Spoken Term Detection and Relevance Score Estimation Using Dot-Product of Pronunciation Embeddings

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F21%3A43962417" target="_blank" >RIV/49777513:23520/21:43962417 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.isca-speech.org/archive/interspeech_2021/svec21_interspeech.html" target="_blank" >https://www.isca-speech.org/archive/interspeech_2021/svec21_interspeech.html</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.21437/Interspeech.2021-1704" target="_blank" >10.21437/Interspeech.2021-1704</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Spoken Term Detection and Relevance Score Estimation Using Dot-Product of Pronunciation Embeddings

Popis výsledku v původním jazyce

The paper describes a novel approach to Spoken Term Detection (STD) in large spoken archives using deep LSTM networks. The work is based on the previous approach of using Siamese neural networks for STD and naturally extends it to directly localize a spoken term and estimate its relevance score. The phoneme confusion network generated by a phoneme recognizer is processed by the deep LSTM network which projects each segment of the confusion network into an embedding space. The searched term is projected into the same embedding space using another deep LSTM network. The relevance score is then computed using a simple dot-product in the embedding space and calibrated using a sigmoid function to predict the probability of occurrence. The location of the searched term is then estimated from the sequence of output probabilities. The deep LSTM networks are trained in a self-supervised manner from paired recognition hypotheses on word and phoneme levels. The method is experimentally evaluated on MALACH data in English and Czech languages.

Název v anglickém jazyce

Spoken Term Detection and Relevance Score Estimation Using Dot-Product of Pronunciation Embeddings

Popis výsledku anglicky

The paper describes a novel approach to Spoken Term Detection (STD) in large spoken archives using deep LSTM networks. The work is based on the previous approach of using Siamese neural networks for STD and naturally extends it to directly localize a spoken term and estimate its relevance score. The phoneme confusion network generated by a phoneme recognizer is processed by the deep LSTM network which projects each segment of the confusion network into an embedding space. The searched term is projected into the same embedding space using another deep LSTM network. The relevance score is then computed using a simple dot-product in the embedding space and calibrated using a sigmoid function to predict the probability of occurrence. The location of the searched term is then estimated from the sequence of output probabilities. The deep LSTM networks are trained in a self-supervised manner from paired recognition hypotheses on word and phoneme levels. The method is experimentally evaluated on MALACH data in English and Czech languages.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20205 - Automation and control systems

Projekt

<a href="/cs/project/VJ01010108" target="_blank" >VJ01010108: Robustní zpracování nahrávek pro operativu a bezpečnost</a><br>

Návaznosti

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

Rok uplatnění

2021

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

978-1-71383-690-2

ISSN

2308-457X

e-ISSN

—

Počet stran výsledku

5

Strana od-do

851-855

Název nakladatele

International Speech Communication Association

Místo vydání

Red Hook, NY

Místo konání akce

Brno, Czech Republic

Datum konání akce

30. 8. 2021

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—