Zero-shot audio classification with factored linear and nonlinear acoustic-semantic projections

Huang Xie; Okko Räsänen; Tuomas Virtanen

doi:10.1109/ICASSP39728.2021.9414994

Zero-shot audio classification with factored linear and nonlinear acoustic-semantic projections

Huang Xie^*
, Okko Räsänen
, Tuomas Virtanen

^*Tämän työn vastaava kirjoittaja

Tietotekniikka

Tutkimustuotos: Konferenssiartikkeli › Tieteellinen › vertaisarvioitu

14 Sitaatiot (Scopus)

18 Lataukset (Pure)

Abstrakti

In this paper, we study zero-shot learning in audio classification through factored linear and nonlinear acoustic-semantic projections between audio instances and sound classes. Zero-shot learning in audio classification refers to classification problems that aim at recognizing audio instances of sound classes, which have no available training data but only semantic side information. In this paper, we address zero-shot learning by employing factored linear and nonlinear acoustic-semantic projections. We develop factored linear projections by applying rank decomposition to a bilinear model, and use nonlinear activation functions, such as tanh, to model the non-linearity between acoustic embeddings and semantic embeddings. Compared with the prior bilinear model, experimental results show that the proposed projection methods are effective for improving classification performance of zero-shot learning in audio classification.

Alkuperäiskieli	Englanti
Otsikko	2021 IEEE International Conference on Acoustics, Speech, and Signal Processing
Alaotsikko	ICASSP 2021
Kustantaja	IEEE
Sivut	326-330
Sivumäärä	5
Vuosikerta	2021-June
ISBN (elektroninen)	978-1-7281-7606-2
ISBN (painettu)	978-1-7281-7605-5
DOI - pysyväislinkit	https://doi.org/10.1109/ICASSP39728.2021.9414994
Tila	Julkaistu - 2021
OKM-julkaisutyyppi	A4 Artikkeli konferenssijulkaisussa
Tapahtuma	IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING - Kesto: 1 tammik. 1900 → 1 tammik. 2000

Julkaisusarja

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

Conference

Conference	IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING
Ajanjakso	1/01/00 → 1/01/00

Rahoitus

The research leading to these results has received funding from the European Research Council under the European Unions H2020 Framework Programme through ERC Grant Agreement 637422 EVERYSOUND. OR was funded by Academy of Finland grant no. 314602.

Julkaisufoorumi-taso

Jufo-taso 1

!!ASJC Scopus subject areas

Software
Signal Processing
Electrical and Electronic Engineering

Pääsy asiakirjaan

10.1109/ICASSP39728.2021.9414994

ICASSP2021_3766_finalAccepted author manuscript, 220 KB

https://urn.fi/URN:NBN:fi:tuni-202203012239

Siteeraa tätä

Xie, H., Räsänen, O., & Virtanen, T. (2021). Zero-shot audio classification with factored linear and nonlinear acoustic-semantic projections. teoksessa 2021 IEEE International Conference on Acoustics, Speech, and Signal Processing: ICASSP 2021 (Vuosikerta 2021-June, Sivut 326-330). (Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing). IEEE. https://doi.org/10.1109/ICASSP39728.2021.9414994

Xie, Huang ; Räsänen, Okko ; Virtanen, Tuomas. / Zero-shot audio classification with factored linear and nonlinear acoustic-semantic projections. 2021 IEEE International Conference on Acoustics, Speech, and Signal Processing: ICASSP 2021. Vuosikerta 2021-June IEEE, 2021. Sivut 326-330 (Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing).

@inproceedings{d8cc7ff608ff48a58fcf662333320292,

title = "Zero-shot audio classification with factored linear and nonlinear acoustic-semantic projections",

abstract = "In this paper, we study zero-shot learning in audio classification through factored linear and nonlinear acoustic-semantic projections between audio instances and sound classes. Zero-shot learning in audio classification refers to classification problems that aim at recognizing audio instances of sound classes, which have no available training data but only semantic side information. In this paper, we address zero-shot learning by employing factored linear and nonlinear acoustic-semantic projections. We develop factored linear projections by applying rank decomposition to a bilinear model, and use nonlinear activation functions, such as tanh, to model the non-linearity between acoustic embeddings and semantic embeddings. Compared with the prior bilinear model, experimental results show that the proposed projection methods are effective for improving classification performance of zero-shot learning in audio classification.",

keywords = "Acoustic-semantic projection, Audio classification, Zero-shot learning",

