Online Speaker Diarization Using Optimized SE-ResNet Architecture
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F46747885%3A24220%2F23%3A00011570" target="_blank" >RIV/46747885:24220/23:00011570 - isvavai.cz</a>
Result on the web
<a href="https://dl.acm.org/doi/10.1007/978-3-031-40498-6_16" target="_blank" >https://dl.acm.org/doi/10.1007/978-3-031-40498-6_16</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-031-40498-6_16" target="_blank" >10.1007/978-3-031-40498-6_16</a>
Alternative languages
Result language
angličtina
Original language name
Online Speaker Diarization Using Optimized SE-ResNet Architecture
Original language description
A new approach to speaker diarization (SD) suitable for real-time processing of streamed data is presented in this work. It utilizes a modified residual network with squeeze-and-excitation blocks (SE-ResNet-34) for extraction of speaker embeddings. These speaker embeddings are calculated in an optimized way by using cached buffers and are subsequently used for voice activity detection (VAD) as well as for block-online k-means clustering with a look-ahead mechanism. All these processing steps are first evaluated separately on a development set compiled from recordings of Czech broadcast programs. The whole scheme is then compared to an offline reference approach on various speech databases that are publicly available and include data in various languages. On this data, our method yields results similar to the reference system while operating on a CPU with a low real-time factor (RTF) below 0.1 and a latency of around 5.5 s.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
<a href="/en/project/TO01000027" target="_blank" >TO01000027: NORDTRANS - Technology for automatic speech transcription in selected Nordic languages</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach
Others
Publication year
2023
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Lecture Notes in Computer Science
ISBN
978-303140497-9
ISSN
03029743
e-ISSN
—
Number of pages
12
Pages from-to
176-187
Publisher name
Springer
Place of publication
Německo
Event location
Plzeň, ČR
Event date
Jan 1, 2023
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—