mlsanityData to 13 Oct 2026

EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberation

arXiv 2406.06185 ↗First posted 10 Jun 2024eess.AS cs.LG cs.SDcited by 64

Not on the map. Why?

Cited by 20 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We release the EARS (Expressive Anechoic Recordings of Speech) dataset, a high-quality speech dataset comprising 107 speakers from diverse backgrounds, totaling in 100 hours of clean, anechoic speech data. The dataset covers a large range of different speaking styles, including emotional speech, different reading styles, non-verbal sounds, and conversational freeform speech. We benchmark various methods for speech enhancement and dereverberation on the dataset and evaluate their performance through a set of instrumental metrics. In addition, we conduct a listening test with 20 participants for the speech enhancement task, where a generative method is preferred. We introduce a blind test set that allows for automatic online evaluation of uploaded data. Dataset download links and automatic evaluation server can be found online.

Key facts. Cited by 64 papers in the map (data through 13 Oct 2026). Builds on 17 of its 35 references that are in the map. First posted on arXiv 10 Jun 2024.

Builds on

17 of 35 references.

References · 17

  1. 2018SDR - half-baked or well done?cited by 422
  2. 2018Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separationcited by 402
  3. 2022Self-Supervised Speech Representation Learning: A Reviewcited by 258
  4. 2020DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressorscited by 239
  5. 2019NeMo: a toolkit for building AI applications using Neural Modulescited by 232
  6. 2017Supervised Speech Separation Based on Deep Learning: An Overviewcited by 213
  7. 2022Speech Enhancement and Dereverberation with Diffusion-based Generative Modelscited by 195
  8. 2021A Survey on Neural Speech Synthesiscited by 182
  9. 2019WHAM!: Extending Speech Separation to Noisy Environmentscited by 155
  10. 2022Hybrid Transformers for Music Source Separationcited by 134
  11. 2022Conditional Diffusion Probabilistic Model for Speech Enhancementcited by 132
  12. 2023ICASSP 2023 Deep Noise Suppression Challengecited by 63
5 more
  1. 2022Analysing Diffusion-based Generative Approaches versus Discriminative Approaches for Speech Restorationcited by 34
  2. 2024ICASSP 2024 Speech Signal Improvement Challengecited by 15
  3. 2021dEchorate: a Calibrated Room Impulse Response Database for Echo-aware Signal Processingcited by 10
  4. 2023Multi-dimensional Speech Quality Assessment in Crowdsourcingcited by 4
  5. 2023BRUDEX Database: Binaural Room Impulse Responses with Uniformly Distributed External Microphonescited by 3

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2024: 1; 2025: 33; 2026: 30.

64 papers.

Sort:

By area:

