Blind Extraction of Moving Audio Source in a Challenging Environment Supported by Speaker Identification Via X-Vectors

Málek, Jiřı́; Janský, Jakub; Kounovsky, Tomas; Koldovsky, Zbynek; Žďánský, Jindřich

doi:10.1109/icassp39728.2021.9414331

Cited by 3 publications

(9 citation statements)

References 20 publications

(31 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Consequently, this allows us to achieve a higher extraction accuracy. This higher accuracy was proven theoretically in [41] and demonstrated experimentally in [42].…”

Section: Introductionmentioning

confidence: 62%

Target Speech Extraction: Independent Vector Extraction Guided by Supervised Speaker Identification

Málek

Janský

Koldovsky

et al. 2022

IEEE/ACM Trans. Audio Speech Lang. Process.

Self Cite

View full text Add to dashboard Cite

This manuscript proposes a novel robust procedure for the extraction of a speaker of interest (SOI) from a mixture of audio sources. The estimation of the SOI is performed via independent vector extraction (IVE). Since the blind IVE cannot distinguish the target source by itself, it is guided towards the SOI via frame-wise speaker identification based on deep learning. Still, an incorrect speaker can be extracted due to guidance failings, especially when processing challenging data. To identify such cases, we propose a criterion for nonintrusively assessing the estimated speaker. It utilizes the same model as the speaker identification, so no additional training is required. When incorrect extraction is detected, we propose a "deflation" step in which the incorrect source is subtracted from the mixture and, subsequently, another attempt to extract the SOI is performed. The process is repeated until successful extraction is achieved. The proposed procedure is experimentally tested on artificial and real-world datasets containing challenging phenomena: source movements, reverberation, transient noise, or microphone failures. The method is compared with state-of-theart blind algorithms as well as with current fully supervised deep learning-based methods.

show abstract

“…Consequently, this allows us to achieve a higher extraction accuracy. This higher accuracy was proven theoretically in [41] and demonstrated experimentally in [42].…”

Section: Introductionmentioning

confidence: 62%

Target Speech Extraction: Independent Vector Extraction Guided by Supervised Speaker Identification

Málek

Janský

Koldovsky

et al. 2022

IEEE/ACM Trans. Audio Speech Lang. Process.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Consequently, this allows us to achieve a higher extraction accuracy. This higher accuracy was proven theoretically in [29] and demonstrated experimentally in [30].…”

Section: Introductionmentioning

confidence: 62%

“…It demonstrates the benefits of the CSV-model on mixtures with moving sources and the ability of g XVEC to direct the extraction towards the SOI. The results of CSV-AuxIVE are compared to the fully static (FS-IVE, [24]) and the block-wise static (BS-IVE, [30]) variants of AuxIVE.…”

Section: Csv Model For Extraction Of a Moving Soimentioning

confidence: 99%

“…The core of the method is an IVE algorithm endowed with the CSV mixing model. It focuses on the SOI using piloting based on the frame-wise speaker identification, similar to our previous works [27], [30]. An improvement for piloting is proposed by incorporation of a non-intrusive criterion for assessment of the extraction performance.…”

Section: Introductionmentioning

confidence: 96%

“…The utilized network topology does not differ from our previous works in[27],[30]. There we described the embedding network as TDNN with modifications.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Target Speech Extraction: Independent Vector Extraction Guided by Supervised Speaker Identification

Málek¹,

Janský²,

Koldovsky³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

This manuscript proposes a novel robust procedure for extraction of a speaker of interest (SOI) from a mixture of audio sources. The estimation of the SOI is blind, performed via independent vector extraction. A recently proposed constant separating vector (CSV) model is employed, which improves the estimation of moving sources. The blind algorithm is guided towards the SOI via the frame-wise speaker identification, which is trained in a supervised manner and is independent of a specific scenario. When processing challenging data, an incorrect speaker may be extracted due to limitations of this guidance. To identify such cases, a criterion non-intrusively assessing quality of the estimated SOI is proposed. It utilizes the same model as the speaker identification; no additional training is therefore required. Using this criterion, the "deflation" approach to extraction is presented. If an incorrect source is estimated, it is subtracted from the mixture and the extraction of the SOI is performed again from the reduced mixture. The proposed procedure is experimentally tested on both artificial and realworld datasets containing challenging phenomena: source movements, reverberation, transient noise or microphone failures. The presented method is comparable to the state-of-the-art blind algorithms on static mixtures; it is more accurate for mixtures containing source movements. Compared to fully supervised methods, the proposed procedure achieves a lower level of accuracy but requires no scenario-specific data for the training.

show abstract

Online Speaker Diarization Using Optimized SE-ResNet Architecture

Kynych,

Zdansky,

Cerva

et al. 2023

Text, Speech, and Dialogue

View full text Add to dashboard Cite

Blind Extraction of Moving Audio Source in a Challenging Environment Supported by Speaker Identification Via X-Vectors

Cited by 3 publications

References 20 publications

Target Speech Extraction: Independent Vector Extraction Guided by Supervised Speaker Identification

Target Speech Extraction: Independent Vector Extraction Guided by Supervised Speaker Identification

Target Speech Extraction: Independent Vector Extraction Guided by Supervised Speaker Identification

Online Speaker Diarization Using Optimized SE-ResNet Architecture

Contact Info

Product

Resources

About