Robust and Discriminative Speaker Embedding via Intra-Class Distance Variance Regularization

Le, Nam; Odobez, Jean-Marc

doi:10.21437/interspeech.2018-1685

Cited by 22 publications

(17 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…with some previous works on the same dataset. EER (%) GMM-UBM [35] 15.0 I-vectors + PLDA [35] 8.8 CNN [35] 7.8 CNN + intra-class + triplet loss [43] 7.9 SincNet [21] 7.2 SincNet+LIM (proposed) 5.8 Table 3: Equal Error Rate (EER%) obtained on speaker verification (using the VoxCeleb corpus).…”

Section: Speaker Verificationmentioning

confidence: 99%

Learning Speaker Representations with Mutual Information

Ravanelli

Bengio

2019

Interspeech 2019

View full text Add to dashboard Cite

Learning good representations is of crucial importance in deep learning. Mutual Information (MI) or similar measures of statistical dependence are promising tools for learning these representations in an unsupervised way. Even though the mutual information between two random variables is hard to measure directly in high dimensional spaces, some recent studies have shown that an implicit optimization of MI can be achieved with an encoder-discriminator architecture similar to that of Generative Adversarial Networks (GANs).In this work, we learn representations that capture speaker identities by maximizing the mutual information between the encoded representations of chunks of speech randomly sampled from the same sentence. The proposed encoder relies on the SincNet architecture and transforms raw speech waveform into a compact feature vector. The discriminator is fed by either positive samples (of the joint distribution of encoded chunks) or negative samples (from the product of the marginals) and is trained to separate them.We report experiments showing that this approach effectively learns useful speaker representations, leading to promising results on speaker identification and verification tasks. Our experiments consider both unsupervised and semi-supervised settings and compare the performance achieved with different objective functions.

show abstract

Section: Speaker Verificationmentioning

confidence: 99%

Learning Speaker Representations with Mutual Information

Ravanelli

Bengio

2019

Interspeech 2019

View full text Add to dashboard Cite

show abstract

“…Extended ResNet implementation from [15] named dilated residual network (DltResNet) is used as the third speaker 10 Kaldi GitHub: https://github.com/kaldi-asr/kaldi verification methods. The implementation is publicly available 11 .…”

Section: ) Dilated Residual Network (Dltresnet)mentioning

confidence: 99%

Multilingual Audio-Visual Smartphone Dataset And Evaluation

Mandalapu¹,

N²,

Ramachandra³

et al. 2021

Preprint

View full text Add to dashboard Cite

Smartphones have been employed with biometric-based verification systems to provide security in highly sensitive applications. Audio-visual biometrics are getting popular due to the usability and also it will be challenging to spoof because of multi-modal nature. In this work, we present an audiovisual smartphone dataset captured in five different recent smartphones. This new dataset contains 103 subjects captured in three different sessions considering the different real-world scenarios. Three different languages are acquired in this dataset to include the problem of language dependency of the speaker recognition systems. These unique characteristics of this dataset will pave the way to implement novel state-of-the-art unimodal or audio-visual speaker recognition systems. We also report the performance of the bench-marked biometric verification systems on our dataset. The robustness of biometric algorithms is evaluated towards multiple dependencies like signal noise, device, language and presentation attacks like replay and synthesized signals with extensive experiments. The obtained results raised many concerns about the generalization properties of state-of-the-art biometrics methods in smartphones.

show abstract

“…In [219], a complementary optimizing goal called intra-class loss is proposed to improve deep speaker embeddings learned with triplet loss. It is shown in the paper that models trained using intra-class loss can yield a significant relative reduction of 30% in equal error rate (EER) compared to the original triplet loss.…”

Section: Deep Learning Work On Voice Recognitionmentioning

confidence: 99%

Biometrics Recognition Using Deep Learning: A Survey

Minaee¹,

Abdolrashidi²,

Su³

et al. 2019

Preprint

View full text Add to dashboard Cite

Deep learning-based models have been very successful in achieving state-of-the-art results in many of the computer vision, speech recognition, and natural language processing tasks in the last few years. These models seem a natural fit for handling the everincreasing scale of biometric recognition problems, from cellphone authentication to airport security systems. Deep learning-based models have increasingly been leveraged to improve the accuracy of different biometric recognition systems in recent years. In this work, we provide a comprehensive survey of more than 120 promising works on biometric recognition (including face, fingerprint, iris, palmprint, ear, voice, signature, and gait recognition), which deploy deep learning models, and show their strengths and potentials in different applications. For each biometric, we first introduce the available datasets that are widely used in the literature and their characteristics. We will then talk about several promising deep learning works developed for that biometric, and show their performance on popular public benchmarks. We will also discuss some of the main challenges while using these models for biometric recognition, and possible future directions to which research in this area is headed.

show abstract

Robust and Discriminative Speaker Embedding via Intra-Class Distance Variance Regularization

Cited by 22 publications

References 18 publications

Learning Speaker Representations with Mutual Information

Learning Speaker Representations with Mutual Information

Multilingual Audio-Visual Smartphone Dataset And Evaluation

Biometrics Recognition Using Deep Learning: A Survey

Contact Info

Product

Resources

About