  1. 2025Scaling Rich Style-Prompted Text-to-Speech Datasetscited by 17
  2. 2025FlowDec: A flow-based full-band general audio codec with high perceptual qualitycited by 15
  3. 2025CapSpeech: Enabling Downstream Applications in Style-Captioned Text-to-Speechcited by 11
  4. 2025AV-Flow: Transforming Text to Audio-Visual Human-like Interactionscited by 9
  5. 2025DiTSE: High-Fidelity Generative Speech Enhancement via Latent Diffusion Transformerscited by 6
  6. 2025Diffusion Buffer: Online Diffusion-based Speech Enhancement with Sub-Second Latencycited by 6
  7. 2025SVeritas: Benchmark for Robust Speaker Verification under Diverse Conditionscited by 6
  8. 2025CoLMbo: Speaker Language Model for Descriptive Profilingcited by 5
  9. 2025Evaluating Bias in Spoken Dialogue LLMs for Real-World Decisions and Recommendationscited by 5
  10. 2026FlowSE-GRPO: Training Flow Matching Speech Enhancement via Online Reinforcement Learningcited by 5
  11. 2025A Study of the Scale Invariant Signal to Distortion Ratio in Speech Separation with Noisy Referencescited by 4
  12. 2025VoiceBridge: General Speech Restoration with One-step Latent Bridge Modelscited by 4
38 more
  1. 2025Real-Time Streamable Generative Speech Restoration with Flow Matchingcited by 4
  2. 2025UniverSR: Unified and Versatile Audio Super-Resolution via Vocoder-Free Flow Matchingcited by 3
  3. 2025Revisiting Audio-language Pretraining for Learning General-purpose Audio Representationcited by 3
  4. 2026Chatterbox-Flash: Prior-Calibrated Block Diffusion for Streaming Zero-Shot TTScited by 3
  5. 2025CleanMel: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASRcited by 2
  6. 2025SupertonicTTS: Towards Highly Efficient and Streamlined Text-to-Speech Systemcited by 2
  7. 2025LipDiffuser: Lip-to-Speech Generation with Conditional Diffusion Modelscited by 2
  8. 2025MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech Enhancementcited by 2
  9. 2025Diffusion Buffer for Online Generative Speech Enhancementcited by 2
  10. 2026Few-shot Acoustic Synthesis with Multimodal Flow Matchingcited by 2
  11. 2024Non-intrusive Speech Quality Assessment with Diffusion Models Trained on Clean Speechcited by 1
  12. 2025MARS6: A Small and Robust Hierarchical-Codec Text-to-Speech Modelcited by 1
  13. 2025Real-Time Streaming Mel Vocoding with Generative Flow Matchingcited by 1
  14. 2025Are Modern Speech Enhancement Systems Vulnerable to Adversarial Attacks?cited by 1
  15. 2025DELULU: Discriminative Embedding Learning Using Latent Units for Speaker-Aware Self-Trained Speech Foundational Modelcited by 1
  16. 2026What and When to Learn: CURriculum Ranking Loss for Large-Scale Speaker Verificationcited by 1
  17. 2026JASTIN: Aligning LLMs for Zero-Shot Audio and Speech Evaluation via Natural Language Instructionscited by 1
  18. 2026KVAE: Family of Tokenizers for Multimodal Generative Modelscited by 1
  19. 2026VoiceDesigner: Text-to-Voice Generation and Editing via Unified Diffusion Modeling and Data Augmentationcited by 1
  20. 2026AURAL: Adaptive Latent Reasoning with Joint Chunk for Speech Language Modelscited by 1
  21. 2025VINP: Variational Bayesian Inference with Neural Speech Prior for Joint ASR-Effective Speech Dereverberation and Blind RIR Identificationcited by 0
  22. 2025Performance improvement of spatial semantic segmentation with enriched audio features and agent-based error correction for DCASE 2025 Challenge Task 4cited by 0
  23. 2025MMMOS: Multi-domain Multi-axis Audio Quality Assessmentcited by 0
  24. 2025U-DREAM: Unsupervised Dereverberation guided by a Reverberation Modelcited by 0
  25. 2025On the Application of Diffusion Models for Simultaneous Denoising and Dereverberationcited by 0
  26. 2025Mixture-of-Experts Framework for Field-of-View Enhanced Signal-Dependent Binauralization of Moving Talkerscited by 0
  27. 2025BatonVoice: An Operationalist Framework for Enhancing Controllable Speech Synthesis with Linguistic Intelligence from LLMscited by 0
  28. 2025Exploring Resolution-Wise Shared Attention in Hybrid Mamba-U-Nets for Improved Cross-Corpus Speech Enhancementcited by 0
  29. 2025BridgeVoC: Revitalizing Neural Vocoder from a Restoration Perspectivecited by 0
  30. 2025Is Phase Really Needed for Weakly-Supervised Dereverberation ?cited by 0
  31. 2026Performance and Complexity Trade-off Optimization of Speech Models During Trainingcited by 0
  32. 2026Joint Enhancement and Classification using Coupled Diffusion Models of Signals and Logitscited by 0
  33. 2026Absorbing Discrete Diffusion for Speech Enhancementcited by 0
  34. 2026A Fast Solver for Interpolating Stochastic Differential Equation Diffusion Models for Speech Restorationcited by 0
  35. 2026UniPASE: A Generative Model for Universal Speech Enhancement with High Fidelity and Low Hallucinationscited by 0
  36. 2026Predictive-Generative Drift Decomposition for Speech Enhancement and Separationcited by 0
  37. 2026Dependence on Early and Late Reverberation of Single-Channel Speaker Distance Estimationcited by 0
  38. 2026Real-time Speech Restoration using Data Prediction Mean Flowscited by 0

50 most cited of 64 All 64 (JSON)