Data Augmentation Using Spectral Warping for Low Resource Children ASR

Hemant Kumar Kathania*, Viredner Kadyan, Sudarsana Reddy Kadiri*, Mikko Kurimo

*Tämän työn vastaava kirjoittaja

Tutkimustuotos: LehtiartikkeliArticleScientificvertaisarvioitu

5 Sitaatiot (Scopus)
59 Lataukset (Pure)

Abstrakti

In low resource children automatic speech recognition (ASR) the performance is degraded due to limited acoustic and speaker variability available in small datasets. In this paper, we propose a spectral warping based data augmentation method to capture more acoustic and speaker variability. This is carried out by warping the linear prediction (LP) spectra computed from speech data. The warped LP spectra computed in a frame-based manner are used with the corresponding LP residuals to synthesize speech to capture more variability. The proposed augmentation method is shown to improve the ASR system performance over the baseline system. We have compared the proposed method with four well-known data augmentation methods: pitch scaling, speaking rate, SpecAug and vocal tract length perturbation (VTLP), and found that the proposed method performs the best. Further, we have combined the proposed method with these existing data augmentation methods to improve the ASR system performance even more. The combined system consisting of the original data, VTLP, SpecAug and the proposed spectral warping method gave the best performance by a relative word error rate reduction of 32.13% and 10.51% over the baseline system for Punjabi children and TLT-school corpus, respectively. The proposed spectral warping method is publicly available at https://github.com/kathania/Spectral-Warping.

AlkuperäiskieliEnglanti
Sivut1507-1513
Sivumäärä7
JulkaisuJournal of Signal Processing Systems
Vuosikerta94
Numero12
Varhainen verkossa julkaisun päivämäärä8 marrask. 2022
DOI - pysyväislinkit
TilaJulkaistu - jouluk. 2022
OKM-julkaisutyyppiA1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä

Sormenjälki

Sukella tutkimusaiheisiin 'Data Augmentation Using Spectral Warping for Low Resource Children ASR'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä