Attention-Based End-To-End Named Entity Recognition From Speech

Dejan Porjazovski; Juho Leinonen; Mikko Kurimo

doi:10.1007/978-3-030-83527-9_40

Attention-Based End-To-End Named Entity Recognition From Speech

Dejan Porjazovski, Juho Leinonen, Mikko Kurimo

Speech Recognition

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussa › Conference article in proceedings › Scientific › vertaisarvioitu

3 Sitaatiot (Scopus)

210 Lataukset (Pure)

Abstrakti

Named entities are heavily used in the field of spoken language understanding, which uses speech as an input. The standard way of doing named entity recognition from speech involves a pipeline of two systems, where first the automatic speech recognition system generates the transcripts, and then the named entity recognition system produces the named entity tags from the transcripts. In such cases, automatic speech recognition and named entity recognition systems are trained independently, resulting in the automatic speech recognition branch not being optimized for named entity recognition and vice versa. In this paper, we propose two attention-based approaches for extracting named entities from speech in an end-to-end manner, that show promising results. We compare both attention-based approaches on Finnish, Swedish, and English data sets, underlining their strengths and weaknesses.

Alkuperäiskieli	Englanti
Otsikko	Text, Speech, and Dialogue - 24th International Conference, TSD 2021, Proceedings
Toimittajat	Kamil Ekštein, František Pártl, Miloslav Konopík
Kustantaja	Springer
Sivut	469 - 480
Sivumäärä	12
ISBN (elektroninen)	978-3-030-83527-9
ISBN (painettu)	9783030835262
DOI - pysyväislinkit	https://doi.org/10.1007/978-3-030-83527-9_40
Tila	Julkaistu - 2021
OKM-julkaisutyyppi	A4 Artikkeli konferenssijulkaisussa
Tapahtuma	International Conference on Text, Speech, and Dialogue - Olomouc, Tshekki Kesto: 6 syysk. 2021 → 9 syysk. 2021 Konferenssinumero: 24

Julkaisusarja

Nimi	Lecture Notes in Computer Science
Vuosikerta	12848
ISSN (painettu)	0302-9743
ISSN (elektroninen)	1611-3349

Conference

Conference	International Conference on Text, Speech, and Dialogue
Lyhennettä	TSD
Maa/Alue	Tshekki
Kaupunki	Olomouc
Ajanjakso	06/09/2021 → 09/09/2021

Pääsy asiakirjaan

10.1007/978-3-030-83527-9_40

TSD_2021_Attention_Based_End_To_End_Named_Entity_Recognition_From_SpeechAccepted author manuscript, 1,15 MB

Muut tiedostot ja linkit

Linkki julkaisuun Scopuksessa

MeMAD: Methods for Managing Audiovisual Data: Combining Automatic Efficiency with Human Accuracy
Kurimo, M., Grönroos, S., Brander, T., Porjazovski, D., Raitio, R., Grósz, T., Virkkunen, A. & Rouhe, A.
27/12/2017 → 31/03/2021
Projekti: EU: Framework programmes funding

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

Siteeraa tätä

Porjazovski, D., Leinonen, J., & Kurimo, M. (2021). Attention-Based End-To-End Named Entity Recognition From Speech. teoksessa K. Ekštein, F. Pártl, & M. Konopík (Toimittajat), Text, Speech, and Dialogue - 24th International Conference, TSD 2021, Proceedings (Sivut 469 - 480). (Lecture Notes in Computer Science; Vuosikerta 12848 ). Springer. https://doi.org/10.1007/978-3-030-83527-9_40

@inproceedings{d4014ded6a724a81bad8beeea6ad2e2b,

title = "Attention-Based End-To-End Named Entity Recognition From Speech",

abstract = "Named entities are heavily used in the field of spoken language understanding, which uses speech as an input. The standard way of doing named entity recognition from speech involves a pipeline of two systems, where first the automatic speech recognition system generates the transcripts, and then the named entity recognition system produces the named entity tags from the transcripts. In such cases, automatic speech recognition and named entity recognition systems are trained independently, resulting in the automatic speech recognition branch not being optimized for named entity recognition and vice versa. In this paper, we propose two attention-based approaches for extracting named entities from speech in an end-to-end manner, that show promising results. We compare both attention-based approaches on Finnish, Swedish, and English data sets, underlining their strengths and weaknesses. ",

