{"total":35,"rows":[{"id":"2206.08312","title":"SoundSpaces 2.0: A Simulation Platform for Visual-Acoustic Learning","created":"2022-06-16","cited_by_count":95,"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":"2110.04057","title":"FAST-RIR: Fast neural diffuse room impulse response generator","created":"2021-10-07","cited_by_count":35,"area":null},{"id":"2106.07732","title":"Learning Audio-Visual Dereverberation","created":"2021-06-14","cited_by_count":26,"area":null},{"id":"2205.09248","title":"MESH2IR: Neural Acoustic Impulse Response Generator for Complex 3D Scenes","created":"2022-05-18","cited_by_count":23,"area":null},{"id":"2202.03416","title":"Deep Impulse Responses: Estimating and Parameterizing Filters with Deep Networks","created":"2022-02-07","cited_by_count":20,"area":null},{"id":"2105.09022","title":"Attack on practical speaker verification system using universal adversarial perturbations","created":"2021-05-19","cited_by_count":18,"area":null},{"id":"2308.12370","title":"AdVerb: Visually Guided Audio Dereverberation","created":"2023-08-23","cited_by_count":15,"area":null},{"id":"2305.07499","title":"Device-Robust Acoustic Scene Classification via Impulse Response Augmentation","created":"2023-05-12","cited_by_count":11,"area":null},{"id":"2211.04473","title":"Towards Improved Room Impulse Response Estimation for Speech Recognition","created":"2022-11-08","cited_by_count":9,"area":null},{"id":"2308.09514","title":"Spatial LibriSpeech: An Augmented Dataset for Spatial Audio Learning","created":"2023-08-18","cited_by_count":7,"area":null},{"id":"2303.07449","title":"Blind Acoustic Room Parameter Estimation Using Phase Features","created":"2023-03-13","cited_by_count":3,"area":null},{"id":"2405.19497","title":"Gaussian Flow Bridges for Audio Domain Transfer with Unpaired Data","created":"2024-05-29","cited_by_count":3,"area":null},{"id":"2507.09750","title":"MB-RIRs: a Synthetic Room Impulse Response Dataset with Frequency-Dependent Absorption Coefficients","created":"2025-07-13","cited_by_count":3,"area":null},{"id":"2202.07219","title":"Multi-style Training for South African Call Centre Audio","created":"2022-02-15","cited_by_count":2,"area":null},{"id":"2212.05360","title":"Synthetic Wave-Geometric Impulse Responses for Improved Speech Dereverberation","created":"2022-12-10","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":"2510.23141","title":"Treble10: A high-quality dataset for far-field speech recognition, dereverberation, and enhancement","created":"2025-10-27","cited_by_count":2,"area":null},{"id":"2210.00721","title":"Efficient acoustic feature transformation in mismatched environments using a Guided-GAN","created":"2022-10-03","cited_by_count":1,"area":null},{"id":"2409.18971","title":"Early Joint Learning of Emotion Information Makes MultiModal Model Understand You Better","created":"2024-09-12","cited_by_count":1,"area":null},{"id":"2510.23320","title":"LibriConvo: Simulating Conversations from Read Literature for ASR and Diarization","created":"2025-10-27","cited_by_count":1,"area":null},{"id":"2511.06458","title":"EchoMark: Perceptual Acoustic Environment Transfer with Watermark-Embedded Room Impulse Response","created":"2025-11-09","cited_by_count":1,"area":null},{"id":"2512.22148","title":"Rethinking Leveraging Pre-Trained Multi-Layer Representations for Speaker Verification","created":"2025-12-15","cited_by_count":1,"area":null},{"id":"2603.21684","title":"LipsAM: Lipschitz-Continuous Amplitude Modifier for Audio Signal Processing and its Application to Plug-and-Play Dereverberation","created":"2026-03-23","cited_by_count":1,"area":null},{"id":"2606.29031","title":"How to Leverage Synthetic Speech for LLM-Based ASR Systems?","created":"2026-06-27","cited_by_count":1,"area":null},{"id":"2203.13259","title":"Computing Optimal Location of Microphone for Improved Speech Recognition","created":"2022-03-24","cited_by_count":0,"area":null},{"id":"2205.07086","title":"Collar-aware Training for Streaming Speaker Change Detection in Broadcast Speech","created":"2022-05-14","cited_by_count":0,"area":null},{"id":"2206.15432","title":"Challenges and Opportunities in Multi-device Speech Processing","created":"2022-06-27","cited_by_count":0,"area":null},{"id":"2303.16621","title":"AraSpot: Arabic Spoken Command Spotting","created":"2023-03-29","cited_by_count":0,"area":null},{"id":"2510.00582","title":"SAGE-LD: Towards Scalable and Generalizable End-to-End Language Diarization via Simulated Data Augmentation","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2511.01773","title":"ADNAC: Audio Denoiser using Neural Audio Codec","created":"2025-11-03","cited_by_count":0,"area":null},{"id":"2606.24066","title":"VieSpeaker: A Large-Scale Vietnamese Speaker Recognition Dataset Beyond Visual Dependency","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2607.01527","title":"Quantifying the Uncertainty of Blindly Estimated Room Embeddings Using a Dispersion-Calibrated Score","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2609.35839","title":"Estimation of Room Impulse Responses from Handclaps","created":"2026-09-24","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}