2204.03594","title":"Heterogeneous Target Speech Separation","created":"2022-04-07","cited_by_count":13,"area":null},{"id":"2302.09908","title":"A Sidecar Separator Can Convert a Single-Talker Speech Recognition System to a Multi-Talker One","created":"2023-02-20","cited_by_count":13,"area":null},{"id":"2311.01052","title":"Resilient Multiple Choice Learning: A learned scoring scheme with application to audio scene analysis","created":"2023-11-02","cited_by_count":12,"area":null},{"id":"2104.08955","title":"Many-Speakers Single Channel Speech Separation with Optimal Permutation Training","created":"2021-04-18","cited_by_count":11,"area":null},{"id":"2112.09382","title":"Discretization and Re-synthesis: an alternative method to solve the Cocktail Party Problem","created":"2021-12-17","cited_by_count":11,"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":"2308.08143","title":"IIANet: An Intra- and Inter-Modality Attention Network for Audio-Visual Speech Separation","created":"2023-08-16","cited_by_count":11,"area":null},{"id":"2407.09817","title":"Empowering Whisper as a Joint Multi-Talker and Target-Talker Speech Recognition System","created":"2024-07-13","cited_by_count":11,"area":null},{"id":"2103.00819","title":"Sandglasset: A Light Multi-Granularity Self-attentive Network For Time-Domain Speech Separation","created":"2021-03-01","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":"2308.16892","title":"ReZero: Region-customizable Sound Extraction","created":"2023-08-31","cited_by_count":10,"area":null},{"id":"2212.10744","title":"An Audio-Visual Speech Separation Model Inspired by Cortico-Thalamo-Cortical Circuits","created":"2022-12-21","cited_by_count":9,"area":null},{"id":"2401.04152","title":"Cross-Speaker Encoding Network for Multi-Talker Speech Recognition","created":"2024-01-08","cited_by_count":9,"area":null},{"id":"2101.05014","title":"Effective Low-Cost Time-Domain Audio Separation Using Globally Attentive Locally Recurrent Networks","created":"2021-01-13","cited_by_count":8,"area":null},{"id":"2210.12108","title":"Adversarial Permutation Invariant Training for Universal Sound Separation","created":"2022-10-21","cited_by_count":8,"area":null},{"id":"2308.10415","title":"TokenSplit: Using Discrete Speech Representations for Direct, Refined, and Transcript-Conditioned Speech Separation and Recognition","created":"2023-08-21","cited_by_count":8,"area":null},{"id":"2410.21269","title":"OmniSep: Unified Omni-Modality Sound Separation with Query-Mixup","created":"2024-10-28","cited_by_count":8,"area":null},{"id":"2106.03903","title":"PILOT: Introducing Transformers for Probabilistic Sound Event Localization","created":"2021-06-07","cited_by_count":7,"area":null},{"id":"2202.03875","title":"MixCycle: Unsupervised Speech Separation via Cyclic Mixture Permutation Invariant Training","created":"2022-02-08","cited_by_count":7,"area":null},{"id":"2208.13085","title":"Target Speaker Voice Activity Detection with Transformers and Its Integration with End-to-End Neural Diarization","created":"2022-08-27","cited_by_count":7,"area":null},{"id":"2211.11917","title":"Latent Iterative Refinement for Modular Source Separation","created":"2022-11-22","cited_by_count":7,"area":null},{"id":"2303.11131","title":"Cocktail HuBERT: Generalized Self-Supervised Pre-training for Mixture and Single-Source Speech","created":"2023-03-20","cited_by_count":7,"area":null},{"id":"2305.16263","title":"Unified Modeling of Multi-Talker Overlapped Speech Recognition and Diarization with a Sidecar Separator","created":"2023-05-25","cited_by_count":7,"area":null},{"id":"2409.00815","title":"Serialized Speech Information Guidance with Overlapped Encoding Separation for Multi-Speaker Automatic Speech Recognition","created":"2024-09-01","cited_by_count":7,"area":null},{"id":"2103.00417","title":"Exploiting Attention-based