ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · 2022 · 54 citations · 23 references
ComputingData ScienceAcousticsComputational AcousticsMachine LearningAcoustic Signal ProcessingSpeech AcousticsSpeech RecognitionAcoustic EnvironmentsAcoustic Event DetectionAcoustic FiltersAcoustic MaskingData AugmentationEqual Error RateModel Performance AnalysisText-independent Speaker Recognition
Acoustic environments affect acoustic characteristics of sound to be recognized by physically interacting with sound wave propagation. Thus, training acoustic models for audio and speech tasks requires regularization on various acoustic environments in order to achieve robust performance in real life applications. We propose FilterAugment, a data augmentation method for regularization of acoustic models on various acoustic environments. FilterAugment mimics acoustic filters by applying different weights on frequency bands, therefore enables model to extract relevant information from wider frequency region. It is an improved version of frequency masking which masks information on random frequency bands. FilterAugment improved sound event detection (SED) model performance by 6.50% while frequency masking only improved 2.13% in terms of polyphonic sound detection score (PSDS). It achieved equal error rate (EER) of 1.22% when applied to a text-independent speaker verification model, outperforming model used frequency masking with EER of 1.26%. Prototype of FilterAugment was applied in our participation in DCASE 2021 challenge task 4, and played a major role in achieving the 3rd rank.
23
mixup: Beyond Empirical Risk Minimization
Hongyi Zhang, Moustapha Cissé, Yann Dauphin et al. · arXiv (Cornell University) · 2017 · 4.8K citations · Full text
SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
Daniel Park, William Chan, Yu Zhang et al. · 2019 · 3.5K citations · Full text
Lawrence E. Kinsler, Austin R. Frey, G. S. Bennett · American Journal of Physics · 1951 · 3.4K citations
AutoAugment: Learning Augmentation Strategies From Data
Ekin D. Cubuk, Barret Zoph, Dandelion Mané et al. · 2019 · 2.7K citations
CNN architectures for large-scale audio classification
Shawn Hershey, Sourish Chaudhuri, Daniel P. W. Ellis et al. · 2017 · 2.5K citations