End-to-end framework for spoof-aware speaker verification

Kang, Woohyun; Alam, Md Jahangir; Fathan, Abderrahim

doi:10.21437/interspeech.2022-139

Cited by 3 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3) End-to-End systems. There are several papers describing the second [21], [22] and the third [23], [24] methods; however, the first method usually outperforms others, although it is much simpler in implementation. The fusion approach was described in [21], [22], [25]- [29].…”

Section: Sasvmentioning

confidence: 99%

RawSpectrogram: On the Way to Effective Streaming Speech Anti-Spoofing

Grinberg,

Shikhov

2023

IEEE Access

View full text Add to dashboard Cite

Traditional anti-spoofing systems cannot be used straightforwardly with streaming audio because they are designed for finite utterances. Such offline models can be applied in streaming with the help of buffering; however, they are not effective in terms of memory and computational consumption. We propose a novel approach called RawSpectrogram that makes offline models streaming-friendly without a significant drop in quality. The method was tested on RawNet2 and AASIST, resulting in new architectures called RawRNN (RawLSTM and RawGRU), RS-AASIST, and TAASIST. The RawRNN-type models are much smaller and achieve a better Equal Error Rate than their base architecture, RawNet2. RS-AASIST and TAASIST have fewer parameters than AASIST and achieve similar quality. We also proved our concept for models with time-frequency transform front-ends and automatic speaker verification systems by proposing RECAPA-TDNN based on ECAPA-TDNN. RS-AASIST and RECAPA-TDNN were combined into the first streaming-friendly spoofing-aware speaker verification system reported in the literature. This joint system achieves significantly better quality than the corresponding offline solutions. All our models require far fewer floating-point operations for score updates. RawSpectrogram usage significantly reduces the latency of the prediction and allows the system to update the probability with each new chunk from the stream, preserving all information from the past. To the best of our knowledge, TAASIST is the most successful voice anti-spoofing system that employs a vanilla Transformer trained using supervised learning.

show abstract

Section: Sasvmentioning

confidence: 99%

RawSpectrogram: On the Way to Effective Streaming Speech Anti-Spoofing

Grinberg,

Shikhov

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Ensembles of multiple CM models in multi-modal fashion are studied in [17]. End-to-end joint solutions with contrastive speaker verification loss and mixup [51] training scheme are proposed in [52].…”

Section: Spoof-aware Speaker Verificationmentioning

confidence: 99%

Learnable MFCCs for Speaker Verification

Liu

Sahidullah

Kinnunen

2021

2021 IEEE International Symposium on Circuits and Systems (ISCAS)

View full text Add to dashboard Cite

We propose a learnable mel-frequency cepstral coefficients (MFCCs) front-end architecture for deep neural network (DNN) based automatic speaker verification. Our architecture retains the simplicity and interpretability of MFCC-based features while allowing the model to be adapted to data flexibly. In practice, we formulate data-driven version of four linear transforms in a standard MFCC extractor -windowing, discrete Fourier transform (DFT), mel filterbank and discrete cosine transform (DCT). Results reported reach up to 6.7% (VoxCeleb1) and 9.7% (SITW) relative improvement in term of equal error rate (EER) from static MFCCs, without additional tuning effort.Index Terms-Speaker verification, feature extraction, melfrequency cesptral coefficients (MFCCs).

show abstract