PF-Net: Personalized Filter for Speaker Recognition from Raw Waveform
Preprint
Abstract
Speaker recognition using i-vector has been replaced by speaker recognition using deep learning. Speaker recognition based on Convolutional Neural Networks (CNNs) has been widely used in recent years, which learn low-level speech representations from raw waveforms. On this basis, a CNN architecture called SincNet proposes a kind of unique convolutional layer, which has achieved band-pass filters. Compared with standard CNNs, SincNet learns the low and high cut-off frequencies of each filter. This paper proposes an improved CNNs architecture called PF-Net, which encourages the first convolutional layer to implement more personalized filters than SincNet. PF-Net parameterizes the frequency domain shape and can realize band-pass filters by learning some deformation points in frequency domain. Compared with standard CNN, PF-Net can learn the characteristics of each filter. Compared with SincNet, PF-Net can learn more characteristic parameters, instead of only low and high cut-off frequencies. This provides a personalized filter bank for different tasks. As a result, our experiments show that the PF-Net converges faster than standard CNN and performs better than SincNet. Our code is available at github.com/TAN-OpenLab/PF-NET.Keywords
All Related Versions
This publication has 30 references indexed in Scilit:
- Speaker Recognition based on Mel-Frequency Cepstral Coefficients and Vector Quantization2021
- Towards Directly Modeling Raw Speech Signal for Speaker Verification Using CNNS2018
- Language diarization for semi-supervised bilingual acoustic model training2017
- Speaker verification with short utterances: a review of challenges, trends and opportunitiesIET Biometrics, 2017
- Deep neural networks for small footprint text-dependent speaker verification2014
- Comparative study of automatic speech recognition techniquesIET Signal Processing, 2013
- Modeling prosodic feature sequences for speaker recognitionSpeech Communication, 2005
- Speaker Verification Using Adapted Gaussian Mixture ModelsDigital Signal Processing, 2000
- Speaker recognition with a MLP classifier and LPCC codebook1999
- An Overview of Speaker Recognition Technology1996