Study of Formant Modification for Children ASR

Hemant Kathania; Sudarsana Kadiri; Paavo Alku; Mikko Kurimo

doi:10.1109/ICASSP40776.2020.9053334

Study of Formant Modification for Children ASR

Hemant Kathania, Sudarsana Kadiri, Paavo Alku, Mikko Kurimo

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussa › Conference contribution › Scientific › vertaisarvioitu

9 Sitaatiot (Scopus)

124 Lataukset (Pure)

Abstrakti

The performance of automatic speech recognition systems for children’s speech is known to suffer from the large variation and mismatch in the acoustic and linguistic attributes between children’s and adults’ speech. One of the various identified sources of mismatch is the difference in formant frequencies between adults and children. In this paper, we propose a formant modification method to mitigate differences between adults’ and children’s speech and to improve the performance of ASR for children. The explored technique gives a relative 27% improvement in system performance compared to a hybrid DNN-HMM baseline. We also compare the system performance with related speaker adaptation methods like vocal tract length normalization (VTLN) and speaking rate adapta-
tion (SRA) and find that the proposed method gives improvements over them, as well. Combining the proposed method with VTLN and SRA results in a further reduction of WER. We also found that the proposed method performs well even
for noisy speech.

Alkuperäiskieli	Englanti
Otsikko	2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings
Kustantaja	IEEE
Sivut	7429-7433
Sivumäärä	5
ISBN (elektroninen)	978-1-5090-6631-5
ISBN (painettu)	978-1-5090-6632-2
DOI - pysyväislinkit	https://doi.org/10.1109/ICASSP40776.2020.9053334
Tila	Julkaistu - toukokuuta 2020
OKM-julkaisutyyppi	A4 Artikkeli konferenssijulkaisuussa
Tapahtuma	IEEE International Conference on Acoustics, Speech, and Signal Processing - Virtual conference, Barcelona, Espanja Kesto: 4 toukokuuta 2020 → 8 toukokuuta 2020 Konferenssinumero: 45

Julkaisusarja

Nimi	Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing
ISSN (painettu)	1520-6149
ISSN (elektroninen)	2379-190X

Conference

Conference	IEEE International Conference on Acoustics, Speech, and Signal Processing
Lyhennettä	ICASSP
Maa/Alue	Espanja
Kaupunki	Barcelona
Ajanjakso	04/05/2020 → 08/05/2020
Muu	Virtual conference

Pääsy asiakirjaan

10.1109/ICASSP40776.2020.9053334

Children_ASR_ICASSP_2020Accepted author manuscript, 219 KB

Muut tiedostot ja linkit

Linkki julkaisuun Scopuksessa

Science-IT
Mikko Hakala (Manager)
Perustieteiden korkeakoulu
Laitteistot/tilat: Facility

Siteeraa tätä

Kathania, H., Kadiri, S., Alku, P., & Kurimo, M. (2020). Study of Formant Modification for Children ASR. teoksessa 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings (Sivut 7429-7433). [9053334] (Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing). IEEE. https://doi.org/10.1109/ICASSP40776.2020.9053334

@inproceedings{c2ad5b2ee1444baf8a7d69c27a029724,

title = "Study of Formant Modification for Children ASR",

abstract = "The performance of automatic speech recognition systems for children{\textquoteright}s speech is known to suffer from the large variation and mismatch in the acoustic and linguistic attributes between children{\textquoteright}s and adults{\textquoteright} speech. One of the various identified sources of mismatch is the difference in formant frequencies between adults and children. In this paper, we propose a formant modification method to mitigate differences between adults{\textquoteright} and children{\textquoteright}s speech and to improve the performance of ASR for children. The explored technique gives a relative 27% improvement in system performance compared to a hybrid DNN-HMM baseline. We also compare the system performance with related speaker adaptation methods like vocal tract length normalization (VTLN) and speaking rate adapta-tion (SRA) and find that the proposed method gives improvements over them, as well. Combining the proposed method with VTLN and SRA results in a further reduction of WER. We also found that the proposed method performs well evenfor noisy speech.",

keywords = "hildren speech recognition, Formant modification, DNN",

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

year = "2020",

month = may,

doi = "10.1109/ICASSP40776.2020.9053334",

language = "English",

isbn = "978-1-5090-6632-2",

series = "Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing",

publisher = "IEEE",

pages = "7429--7433",

booktitle = "2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings",

address = "United States",

note = "IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP ; Conference date: 04-05-2020 Through 08-05-2020",

