Overlapped Speech Detection in Broadcast Streams Using X-vectors

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F46747885%3A24220%2F22%3A00009899" target="_blank" >RIV/46747885:24220/22:00009899 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.isca-speech.org/archive/pdfs/interspeech_2022/mateju22_interspeech.pdf" target="_blank" >https://www.isca-speech.org/archive/pdfs/interspeech_2022/mateju22_interspeech.pdf</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.21437/Interspeech.2022-81" target="_blank" >10.21437/Interspeech.2022-81</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Overlapped Speech Detection in Broadcast Streams Using X-vectors

Popis výsledku v původním jazyce

A new approach to overlapped speech detection (OSD) is introduced in this work. It is designed for real-time processing of streamed data and utilizes x-vectors as its input features. It thus allows us to reduce computational demands within the entire streaming data processing chain, where the same x-vectors can also be used for the related task of speaker diarization. Within our method, the x-vectors are extracted using a feed-forward sequential memory network (FSMN) and then fed into a simple neural classifier (speech or cross-talk), whose output is smoothed by a decoder based on weighted finite-state transducers (WFSTs). The evaluation is done on a Czech/Slovak broadcast dataset (we make this data public) and on the AMI meeting corpus. Our online method yields a solid performance while operating with a 2-second latency.

Název v anglickém jazyce

Overlapped Speech Detection in Broadcast Streams Using X-vectors

Popis výsledku anglicky

A new approach to overlapped speech detection (OSD) is introduced in this work. It is designed for real-time processing of streamed data and utilizes x-vectors as its input features. It thus allows us to reduce computational demands within the entire streaming data processing chain, where the same x-vectors can also be used for the related task of speaker diarization. Within our method, the x-vectors are extracted using a feed-forward sequential memory network (FSMN) and then fed into a simple neural classifier (speech or cross-talk), whose output is smoothed by a decoder based on weighted finite-state transducers (WFSTs). The evaluation is done on a Czech/Slovak broadcast dataset (we make this data public) and on the AMI meeting corpus. Our online method yields a solid performance while operating with a 2-second latency.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20201 - Electrical and electronic engineering

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)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2022

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

4

Strana od-do

4606 - 4610

Název nakladatele

ISCA

Místo vydání

Jižní Korea

Místo konání akce

Incheon, South Korea

Datum konání akce

1. 1. 2022

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000900724504158