Non-linear PLDA for i-vector speaker verification

Novoselov, Sergey; Pekhovsky, Timur; Kudashev, Oleg; Mendelev, Valentin; Prudnikov, Alexey

doi:10.21437/interspeech.2015-87

Cited by 36 publications

(13 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the front-end level, let us mention for example using NN bottleneck features (BNF) instead of conventional Mel Frequency Cepstral Coefficients (MFCC, Lozano-Diez et al, 2016) or simply concatenating BNF and MFCCs (Matějka et al, 2016) which greatly improves the performance and increases system robustness. Higher in the modeling pipeline, NN acoustic models can be used instead of Gaussian Mixture Models (GMM) for extraction of sufficient statistics (Lei et al, 2014) or for either complementing PLDA (Novoselov et al, 2015;Bhattacharya et al, 2016) or replacing it (Ghahabi and Hernando, 2014).…”

Section: Introductionmentioning

confidence: 99%

Analysis of DNN Speech Signal Enhancement for Robust Speaker Recognition

Novotny

Plchot

Glembek

et al. 2019

Computer Speech & Language

View full text Add to dashboard Cite

In this work, we present an analysis of a DNN-based autoencoder for speech enhancement, dereverberation and denoising. The target application is a robust speaker verification (SV) system. We start our approach by carefully designing a data augmentation process to cover wide range of acoustic conditions and obtain rich training data for various components of our SV system. We augment several well-known databases used in SV with artificially noised and reverberated data and we use them to train a denoising autoencoder (mapping noisy and reverberated speech to its clean version) as well as an x-vector extractor which is currently considered as state-of-the-art in SV. Later, we use the autoencoder as a preprocessing step for text-independent SV system. We compare results achieved with autoencoder enhancement, multi-condition PLDA training and their simultaneous use. We present a detailed analysis with various conditions of NIST SRE 2010, 2016, PRISM and with re-transmitted data. We conclude that the proposed preprocessing can significantly improve both i-vector and x-vector baselines and that this technique can be used to build a robust SV system for various target domains.

show abstract

Section: Introductionmentioning

confidence: 99%

Analysis of DNN Speech Signal Enhancement for Robust Speaker Recognition

Novotny

Plchot

Glembek

et al. 2019

Computer Speech & Language

View full text Add to dashboard Cite

show abstract

“…Most of the attempts have replaced or improved one of the components of an i-vector + PLDA system (feature extraction, calculation of sufficient statistics, i-vector extraction or PLDA) with a neural network. As examples, let us mention: using NN bottleneck features instead of conventional MFCC features [1], NN acoustic models replacing Gaussian Mixture Models for extraction of sufficient statistics [2], NNs for either complementing PLDA [3,4] or replacing it [5]. More ambitiously, NNs that take the frame level features of an utterance as input and directly produce an utterance level representation-usually referred to as an embedding-have in the past two years almost replaced the generative i-vector approach in text independent speaker recognition [6,7,8,9,10,11,12].…”

Section: Introductionmentioning

confidence: 99%

Factorization of Discriminatively Trained i-Vector Extractor for Speaker Recognition

Novotny¹,

Plchot

Glembek

et al. 2019

Interspeech 2019

View full text Add to dashboard Cite

In this work, we continue in our research on i-vector extractor for speaker verification (SV) and we optimize its architecture for fast and effective discriminative training. We were motivated by computational and memory requirements caused by the large number of parameters of the original generative ivector model. Our aim is to preserve the power of the original generative model, and at the same time focus the model towards extraction of speaker-related information. We show that it is possible to represent a standard generative i-vector extractor by a model with significantly less parameters and obtain similar performance on SV tasks. We can further refine this compact model by discriminative training and obtain i-vectors that lead to better performance on various SV benchmarks representing different acoustic domains.

show abstract

“…This work investigates prominent techniques from speaker recognition field combined with face recognition and general deep learning science to bring new thoughts on how speaker recognition systems can be developed. I-vector-based systems are well known to be state-of-the-art solutions to the text-independent speaker verification problem [1,2,3]. The i-vector framework has inspired deep learning system design in this field.…”

Section: Introductionmentioning

confidence: 99%

On deep speaker embeddings for text-independent speaker recognition

Novoselov¹,

Shulipa²,

Kremnev³

et al. 2018

The Speaker and Language Recognition Workshop (Odyssey 2018)

Self Cite

View full text Add to dashboard Cite

We investigate deep neural network performance in the textindependent speaker recognition task. We demonstrate that using angular softmax activation at the last classification layer of a classification neural network instead of a simple softmax activation allows to train a more generalized discriminative speaker embedding extractor. Cosine similarity is an effective metric for speaker verification in this embedding space. We also address the problem of choosing an architecture for the extractor. We found that deep networks with residual frame level connections outperform wide but relatively shallow architectures. This paper also proposes several improvements for previous DNN-based extractor systems to increase the speaker recognition accuracy. We show that the discriminatively trained similarity metric learning approach outperforms the standard LDA-PLDA method as an embedding backend. The results obtained on Speakers in the Wild and NIST SRE 2016 evaluation sets demonstrate robustness of the proposed systems when dealing with close to real-life conditions.

show abstract

Non-linear PLDA for i-vector speaker verification

Cited by 36 publications

References 6 publications

Analysis of DNN Speech Signal Enhancement for Robust Speaker Recognition

Analysis of DNN Speech Signal Enhancement for Robust Speaker Recognition

Factorization of Discriminatively Trained i-Vector Extractor for Speaker Recognition

On deep speaker embeddings for text-independent speaker recognition

Contact Info

Product

Resources

About