Wavelet Scattering Transform for Improving Generalization in Low-Resourced Spoken Language Identification
Commonly used features in spoken language identification (LID), such as mel-spectrogram or MFCC, lose high-frequency information due to windowing. The loss further increases for longer temporal contexts. To improve generalization of the low-resourced LID systems, we investigate an alternate feature representation, wavelet scattering transform (WST), that compensates for the shortcomings. To our knowledge, WST is not explored earlier in LID tasks. We first optimize WST features for multiple South Asian LID corpora. We show that LID requires low octave resolution and frequency-scattering is not useful. Further, cross-corpora evaluations show that the optimal WST hyper-parameters depend on both train and test corpora. Hence, we develop fused ECAPA-TDNN based LID systems with different sets of WST hyper-parameters to improve generalization for unknown data. Compared to MFCC, EER is reduced upto 14.05% and 6.40% for same-corpora and blind VoxLingua107 evaluations, respectively.
Code (0)
등록된 구현이 없습니다.
Tasks
Language IdentificationSpoken language identificationSimilar Papers 제목 키워드 기반
Understanding Graph Neural Networks with Generalized Geometric Scattering Transforms
The scattering transform is a multilayered wavelet-based deep learning architecture that acts as a model of convolutional neural networks. Recently, several works have introduced generalizations of the scattering transfo…
Wavelet Scattering on the Pitch Spiral
We present a new representation of harmonic sounds that linearizes the dynamics of pitch and spectral envelope, while remaining stable to deformations in the time-frequency plane. It is an instance of the scattering tran…
Parametric Scattering Networks
The wavelet scattering transform creates geometric invariants and deformation stability. In multiple signal domains, it has been shown to yield more discriminative representations compared to other non-learned representa…
Image ClassificationSmall Data Image ClassificationExploring the Optimality of Tight-Frame Scattering Networks
The wavelet scattering transform creates geometric invariants and deformation stability. In multiple signal domains, it has been shown to yield more discriminative representations compared to other non-learned representa…
Generic Deep Networks with Wavelet Scattering
We introduce a two-layer wavelet scattering network, for object classification. This scattering transform computes a spatial wavelet transform on the first layer and a new joint wavelet transform along spatial, angular a…
General Classification