Sequence-to-Sequence Architectures for Sound Event Localization","created":"2021-02-28","cited_by_count":6,"area":null},{"id":"2105.12315","title":"Training Speech Enhancement Systems with Noisy Speech Datasets","created":"2021-05-26","cited_by_count":6,"area":null},{"id":"2110.10103","title":"Continual self-training with bootstrapped remixing for speech enhancement","created":"2021-10-19","cited_by_count":6,"area":null},{"id":"2310.07284","title":"Typing to Listen at the Cocktail Party: Text-Guided Target Speaker Extraction","created":"2023-10-11","cited_by_count":6,"area":null},{"id":"2402.03710","title":"Listen, Chat, and Remix: Text-Guided Soundscape Remixing for Enhanced Auditory Experience","created":"2024-02-06","cited_by_count":6,"area":null},{"id":"2103.02378","title":"Continuous Speech Separation with Ad Hoc Microphone Arrays","created":"2021-03-03","cited_by_count":5,"area":null},{"id":"2104.08450","title":"MIMO Self-attentive RNN Beamformer for Multi-speaker Speech Separation","created":"2021-04-17","cited_by_count":5,"area":null},{"id":"2105.13802","title":"DIVE: End-to-end Speech Diarization via Iterative Speaker Embedding","created":"2021-05-28","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":"2211.05172","title":"Speech separation with large-scale self-supervised learning","created":"2022-11-09","cited_by_count":5,"area":null},{"id":"2211.05927","title":"Optimal Condition Training for Target Source Separation","created":"2022-11-11","cited_by_count":5,"area":null},{"id":"2211.16028","title":"JaCappella Corpus: A Japanese a Cappella Vocal Ensemble Corpus","created":"2022-11-29","cited_by_count":5,"area":null},{"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":"2312.10305","title":"Self-Supervised Disentangled Representation Learning for Robust Target Speech Extraction","created":"2023-12-16","cited_by_count":5,"area":null},{"id":"2404.01740","title":"Weakly-supervised Audio Separation via Bi-modal Semantic Similarity","created":"2024-04-02","cited_by_count":5,"area":null},{"id":"2407.03966","title":"Serialized Output Training by Learned Dominance","created":"2024-07-04","cited_by_count":5,"area":null},{"id":"2509.04488","title":"Serialized Output Prompting for Large Language Model-based Multi-Talker Speech Recognition","created":"2025-09-01","cited_by_count":5,"area":null},{"id":"2601.06896","title":"TagSpeech: End-to-End Multi-Speaker ASR and Diarization with Fine-Grained Temporal Grounding","created":"2026-01-11","cited_by_count":5,"area":null},{"id":"2102.04945","title":"On permutation invariant training for speech source separation","created":"2021-02-09","cited_by_count":4,"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":"2107.01549","title":"Unified Autoregressive Modeling for Joint End-to-End Multi-Talker Overlapped Speech Recognition and Speaker Attribute Estimation","created":"2021-07-04","cited_by_count":4,"area":null},{"id":"2110.04791","title":"Stepwise-Refining Speech Separation Network via Fine-Grained Encoding in High-order Latent Domain","created":"2021-10-10","cited_by_count":4,"area":null},{"id":"2201.09167","title":"Mixed X-Ray Image Separation for Artworks with Concealed Designs","created":"2022-01-23","cited_by_count":4,"area":null},{"id":"2201.09592","title":"Unsupervised Music Source Separation Using Differentiable Parametric Source Models","created":"2022-01-24","cited_by_count":4,"area":null},{"id":"2207.04203","title":"Learning to Separate Voices by Spatial Regions","created":"2022-07-09","cited_by_count":4,"area":null},{"id":"2211.07951","title":"Show Me the Instruments: Musical Instrument Retrieval from Mixture Audio","created":"2022-11-15","cited_by_count":4,"area":null},{"id":"2303.07143","title":"Multi-Microphone Speaker Separation by Spatial Regions","created":"2023-03-13","cited_by_count":4,"area":null},{"id":"2306.00160","title":"Audio-Visual