}

Kathania, H, Kadiri, S , Alku, P & Kurimo, M 2020, Study of Formant Modification for Children ASR. julkaisussa 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings., 9053334, Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, IEEE, Sivut 7429-7433, IEEE International Conference on Acoustics, Speech, and Signal Processing, Barcelona, Espanja, 04/05/2020. https://doi.org/10.1109/ICASSP40776.2020.9053334

Study of Formant Modification for Children ASR. / Kathania, Hemant; Kadiri, Sudarsana ; Alku, Paavo ; Kurimo, Mikko.

2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings. IEEE, 2020. s. 7429-7433 9053334 (Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing).

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussa › Conference contribution › Scientific › vertaisarvioitu

TY - GEN

T1 - Study of Formant Modification for Children ASR

AU - Kathania, Hemant

AU - Kadiri, Sudarsana

AU - Alku, Paavo

AU - Kurimo, Mikko

N1 - Conference code: 45

PY - 2020/5

Y1 - 2020/5

N2 - The performance of automatic speech recognition systems for children’s speech is known to suffer from the large variation and mismatch in the acoustic and linguistic attributes between children’s and adults’ speech. One of the various identified sources of mismatch is the difference in formant frequencies between adults and children. In this paper, we propose a formant modification method to mitigate differences between adults’ and children’s speech and to improve the performance of ASR for children. The explored technique gives a relative 27% improvement in system performance compared to a hybrid DNN-HMM baseline. We also compare the system performance with related speaker adaptation methods like vocal tract length normalization (VTLN) and speaking rate adapta-tion (SRA) and find that the proposed method gives improvements over them, as well. Combining the proposed method with VTLN and SRA results in a further reduction of WER. We also found that the proposed method performs well evenfor noisy speech.

AB - The performance of automatic speech recognition systems for children’s speech is known to suffer from the large variation and mismatch in the acoustic and linguistic attributes between children’s and adults’ speech. One of the various identified sources of mismatch is the difference in formant frequencies between adults and children. In this paper, we propose a formant modification method to mitigate differences between adults’ and children’s speech and to improve the performance of ASR for children. The explored technique gives a relative 27% improvement in system performance compared to a hybrid DNN-HMM baseline. We also compare the system performance with related speaker adaptation methods like vocal tract length normalization (VTLN) and speaking rate adapta-tion (SRA) and find that the proposed method gives improvements over them, as well. Combining the proposed method with VTLN and SRA results in a further reduction of WER. We also found that the proposed method performs well evenfor noisy speech.

KW - hildren speech recognition

KW - Formant modification

KW - DNN

UR - http://www.scopus.com/inward/record.url?scp=85089213866&partnerID=8YFLogxK

U2 - 10.1109/ICASSP40776.2020.9053334

DO - 10.1109/ICASSP40776.2020.9053334

M3 - Conference contribution

SN - 978-1-5090-6632-2

T3 - Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing

SP - 7429

EP - 7433

BT - 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings

PB - IEEE

T2 - IEEE International Conference on Acoustics, Speech, and Signal Processing

Y2 - 4 May 2020 through 8 May 2020

ER -

Kathania H, Kadiri S , Alku P , Kurimo M. Study of Formant Modification for Children ASR. julkaisussa 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings. IEEE. 2020. s. 7429-7433. 9053334. (Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing). https://doi.org/10.1109/ICASSP40776.2020.9053334

Study of Formant Modification for Children ASR

Abstrakti

Julkaisusarja

Conference

Pääsy asiakirjaan

Muut tiedostot ja linkit

Sormenjälki

Laitteet

Science-IT

Siteeraa tätä