A Novel Learnable Dictionary Encoding Layer for End-to-End Language Identification

Cai, Weicheng; Cai, Zexin; Zhang, Xiang; Wang, Xiaoqi; Li, Ming

doi:10.1109/icassp.2018.8462025

Cited by 64 publications

(48 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Self-attentive pooling layer [20], learnable dictionary encoding layer [21], and dictionary-based NetVLAD layer [22,23] are other commonly used encoding layers. Once the utterance-level representation is extracted, a fully connected layer and a speaker classifier are employed to further abstract the speaker representation and classify the training speakers.…”

Section: Revisit: Deep Speaker Embeddingmentioning

confidence: 99%

Within-Sample Variability-Invariant Loss for Robust Speaker Recognition Under Noisy Environments

Cai

2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

Despite the significant improvements in speaker recognition enabled by deep neural networks, unsatisfactory performance persists under noisy environments. In this paper, we train the speaker embedding network to learn the "clean" embedding of the noisy utterance. Specifically, the network is trained with the original speaker identification loss with an auxiliary within-sample variability-invariant loss. This auxiliary variability-invariant loss is used to learn the same embedding among the clean utterance and its noisy copies and prevents the network from encoding the undesired noises or variabilities into the speaker representation. Furthermore, we investigate the data preparation strategy for generating clean and noisy utterance pairs on-the-fly. The strategy generates different noisy copies for the same clean utterance at each training step, helping the speaker embedding network generalize better under noisy environments. Experiments on VoxCeleb1 indicate that the proposed training framework improves the performance of the speaker verification system in both clean and noisy conditions.

show abstract

Section: Revisit: Deep Speaker Embeddingmentioning

confidence: 99%

Within-Sample Variability-Invariant Loss for Robust Speaker Recognition Under Noisy Environments

Cai

2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

show abstract

“…On the other hand, traditional methods for speaker and language identification such as i-vector systems have explored the use of statistical or dictionary-based methods for aggregation. A number of recent works have proposed to bring similar methods to deep speaker recognition [11,12,13,14,15] (described in Sec. 1.1).…”

Section: Introductionmentioning

confidence: 99%

Utterance-level Aggregation for Speaker Recognition in the Wild

Xie

Nagrani

Chung

et al. 2019

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

260

245

View full text Add to dashboard Cite

The objective of this paper is speaker recognition 'in the wild' -where utterances may be of variable length and also contain irrelevant signals. Crucial elements in the design of deep networks for this task are the type of trunk (frame level) network, and the method of temporal aggregation. We propose a powerful speaker recognition deep network, using a 'thin-ResNet' trunk architecture, and a dictionary-based NetVLAD or GhostVLAD layer to aggregate features across time, that can be trained end-to-end. We show that our network achieves state of the art performance by a significant margin on the VoxCeleb1 test set for speaker recognition, whilst requiring fewer parameters than previous methods. We also investigate the effect of utterance length on performance, and conclude that for 'in the wild' data, a longer length is beneficial.

show abstract

“…We implemented two variants of SENets: SEnet34 with ResNet34 backbone, and SEnet50 with ResNet50 backbone. Mean-Std ResNet: Recent work in speaker recognition [29,30] has demonstrated that ResNet [27] with pooling achieves comparable results as x-vectors [31]. Therefore, we introduced ResNet with pooling for anti-spoofing.…”

Section: Dnn Modelmentioning

confidence: 99%

ASSERT: Anti-Spoofing with Squeeze-Excitation and Residual Networks

et al. 2019

View full text Add to dashboard Cite

We present JHU's system submission to the ASVspoof 2019 Challenge: Anti-Spoofing with Squeeze-Excitation and Residual neTworks (ASSERT). Anti-spoofing has gathered more and more attention since the inauguration of the ASVspoof Challenges, and ASVspoof 2019 dedicates to address attacks from all three major types: text-to-speech, voice conversion, and replay. Built upon previous research work on Deep Neural Network (DNN), ASSERT is a pipeline for DNN-based approach to anti-spoofing. ASSERT has four components: feature engineering, DNN models, network optimization and system combination, where the DNN models are variants of squeeze-excitation and residual networks. We conducted an ablation study of the effectiveness of each component on the ASVspoof 2019 corpus, and experimental results showed that ASSERT obtained more than 93% and 17% relative improvements over the baseline systems in the two sub-challenges in ASVspooof 2019, ranking ASSERT one of the top performing systems. Code and pretrained models will be made publicly available.

show abstract

A Novel Learnable Dictionary Encoding Layer for End-to-End Language Identification

Cited by 64 publications

References 23 publications

Within-Sample Variability-Invariant Loss for Robust Speaker Recognition Under Noisy Environments

Within-Sample Variability-Invariant Loss for Robust Speaker Recognition Under Noisy Environments

Utterance-level Aggregation for Speaker Recognition in the Wild

ASSERT: Anti-Spoofing with Squeeze-Excitation and Residual Networks

Contact Info

Product

Resources

About