A Speaker Recognition System for the SITW Challenge

Kudashev, Oleg; Novoselov, Sergey; Simonchik, Konstantin; Kozlov, Alexander

doi:10.21437/interspeech.2016-1197

Cited by 10 publications

(6 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Note that when trained with augmented data, the DNNbased speaker embedding systems significantly outperform our previous i-vector-based systems on SITW protocol [37].…”

Section: Resultsmentioning

confidence: 81%

Triplet Loss Based Cosine Similarity Metric Learning for Text-independent Speaker Recognition

et al. 2018

Self Cite

View full text Add to dashboard Cite

Deep neural network based speaker embeddings become increasingly popular in the text-independent speaker recognition task. In contrast to a generatively trained i-vector extractor, a DNN speaker embedding extractor is usually trained discriminatively in the closed set classification scenario using softmax. The problem we addressed in the paper is choosing a dnn based speaker embedding backend solution for the speaker verification scoring. There are several options to perform speaker verification in the dnn embedding space. One of them is using a simple heuristic speaker similarity metric for scoring (e.g. cosine metric). Similarly with i-vector based systems, the standard Linear Discriminant Analisys (LDA) followed by the Probabilistic Linear Discriminant Analisys (PLDA) can be used for segregating speaker information. As an alternative, the discriminative metric learning approach can be considered. This work demonstrates that performance of deep speaker embeddings based systems can be improved by using Cosine Similarity Metric Learning (CSML) with the triplet loss training scheme. Results obtained on Speakers in the Wild and NIST SRE 2016 evaluation sets demonstrate superiority and robustness of CSML based systems.

show abstract

“…Note that when trained with augmented data, the DNNbased speaker embedding systems significantly outperform our previous i-vector-based systems on SITW protocol [37].…”

Section: Resultsmentioning

confidence: 81%

Triplet Loss Based Cosine Similarity Metric Learning for Text-independent Speaker Recognition

et al. 2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…IDV and DICN approaches are applied on the out-of-domain ivector set and they are indicated as IDV-SWB and DICN-SWB respectively. For comparison with prior Autoencoderbased method, we developed DAE using out-of-domain dataset which has speaker label with 1300 nodes of single hidden layer as Kudashev's approach [23] and examined as shown in system 8.…”

Section: Performance Comparison To State-of-the-art Techniquesmentioning

confidence: 99%

“…Autoencoder based domain adaptation is widely used in machine learning community [17]- [19] and also adopted already on speech processing area [20]- [22]. Recently Kudashev [23] proposed a DAE-based denoising and domain adaptation for speaker recognition.…”

Section: Introductionmentioning

confidence: 99%

Autoencoder Based Domain Adaptation for Speaker Recognition Under Insufficient Channel Information

Shon¹,

Mun²,

Kim

et al. 2017

Interspeech 2017

View full text Add to dashboard Cite

In real-life conditions, mismatch between development and test domain degrades speaker recognition performance. To solve the issue, many researchers explored domain adaptation approaches using matched in-domain dataset. However, adaptation would be not effective if the dataset is insufficient to estimate channel variability of the domain. In this paper, we explore the problem of performance degradation under such a situation of insufficient channel information. In order to exploit limited in-domain dataset effectively, we propose an unsupervised domain adaptation approach using Autoencoder based Domain Adaptation (AEDA). The proposed approach combines an autoencoder with a denoising autoencoder to adapt resource-rich development dataset to test domain. The proposed technique is evaluated on the Domain Adaptation Challenge 13 experimental protocols that is widely used in speaker recognition for domain mismatched condition. The results show significant improvements over baselines and results from other prior studies.

show abstract

“…The performance of speaker verification degrades significantly when the speech is corrupted by interference speakers. Speaker diarization can be useful for speaker verification with nonoverlapping multi-talker speech [1][2][3][4][5][6]. It can effectively exclude unwanted speech segments when the speakers only slightly overlap [7,8].…”

Section: Introductionmentioning

confidence: 99%

Target Speaker Extraction for Multi-Talker Speaker Verification

Rao

Chng

et al. 2019

Interspeech 2019

View full text Add to dashboard Cite

The performance of speaker verification degrades significantly when the test speech is corrupted by interference from nontarget speakers. Speaker diarization separates speakers well only if the speakers are not overlapped. However, if multiple talkers speak at the same time, we need a technique to separate the speech in the spectral domain. In this paper, we study a way to extract the target speaker's speech from an overlapped multi-talker speech. Specifically, given some reference speech samples from the target speaker, the target speaker's speech is firstly extracted from the overlapped multi-talker speech, then the extracted speech is processed in the speaker verification system. Experimental results show that the proposed approach significantly improves the performance of overlapped multi-talker speaker verification and achieves 64.4% relative EER reduction over the zero-effort baseline.

show abstract

A Speaker Recognition System for the SITW Challenge

Cited by 10 publications

References 8 publications

Triplet Loss Based Cosine Similarity Metric Learning for Text-independent Speaker Recognition

Triplet Loss Based Cosine Similarity Metric Learning for Text-independent Speaker Recognition

Autoencoder Based Domain Adaptation for Speaker Recognition Under Insufficient Channel Information

Target Speaker Extraction for Multi-Talker Speaker Verification

Contact Info

Product

Resources

About