A prosody inspired RNN approach for punctuation of machine produced speech transcripts to improve human readability

Moro, Anna L.; Szaszák, György

doi:10.1109/coginfocom.2017.8268246

Cited by 12 publications

(8 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Algumas pesquisas apontaram pouca identificação de vírgulas nos sistemas ASRreconhecimento automático de fala -que transformam a fala em texto (MORÓ & SZASZÁK, 2017a;SZASZÁK, 2017b). A vírgula pode indicar três tons (suspensivo, asserção e pergunta), sendo marcadores prosódicos que podem ser expressos de diversas maneiras e servem para orientar o leitor quanto às variações melódicas e entoacionais do discurso (CAGLIARI, 1989).…”

Section: Discussionunclassified

Características prosódicas associadas aos sinais de pontuação

Galdino

Silva

Oliveira

2021

CadLin

View full text Add to dashboard Cite

O objetivo deste artigo é apresentar uma revisão de escopo sobre as características prosódicas associadas aos sinais de pontuação. Foi realizado um levantamento bibliográfico a partir da pesquisa de descritores em inglês e português, organizados de acordo com a seguinte sintaxe: prosódia AND acústica AND discurso AND estrutura AND ("sinais de pontuação" OR "pontuação gráfica" OR "sinal de pontuação"), sem incluir citações e patentes nas bases de dados: OvidMedlin, Public Medicine Library (PubMed), Scopus (Elsevier), Ebscohost (Academic Search Premier), Gale Academic Online e Google Scholar. Observamos que existe uma diversidade de métodos empregados para analisar a correlação entre os sinais de pontuação e as características prosódicas. Os estudos desta revisão confirmaram nossa pergunta de pesquisa, evidenciando a relação entre os sinais de pontuação e os aspectos prosódicos. A maioria dos trabalhos relacionados à tecnologia desenvolveu diferentes redes neurais para transformar texto em fala e/ou para converter fala em texto e mostrou que as pausas são apontadas como indicadores mais fortes dos sinais de pontuação.

show abstract

Section: Discussionunclassified

Características prosódicas associadas aos sinais de pontuação

Galdino

Silva

Oliveira

2021

CadLin

View full text Add to dashboard Cite

show abstract

“…This includes those that incorporate acoustic information (B. Garg and Anika, 2018;Moro and Szaszak, 2017;Szaszák and Tündik, 2019;Nanchen and Garner, 2019;Moró and Szaszák, 2017;Klejch et al, 2016Klejch et al, , 2017 and those that apply attention on top (Tilk and Alumäe, 2016;Oktem et al, 2017;Kim, 2019;Juin et al, 2017).…”

Section: Related Workmentioning

confidence: 99%

Efficient Automatic Punctuation Restoration Using Bidirectional Transformers with Robust Inference

Courtland¹,

Faulkner²,

McElvain³

2020

Proceedings of the 17th International Conference on Spoken Language Translation

View full text Add to dashboard Cite

Though people rarely speak in complete sentences, punctuation confers many benefits to the readers of transcribed speech. Unfortunately, most ASR systems do not produce punctuated output. To address this, we propose a solution for automatic punctuation that is both cost efficient and easy to train. Our solution benefits from the recent trend in fine-tuning transformer-based language models. We also modify the typical framing of this task by predicting punctuation for sequences rather than individual tokens, which makes for more efficient training and inference. Finally, we find that aggregating predictions across multiple context windows improves accuracy even further. Our best model achieves a new state of the art on benchmark data (TED Talks) with a combined F1 of 83.9, representing a 48.7% relative improvement (15.3 absolute) over the previous state of the art.

show abstract

“…This includes those that incorporate acoustic information (B. Garg and Anika, 2018;Moro and Szaszak, 2017;Szaszák and Tündik, 2019;Nanchen and Garner, 2019;Moró and Szaszák, 2017;Klejch et al, 2016Klejch et al, , 2017 and those that apply attention on top Oktem et al, 2017;Kim, 2019;Juin et al, 2017).…”

Section: Related Workmentioning

confidence: 99%

Proceedings of the 17th International Conference on Spoken Language Translation

Federico¹,

Waibel²,

Knight³

et al. 2020

View full text Add to dashboard Cite

The conference chairs and organizers would like to express their gratitude to everyone who contributed and supported IWSLT. Our IWSLT-20 program exceeds all our expectations in quality and breath, particularly when considering the challenges during a pandemic under lock-downs and health and travel restrictions. We thank the challenge track chairs, organizers, and participants, the program chairs and committee members, as well as all the authors that went the extra mile to submit system and research papers to IWSLT, and make this year's conference our most vibrant than ever. We also wish to express our sincere gratitude to ACL for hosting our conference and for arranging the logistics and infrastructure that allow us to hold IWSLT 2020 as a virtual online conference.

show abstract

A prosody inspired RNN approach for punctuation of machine produced speech transcripts to improve human readability

Cited by 12 publications

References 19 publications

Características prosódicas associadas aos sinais de pontuação

Características prosódicas associadas aos sinais de pontuação

Efficient Automatic Punctuation Restoration Using Bidirectional Transformers with Robust Inference

Proceedings of the 17th International Conference on Spoken Language Translation

Contact Info

Product

Resources

About