{"total":33,"rows":[{"id":"2101.08596","title":"LEAF: A Learnable Frontend for Audio Classification","created":"2021-01-21","cited_by_count":69,"area":null},{"id":"2111.10592","title":"Deep Spoken Keyword Spotting: An Overview","created":"2021-11-20","cited_by_count":43,"area":null},{"id":"2312.07439","title":"BIRB: A Generalization Benchmark for Information Retrieval in Bioacoustics","created":"2023-12-12","cited_by_count":19,"area":null},{"id":"2102.03207","title":"Real-time Denoising and Dereverberation with Tiny Recurrent U-Net","created":"2021-02-05","cited_by_count":16,"area":null},{"id":"2206.12513","title":"Domain Generalization with Relaxed Instance Frequency-wise Normalization for Multi-device Acoustic Scene Classification","created":"2022-06-24","cited_by_count":16,"area":null},{"id":"2403.02522","title":"HeAR -- Health Acoustic Representations","created":"2024-03-04","cited_by_count":15,"area":null},{"id":"2110.15957","title":"Visual Keyword Spotting with Attention","created":"2021-10-29","cited_by_count":11,"area":null},{"id":"2201.07677","title":"Tiny, always-on and fragile: Bias propagation through design choices in on-device machine learning workflows","created":"2022-01-19","cited_by_count":8,"area":null},{"id":"2207.05508","title":"EfficientLEAF: A Faster LEarnable Audio Frontend of Questionable Use","created":"2022-07-12","cited_by_count":8,"area":null},{"id":"2111.06531","title":"Domain Generalization on Efficient Acoustic Scene Classification using Residual Normalization","created":"2021-11-12","cited_by_count":6,"area":null},{"id":"2210.01719","title":"Learning Temporal Resolution in Spectrogram for Audio Classification","created":"2022-10-04","cited_by_count":4,"area":null},{"id":"2102.03468","title":"Sound Event Detection in Urban Audio With Single and Multi-Rate PCEN","created":"2021-02-06","cited_by_count":3,"area":null},{"id":"2207.07773","title":"Segment-level Metric Learning for Few-shot Bioacoustic Event Detection","created":"2022-07-15","cited_by_count":3,"area":null},{"id":"2105.11856","title":"Spectrum Correction: Acoustic Scene Classification with Mismatched Recording Devices","created":"2021-05-25","cited_by_count":2,"area":null},{"id":"2109.12058","title":"Optimized Power Normalized Cepstral Coefficients towards Robust Deep Speaker Verification","created":"2021-09-24","cited_by_count":2,"area":null},{"id":"2212.03812","title":"An Overview of Indian Spoken Language Recognition from Machine Learning Perspective","created":"2022-11-30","cited_by_count":2,"area":null},{"id":"2311.02369","title":"TACNET: Temporal Audio Source Counting Network","created":"2023-11-04","cited_by_count":2,"area":null},{"id":"2109.12056","title":"Parameterized Channel Normalization for Far-field Deep Speaker Verification","created":"2021-09-24","cited_by_count":1,"area":null},{"id":"2202.05236","title":"Learnable Nonlinear Compression for Robust Speaker Verification","created":"2022-02-10","cited_by_count":1,"area":null},{"id":"2203.15519","title":"Learning neural audio features without supervision","created":"2022-03-29","cited_by_count":1,"area":null},{"id":"2305.17706","title":"Spot keywords from very noisy and mixed speech","created":"2023-05-28","cited_by_count":1,"area":null},{"id":"2310.11379","title":"Robust Wake-Up Word Detection by Two-stage Multi-resolution Ensembles","created":"2023-10-17","cited_by_count":1,"area":null},{"id":"2207.13843","title":"Deep Learning-Based Acoustic Mosquito Detection in Noisy Conditions Using Trainable Kernels and Augmentations","created":"2022-07-28","cited_by_count":0,"area":null},{"id":"2408.13644","title":"Studying the Effect of Audio Filters in Pre-Trained Models for Environmental Sound Classification","created":"2024-08-24","cited_by_count":0,"area":null},{"id":"2409.08997","title":"Biomimetic Frontend for Differentiable Audio Processing","created":"2024-09-13","cited_by_count":0,"area":null},{"id":"2409.12076","title":"Unsupervised Domain Adaptation Via Data Pruning","created":"2024-09-18","cited_by_count":0,"area":null},{"id":"2410.04235","title":"Improving Distribution Alignment with Diversity-based Sampling","created":"2024-10-05","cited_by_count":0,"area":null},{"id":"2601.16316","title":"EdgeSpot: Efficient and High-Performance Few-Shot Model for Keyword Spotting","created":"2026-01-22","cited_by_count":0,"area":null},{"id":"2603.14917","title":"Spectrogram features for audio and speech analysis","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2604.10503","title":"Cross-Cultural Bias in Mel-Scale Representations: Evidence and Alternatives from Speech and Music","created":"2026-04-12","cited_by_count":0,"area":null},{"id":"2606.10407","title":"Time-frequency localization of bird calls in dense soundscapes","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2608.23101","title":"PolyChirp: Multi-Species Birdsong Classification Using TinyML on Low-Power Acoustic Sensors","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.31699","title":"Normalise or condition? Noise-floor front-ends for on-board keyword spotting under UAV rotor ego-noise","created":"2026-09-19","cited_by_count":0,"area":null}],"next_cursor":null}