Speech Separation in Noisy Environments with a Lightweight Iterative Model","created":"2023-05-31","cited_by_count":4,"area":null},{"id":"2306.12173","title":"Mixture Encoder for Joint Speech Separation and Recognition","created":"2023-06-21","cited_by_count":4,"area":null},{"id":"2310.11713","title":"Separating Invisible Sounds Toward Universal Audiovisual Scene-Aware Sound Separation","created":"2023-10-18","cited_by_count":4,"area":null},{"id":"2409.00819","title":"LibriheavyMix: A 20,000-Hour Dataset for Single-Channel Reverberant Multi-Talker Speech Separation, ASR and Speaker Diarization","created":"2024-09-01","cited_by_count":4,"area":null},{"id":"2409.12388","title":"Disentangling Speakers in Multi-Talker Speech Recognition with Speaker-Aware CTC","created":"2024-09-19","cited_by_count":4,"area":null},{"id":"2505.10975","title":"Survey of End-to-End Multi-Speaker Automatic Speech Recognition for Monaural Audio","created":"2025-05-16","cited_by_count":4,"area":null},{"id":"2508.14623","title":"A Study of the Scale Invariant Signal to Distortion Ratio in Speech Separation with Noisy References","created":"2025-08-20","cited_by_count":4,"area":null},{"id":"2101.04041","title":"Evaluating Disentanglement of Structured Representations","created":"2021-01-11","cited_by_count":3,"area":null},{"id":"2103.00816","title":"Contrastive Separative Coding for Self-supervised Representation Learning","created":"2021-03-01","cited_by_count":3,"area":null},{"id":"2106.07016","title":"WASE: Learning When to Attend for Speaker Extraction in Cocktail Party Environments","created":"2021-06-13","cited_by_count":3,"area":null},{"id":"2111.00316","title":"Real-time Speaker counting in a cocktail party scenario using Attention-guided Convolutional Neural Network","created":"2021-10-30","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":"2210.14536","title":"Position tracking of a varying number of sound sources with sliding permutation invariant training","created":"2022-10-26","cited_by_count":3,"area":null},{"id":"2211.04304","title":"BER: Balanced Error Rate For Speaker Diarization","created":"2022-11-08","cited_by_count":3,"area":null},{"id":"2211.07302","title":"MedleyVox: An Evaluation Dataset for Multiple Singing Voices Separation","created":"2022-11-14","cited_by_count":3,"area":null},{"id":"2212.00369","title":"Deep neural network techniques for monaural speech enhancement: state of the art analysis","created":"2022-12-01","cited_by_count":3,"area":null},{"id":"2303.06806","title":"Neural Diarization with Non-autoregressive Intermediate Attractors","created":"2023-03-13","cited_by_count":3,"area":null},{"id":"2305.00926","title":"Joint Modelling of Spoken Language Understanding Tasks with Integrated Dialog History","created":"2023-05-01","cited_by_count":3,"area":null},{"id":"2308.04169","title":"Dual input neural networks for positional sound source localization","created":"2023-08-08","cited_by_count":3,"area":null},{"id":"2408.16126","title":"Improving Generalization of Speech Separation in Real-World Scenarios: Strategies in Simulation, Optimization, and Evaluation","created":"2024-08-28","cited_by_count":3,"area":null},{"id":"2411.18497","title":"Multiple Choice Learning for Efficient Speech Separation with Many Speakers","created":"2024-11-27","cited_by_count":3,"area":null},{"id":"2505.08694","title":"A Survey of Deep Learning for Complex Speech Spectrograms","created":"2025-05-13","cited_by_count":3,"area":null},{"id":"2605.05866","title":"XDecomposer: Learning Prior-Free Set Decomposition for Multiphase X-ray Diffraction","created":"2026-05-07","cited_by_count":3,"area":null},{"id":"2103.01461","title":"Tune-In: Training Under Negative Environments with Interference for Attention Networks Simulating Cocktail Party Effect","created":"2021-03-02","cited_by_count":2,"area":null}],"next_cursor":"100"}