Conference paper| DIEZ Sánchez Mireia, BURGET Lukáš and MATĚJKA Pavel. Speaker Diarization based on Bayesian HMM with Eigenvoice Priors. In: Proceedings of Odyssey 2018. Les Sables d´Olonne: International Speech Communication Association, 2018, pp. 147-154. ISSN 2312-2846. | | Publication language: | english |
|---|
| Original title: | Speaker Diarization based on Bayesian HMM with Eigenvoice Priors |
|---|
| Title (cs): | Diarizace založená na bayessovském HMM s Eigenvoice apriorní informací |
|---|
| Pages: | 147-154 |
|---|
| Proceedings: | Proceedings of Odyssey 2018 |
|---|
| Conference: | Odyssey 2018 |
|---|
| Place: | Les Sables d´Olonne, FR |
|---|
| Year: | 2018 |
|---|
| Journal: | Proceedings of Odyssey: The Speaker and Language Recognition Workshop, Vol. 2018, No. 6, 4 Rue des Fauvettes - Lous Tourils, F-66390 BAIXAS, FR |
|---|
| ISSN: | 2312-2846 |
|---|
| DOI: | 10.21437/Odyssey.2018-21 |
|---|
| Publisher: | International Speech Communication Association |
|---|
| URL: | http://www.fit.vutbr.cz/research/groups/speech/publi/2018/diez_odyssey2018_63.pdf [PDF] |
|---|
| Keywords |
|---|
| Speaker diarization, speaker recognition |
| Annotation |
|---|
| Nowadays, most speaker diarization methods address the
task in two steps: segmentation of the input conversation into
(preferably) speaker homogeneous segments, and clustering.
Generally, different models and techniques are used for the two
steps. In this paper we present a very elegant approach where a
straightforward and efficient Variational Bayes (VB) inference
in a single probabilistic model addresses the complete SD problem.
Our model is a Bayesian Hidden Markov Model, in which
states represent speaker specific distributions and transitions between
states represent speaker turns. As in the ivector or JFA
models, speaker distributions are modeled by GMMs with parameters
constrained by eigenvoice priors. This allows to robustly
estimate the speaker models from very short speech segments.
The model, which was released as open source code
and has already been used by several labs, is fully described
for the first time in this paper. We present results and the system
is compared and combined with other state-of-the-art approaches.
The model provides the best results reported so far
on the CALLHOME dataset. |
| BibTeX: |
|---|
@INPROCEEDINGS{
author = {Mireia S{\'{a}}nchez Diez and Luk{\'{a}}{\v{s}}
Burget and Pavel Mat{\v{e}}jka},
title = {Speaker Diarization based on Bayesian HMM with
Eigenvoice Priors},
pages = {147--154},
booktitle = {Proceedings of Odyssey 2018},
journal = {Proceedings of Odyssey: The Speaker and Language Recognition
Workshop},
volume = 2018,
number = 6,
year = 2018,
location = {Les Sables dOlonne, FR},
publisher = {International Speech Communication Association},
ISSN = {2312-2846},
doi = {10.21437/Odyssey.2018-21},
language = {english},
url = {http://www.fit.vutbr.cz/research/view_pub.php.en.iso-8859-2?id=11786}
} |
|
Faculty of Information Technology