author = "Dejan Porjazovski and Juho Leinonen and Mikko Kurimo",

note = "| openaire: EC/H2020/780069/EU//MeMAD ; International Conference on Text, Speech, and Dialogue, TSD ; Conference date: 06-09-2021 Through 09-09-2021",

year = "2021",

doi = "10.1007/978-3-030-83527-9_40",

language = "English",

isbn = "9783030835262",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "469 -- 480",

editor = "Kamil Ek{\v s}tein and Franti{\v s}ek P{\'a}rtl and Miloslav Konop{\'i}k",

booktitle = "Text, Speech, and Dialogue - 24th International Conference, TSD 2021, Proceedings",

address = "Germany",

}

Porjazovski, D , Leinonen, J & Kurimo, M 2021, Attention-Based End-To-End Named Entity Recognition From Speech. julkaisussa K Ekštein, F Pártl & M Konopík (toim), Text, Speech, and Dialogue - 24th International Conference, TSD 2021, Proceedings. Lecture Notes in Computer Science, Vuosikerta 12848 , Springer, Sivut 469 - 480, International Conference on Text, Speech, and Dialogue, Olomouc, Tshekki, 06/09/2021. https://doi.org/10.1007/978-3-030-83527-9_40

Attention-Based End-To-End Named Entity Recognition From Speech. / Porjazovski, Dejan ; Leinonen, Juho ; Kurimo, Mikko.
Text, Speech, and Dialogue - 24th International Conference, TSD 2021, Proceedings. toim. / Kamil Ekštein; František Pártl; Miloslav Konopík. Springer, 2021. s. 469 - 480 (Lecture Notes in Computer Science; Vuosikerta 12848 ).

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussa › Conference article in proceedings › Scientific › vertaisarvioitu

TY - GEN

T1 - Attention-Based End-To-End Named Entity Recognition From Speech

AU - Porjazovski, Dejan

AU - Leinonen, Juho

AU - Kurimo, Mikko

N1 - Conference code: 24

PY - 2021

Y1 - 2021

N2 - Named entities are heavily used in the field of spoken language understanding, which uses speech as an input. The standard way of doing named entity recognition from speech involves a pipeline of two systems, where first the automatic speech recognition system generates the transcripts, and then the named entity recognition system produces the named entity tags from the transcripts. In such cases, automatic speech recognition and named entity recognition systems are trained independently, resulting in the automatic speech recognition branch not being optimized for named entity recognition and vice versa. In this paper, we propose two attention-based approaches for extracting named entities from speech in an end-to-end manner, that show promising results. We compare both attention-based approaches on Finnish, Swedish, and English data sets, underlining their strengths and weaknesses.

AB - Named entities are heavily used in the field of spoken language understanding, which uses speech as an input. The standard way of doing named entity recognition from speech involves a pipeline of two systems, where first the automatic speech recognition system generates the transcripts, and then the named entity recognition system produces the named entity tags from the transcripts. In such cases, automatic speech recognition and named entity recognition systems are trained independently, resulting in the automatic speech recognition branch not being optimized for named entity recognition and vice versa. In this paper, we propose two attention-based approaches for extracting named entities from speech in an end-to-end manner, that show promising results. We compare both attention-based approaches on Finnish, Swedish, and English data sets, underlining their strengths and weaknesses.

UR - http://www.scopus.com/inward/record.url?scp=85115247889&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-83527-9_40

DO - 10.1007/978-3-030-83527-9_40

M3 - Conference article in proceedings

SN - 9783030835262

T3 - Lecture Notes in Computer Science

SP - 469

EP - 480

BT - Text, Speech, and Dialogue - 24th International Conference, TSD 2021, Proceedings

A2 - Ekštein, Kamil

A2 - Pártl, František

A2 - Konopík, Miloslav

PB - Springer

T2 - International Conference on Text, Speech, and Dialogue

Y2 - 6 September 2021 through 9 September 2021

ER -

Attention-Based End-To-End Named Entity Recognition From Speech

Abstrakti

Julkaisusarja

Conference

Pääsy asiakirjaan

Muut tiedostot ja linkit

Sormenjälki

Projektit

MeMAD: Methods for Managing Audiovisual Data: Combining Automatic Efficiency with Human Accuracy

Laitteet

Science-IT

Siteeraa tätä