LSTM Neural Network for Speaker Change Detection in Telephone Conversations
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F18%3A43952855" target="_blank" >RIV/49777513:23520/18:43952855 - isvavai.cz</a>
Result on the web
<a href="https://link.springer.com/chapter/10.1007%2F978-3-319-99579-3_24" target="_blank" >https://link.springer.com/chapter/10.1007%2F978-3-319-99579-3_24</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-319-99579-3_24" target="_blank" >10.1007/978-3-319-99579-3_24</a>
Alternative languages
Result language
angličtina
Original language name
LSTM Neural Network for Speaker Change Detection in Telephone Conversations
Original language description
In this paper, we analyze an approach to speaker change detection in telephone conversations based on recurrent Long Short-Term Memory Neural Networks. We compare this approach to speaker change detection via Convolutional Neural Networks. We show that by finetuning the architecture and using suitable input data in the form of spectrograms, we obtain better results relatively by 2%.We have discovered that a smaller architecture performs better on unseen data. Also, we found out that using stateful LSTM layers that try to remember whole conversations is much worse than using recurrent networks that memorize only small sequences of speech.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
20205 - Automation and control systems
Result continuities
Project
<a href="/en/project/GBP103%2F12%2FG084" target="_blank" >GBP103/12/G084: Center for Large Scale Multi-modal Data Interpretation</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2018
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Speech and Computer 20th International Conference, SPECOM 2018 Leipzig, Germany, September 18–22, 2018, Proceedings
ISBN
978-3-319-99578-6
ISSN
0302-9743
e-ISSN
1611-3349
Number of pages
8
Pages from-to
226-233
Publisher name
Springer Nature Switzerland AG
Place of publication
Cham
Event location
Leipzig, Germany
Event date
Sep 18, 2018
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—