Spectral modification for recognition of children’s speech under mismatched conditions

Loading...
Thumbnail Image
Journal Title
Journal ISSN
Volume Title
Conference article in proceedings
Date
2021-05-31
Major/Subject
Mcode
Degree programme
Language
en
Pages
7
94–100
Series
Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa), Linköping electronic conference proceedings, issue 178
Abstract
n this paper, we propose spectral modification by sharpening formants and by reducing the spectral tilt to recognize children’s speech by automatic speech recognition (ASR) systems developed using adult speech. In this type of mismatched condition, the ASR performance is degraded due to the acoustic and linguistic mismatch in the attributes between children and adult speakers. The proposed method is used to improve the speech intelligibility to enhance the children’s speech recognition using an acoustic model trained on adult speech. In the experiments, WSJCAM0 and PFSTAR are used as databases for adults’ and children’s speech, respectively. The proposed technique gives a significant improvement in the context of the DNN-HMM-based ASR. Furthermore, we validate the robustness of the technique by showing that it performs well also in mismatched noise conditions.
Description
Keywords
Other note
Citation
Kathania , H , Kadiri , S , Alku , P & Kurimo , M 2021 , Spectral modification for recognition of children’s speech under mismatched conditions . in Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa) . Linköping electronic conference proceedings , no. 178 , Linköping University Electronic Press , Sweden , pp. 94–100 , Nordic Conference on Computational Linguistics , Reykjavik , Iceland , 31/05/2021 . < https://www.aclweb.org/anthology/2021.nodalida-main.10 >