Online Punctuation Restoration using ELECTRA Model for streaming ASR Systems

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F46747885%3A24220%2F23%3A00011545" target="_blank" >RIV/46747885:24220/23:00011545 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.isca-archive.org/interspeech_2023/polacek23_interspeech.html" target="_blank" >https://www.isca-archive.org/interspeech_2023/polacek23_interspeech.html</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.21437/Interspeech.2023-664" target="_blank" >10.21437/Interspeech.2023-664</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Online Punctuation Restoration using ELECTRA Model for streaming ASR Systems

Popis výsledku v původním jazyce

In this work, we propose a lightweight online approach to automatic punctuation restoration (APR), which can be utilized in speech transcription systems for, e.g., live captioning TV or radio streams. It uses only text input without prosodic features and a fine-tuned ELECTRA-Small model with a two-layer classification head. It allows for restoring question marks, commas, and periods with a very short inference time and a low latency of just three words. Our APR scheme is first tuned and compared to other architectures on a set of manual TV news transcripts. The resulting system is then compared to another real-time APR module utilizing a recurrent network and a combination of text and acoustic features. The test data we use contains automatic transcripts of radio talks and TV debates; we are also publishing this data. The results show that our APR module performs better than the above-mentioned system and yields on the two test sets an average F1 of 71.2% and 69.4%, respectively.

Název v anglickém jazyce

Online Punctuation Restoration using ELECTRA Model for streaming ASR Systems

Popis výsledku anglicky

In this work, we propose a lightweight online approach to automatic punctuation restoration (APR), which can be utilized in speech transcription systems for, e.g., live captioning TV or radio streams. It uses only text input without prosodic features and a fine-tuned ELECTRA-Small model with a two-layer classification head. It allows for restoring question marks, commas, and periods with a very short inference time and a low latency of just three words. Our APR scheme is first tuned and compared to other architectures on a set of manual TV news transcripts. The resulting system is then compared to another real-time APR module utilizing a recurrent network and a combination of text and acoustic features. The test data we use contains automatic transcripts of radio talks and TV debates; we are also publishing this data. The results show that our APR module performs better than the above-mentioned system and yields on the two test sets an average F1 of 71.2% and 69.4%, respectively.

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

2023

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

ISBN

—

ISSN

2308-457X

e-ISSN

—

Počet stran výsledku

5

Strana od-do

446-450

Název nakladatele

ISCA

Místo vydání

Irsko

Místo konání akce

Dublin, Irsko

Datum konání akce

1. 1. 2023

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—