Lexicon-based vs. Lexicon-free ASR for Norwegian Parliament Speech Transcription

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F46747885%3A24220%2F22%3A00009900" target="_blank" >RIV/46747885:24220/22:00009900 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/chapter/10.1007/978-3-031-16270-1_33" target="_blank" >https://link.springer.com/chapter/10.1007/978-3-031-16270-1_33</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-031-16270-1_33" target="_blank" >10.1007/978-3-031-16270-1_33</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Lexicon-based vs. Lexicon-free ASR for Norwegian Parliament Speech Transcription

Popis výsledku v původním jazyce

Norwegian is a challenging language for automatic speech recognition research because it has two written standards (Bokmal and Nynorsk) and a large number of distinct dialects, from which none has status of an official spoken norm. A traditional lexicon-based approach to ASR leads to a huge lexicon (because of the two standards and also due to compound words) with many spelling and pronunciation variants, and consequently to a large (and sparse) language model (LM). We have built a system with 601k-word lexicon and an acoustic model (AM) based on several types of neural networks and compare its performance with a lexicon-free end-to-end system developed in the ESPnet framework. For evaluation we use a publically available dataset of Norwegian parliament speeches that offers 100 h for training and 12 h for testing. In spite of this rather limited training resource, the lexicon-free approach yields significantly better results (13.0% word-error rate) compared to the best system with the lexicon, LM and neural network AM (that achieved 22.5% WER).

Název v anglickém jazyce

Lexicon-based vs. Lexicon-free ASR for Norwegian Parliament Speech Transcription

Popis výsledku anglicky

Norwegian is a challenging language for automatic speech recognition research because it has two written standards (Bokmal and Nynorsk) and a large number of distinct dialects, from which none has status of an official spoken norm. A traditional lexicon-based approach to ASR leads to a huge lexicon (because of the two standards and also due to compound words) with many spelling and pronunciation variants, and consequently to a large (and sparse) language model (LM). We have built a system with 601k-word lexicon and an acoustic model (AM) based on several types of neural networks and compare its performance with a lexicon-free end-to-end system developed in the ESPnet framework. For evaluation we use a publically available dataset of Norwegian parliament speeches that offers 100 h for training and 12 h for testing. In spite of this rather limited training resource, the lexicon-free approach yields significantly better results (13.0% word-error rate) compared to the best system with the lexicon, LM and neural network AM (that achieved 22.5% WER).

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/TO01000027" target="_blank" >TO01000027: NORDTRANS - Technologie pro automatický přepis řeči ve vybraných severských jazycích</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2022

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Lecture Notes in Computer Science

ISBN

978-303116269-5

ISSN

0302-9743

e-ISSN

—

Počet stran výsledku

9

Strana od-do

401-409

Název nakladatele

SPRINGER-VERLAG BERLIN

Místo vydání

—

Místo konání akce

Brno

Datum konání akce

1. 1. 2022

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000866222300033