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

Hemant Kathania; Sudarsana Kadiri; Paavo Alku; Mikko Kurimo

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

Hemant Kathania, Sudarsana Kadiri, Paavo Alku, Mikko Kurimo

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

24 Downloads (Pure)

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.

Original language	English
Title of host publication	Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa)
Place of Publication	Sweden
Publisher	Linköping University Electronic Press
Pages	94–100
Number of pages	7
ISBN (Electronic)	978-91-7929-614-8
Publication status	Published - 31 May 2021
MoE publication type	A4 Conference publication
Event	Nordic Conference on Computational Linguistics - Reykjavik, Iceland Duration: 31 May 2021 → 2 Jun 2021

Publication series

Name	Linköping electronic conference proceedings
Number	178
ISSN (Print)	1650-3686
ISSN (Electronic)	1650-3740

Conference

Conference	Nordic Conference on Computational Linguistics
Abbreviated title	NoDaLiDa
Country/Territory	Iceland
City	Reykjavik
Period	31/05/2021 → 02/06/2021

Access to Document

2021.nodalida-main.10Final published version, 1.4 MBLicence: CC BY-NC-SA

https://www.aclweb.org/anthology/2021.nodalida-main.10

OpenUrl availability

Full text

-: Movie Making Finland: Finnish fiction films as audiovisual big data, 1907-2017
Kurimo, M., Virkkunen, A., Moisio, A., Porjazovski, D. & Kathania, H.
01/01/2020 → 31/12/2022
Project: Academy of Finland: Other research funding

Science-IT
Mikko Hakala (Manager)
School of Science
Facility/equipment: Facility

Cite this

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) (pp. 94–100). (Linköping electronic conference proceedings; No. 178). Linköping University Electronic Press. https://www.aclweb.org/anthology/2021.nodalida-main.10

@inproceedings{f8d4629ad7ea4a3db10fce0cbed26c35,

title = "Spectral modification for recognition of children{\textquoteright}s speech under mismatched conditions",

abstract = "n this paper, we propose spectral modification by sharpening formants and by reducing the spectral tilt to recognize children{\textquoteright}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{\textquoteright}s speech recognition using an acoustic model trained on adult speech. In the experiments, WSJCAM0 and PFSTAR are used as databases for adults{\textquoteright} and children{\textquoteright}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.",

author = "Hemant Kathania and Sudarsana Kadiri and Paavo Alku and Mikko Kurimo",

year = "2021",

month = may,

day = "31",

language = "English",

series = "Link{\"o}ping electronic conference proceedings",

publisher = "Link{\"o}ping University Electronic Press",

number = "178",

pages = "94–100",

booktitle = "Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa)",

address = "Sweden",

note = "Nordic Conference on Computational Linguistics, NoDaLiDa ; Conference date: 31-05-2021 Through 02-06-2021",

}

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>

Spectral modification for recognition of children’s speech under mismatched conditions. / Kathania, Hemant; Kadiri, Sudarsana ; Alku, Paavo et al.
Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa). Sweden: Linköping University Electronic Press, 2021. p. 94–100 (Linköping electronic conference proceedings; No. 178).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Spectral modification for recognition of children’s speech under mismatched conditions

AU - Kathania, Hemant

AU - Kadiri, Sudarsana

AU - Alku, Paavo

AU - Kurimo, Mikko

PY - 2021/5/31

Y1 - 2021/5/31

N2 - 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.

AB - 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.

M3 - Conference contribution

T3 - Linköping electronic conference proceedings

SP - 94

EP - 100

BT - Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa)

PB - Linköping University Electronic Press

CY - Sweden

T2 - Nordic Conference on Computational Linguistics

Y2 - 31 May 2021 through 2 June 2021

ER -

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

Abstract

Publication series

Conference

Access to Document

OpenUrl availability

Fingerprint

Projects

-: Movie Making Finland: Finnish fiction films as audiovisual big data, 1907-2017

Equipment

Science-IT

Cite this