author = "Huang Xie and Okko R{\"a}s{\"a}nen and Tuomas Virtanen",

note = "Funding Information: The research leading to these results has received funding from the European Research Council under the European Unions H2020 Framework Programme through ERC Grant Agreement 637422 EVERYSOUND. OR was funded by Academy of Finland grant no. 314602. Publisher Copyright: {\textcopyright} 2021 IEEE JUFOID=57409; IEEE International Conference on Acoustics, Speech and Signal Processing ; Conference date: 01-01-1900 Through 01-01-2000",

year = "2021",

doi = "10.1109/ICASSP39728.2021.9414994",

language = "English",

isbn = "978-1-7281-7605-5",

volume = "2021-June",

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

publisher = "IEEE",

pages = "326--330",

booktitle = "2021 IEEE International Conference on Acoustics, Speech, and Signal Processing",

address = "United States",

}

Xie, H, Räsänen, O & Virtanen, T 2021, Zero-shot audio classification with factored linear and nonlinear acoustic-semantic projections. julkaisussa 2021 IEEE International Conference on Acoustics, Speech, and Signal Processing: ICASSP 2021. Vuosikerta 2021-June, Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, IEEE, Sivut 326-330, IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, 1/01/00. https://doi.org/10.1109/ICASSP39728.2021.9414994

Zero-shot audio classification with factored linear and nonlinear acoustic-semantic projections. / Xie, Huang; Räsänen, Okko ; Virtanen, Tuomas.
2021 IEEE International Conference on Acoustics, Speech, and Signal Processing: ICASSP 2021. Vuosikerta 2021-June IEEE, 2021. s. 326-330 (Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing).

Tutkimustuotos: Konferenssiartikkeli › Tieteellinen › vertaisarvioitu

TY - GEN

T1 - Zero-shot audio classification with factored linear and nonlinear acoustic-semantic projections

AU - Xie, Huang

AU - Räsänen, Okko

AU - Virtanen, Tuomas

N1 - Funding Information: The research leading to these results has received funding from the European Research Council under the European Unions H2020 Framework Programme through ERC Grant Agreement 637422 EVERYSOUND. OR was funded by Academy of Finland grant no. 314602. Publisher Copyright: © 2021 IEEE JUFOID=57409

PY - 2021

Y1 - 2021

N2 - In this paper, we study zero-shot learning in audio classification through factored linear and nonlinear acoustic-semantic projections between audio instances and sound classes. Zero-shot learning in audio classification refers to classification problems that aim at recognizing audio instances of sound classes, which have no available training data but only semantic side information. In this paper, we address zero-shot learning by employing factored linear and nonlinear acoustic-semantic projections. We develop factored linear projections by applying rank decomposition to a bilinear model, and use nonlinear activation functions, such as tanh, to model the non-linearity between acoustic embeddings and semantic embeddings. Compared with the prior bilinear model, experimental results show that the proposed projection methods are effective for improving classification performance of zero-shot learning in audio classification.

AB - In this paper, we study zero-shot learning in audio classification through factored linear and nonlinear acoustic-semantic projections between audio instances and sound classes. Zero-shot learning in audio classification refers to classification problems that aim at recognizing audio instances of sound classes, which have no available training data but only semantic side information. In this paper, we address zero-shot learning by employing factored linear and nonlinear acoustic-semantic projections. We develop factored linear projections by applying rank decomposition to a bilinear model, and use nonlinear activation functions, such as tanh, to model the non-linearity between acoustic embeddings and semantic embeddings. Compared with the prior bilinear model, experimental results show that the proposed projection methods are effective for improving classification performance of zero-shot learning in audio classification.

KW - Acoustic-semantic projection

KW - Audio classification

KW - Zero-shot learning

U2 - 10.1109/ICASSP39728.2021.9414994

DO - 10.1109/ICASSP39728.2021.9414994

M3 - Conference contribution

AN - SCOPUS:85115058220

SN - 978-1-7281-7605-5

VL - 2021-June

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

SP - 326

EP - 330

BT - 2021 IEEE International Conference on Acoustics, Speech, and Signal Processing

PB - IEEE

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

Y2 - 1 January 1900 through 1 January 2000

ER -

Xie H, Räsänen O , Virtanen T. Zero-shot audio classification with factored linear and nonlinear acoustic-semantic projections. julkaisussa 2021 IEEE International Conference on Acoustics, Speech, and Signal Processing: ICASSP 2021. Vuosikerta 2021-June. IEEE. 2021. s. 326-330. (Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing). doi: 10.1109/ICASSP39728.2021.9414994

Zero-shot audio classification with factored linear and nonlinear acoustic-semantic projections

Abstrakti

Julkaisusarja

Conference

Rahoitus

Julkaisufoorumi-taso

!!ASJC Scopus subject areas

Pääsy asiakirjaan

Sormenjälki

Siteeraa tätä