Variational Bayesian speaker diarization of meeting recordings

Valente, Fabio; Motlíček, Petr; Vijayasenan, Deepu

doi:10.1109/icassp.2010.5495087

Cited by 22 publications

(14 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Triplet-loss network has been successfully used for speaker diarization and speaker recognition [12,11,16,17]. During training, three utterances, referred to as triplet, τ = (X a , X p , X n ) are fed as input.…”

Section: Triplet-lossmentioning

confidence: 99%

DNN Based Speaker Embedding Using Content Information for Text-Dependent Speaker Verification

Dey

Koshinaka²,

Motlíček

et al. 2018

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

In this paper, we are interested in exploring Deep Neural Network (DNN) based speaker embedding for Random-digit task using content information. To this end, a technique is applied to automatically select common phonetic units between the enrollment and test data to produce speaker verification scores. Furthermore, a novel approach is proposed to incorporate content information in the DNN directly. It is hypothesized that features extracted using this DNN will be helpful for the task. Experiments on the RSR dataset show that the proposed method outperforms the baseline i-vector system by 43% relative equal error rate.

show abstract

Section: Triplet-lossmentioning

confidence: 99%

DNN Based Speaker Embedding Using Content Information for Text-Dependent Speaker Verification

Dey

Koshinaka²,

Motlíček

et al. 2018

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Other approaches make use of relationships among multiple segments in a limited area, e.g., Mean-Shift (MS) [27][28][29][30][31]. Decisions can also be made keeping in mind all the acoustic segments, as Kmeans [7,32], variational Bayes [33], and fully Bayesian PLDAs [8,9,34].…”

Section: Speaker Diarization State Of the Artmentioning

confidence: 99%

Unsupervised adaptation of PLDA models for broadcast diarization

Viñals

Giménez

Villalba

et al. 2019

J AUDIO SPEECH MUSIC PROC.

View full text Add to dashboard Cite

We present a novel model adaptation approach to deal with data variability for speaker diarization in a broadcast environment. Expensive human annotated data can be used to mitigate the domain mismatch by means of supervised model adaptation approaches. By contrast, we propose an unsupervised adaptation method which does not need for in-domain labeled data but only the recording that we are diarizing. We rely on an inner adaptation block which combines Agglomerative Hierarchical Clustering (AHC) and Mean-Shift (MS) clustering techniques with a Fully Bayesian Probabilistic Linear Discriminant Analysis (PLDA) to produce pseudo-speaker labels suitable for model adaptation. We propose multiple adaptation approaches based on this basic block, including unsupervised and semi-supervised. Our proposed solutions, analyzed with the Multi-Genre Broadcast 2015 (MGB) dataset, reported significant improvements (16% relative improvement) with respect to the baseline, also outperforming a supervised adaptation proposal with low resources (9% relative improvement). Furthermore, our proposed unsupervised adaptation is totally compatible with a supervised one. The joint use of both adaptation techniques (supervised and unsupervised) shows a 13% relative improvement with respect to only considering the supervised adaptation.

show abstract

“…In recent years, meeting speech recognition (Maganti et al, 2007;Nasu et al, 2011) and meeting speaker diarization (Boakye et al, 2008;Ben-Harush et al, 2009;Stolcke et al, 2010;Sun et al, 2010;Valente et al, 2010;Vijayasenan et al, 2010;Boakye et al, 2011;Stolcke, 2011;Valente et al, 2011;Yella et al, 2011;Vijayasenan et al, 2012;Zwyssig et al, 2012) have been effectively utilized to transcribe and browse meeting procedures. However, their performance is usually low at the overlapped speech segments where more than one speaker is speaking.…”

Section: Introductionmentioning

confidence: 99%

Detection of overlapped speech using lapel microphones in meeting

Yokoyama

Nasu

Iwano

et al. 2013

Speech Communication

View full text Add to dashboard Cite

We propose an overlapped speech detection method for speech recognition and speaker diarization of meetings, where each speaker wears a lapel microphone. Two novel features are utilized as inputs for a GMM-based detector. One is speech power after cross-channel spectral subtraction which reduces the power from the other speakers. The other is an amplitude spectral cosine correlation coefficient which effectively extracts the correlation of spectral components in a rather quiet condition. We evaluated our method using a meeting speech corpus of four speakers. The accuracy of our proposed method, 75.7%, was significantly better than that of the conventional method, 66.8%, which uses raw speech power and power spectral Pearson's correlation coefficient.

show abstract

Variational Bayesian speaker diarization of meeting recordings

Cited by 22 publications

References 6 publications

DNN Based Speaker Embedding Using Content Information for Text-Dependent Speaker Verification

DNN Based Speaker Embedding Using Content Information for Text-Dependent Speaker Verification

Unsupervised adaptation of PLDA models for broadcast diarization

Detection of overlapped speech using lapel microphones in meeting

Contact Info

Product

Resources

About