Related papers: A Bayesian Approach to Estimation of Speaker Norma…
In this letter, we propose a vocal tract length (VTL) perturbation method for text-dependent speaker verification (TD-SV), in which a set of TD-SV systems are trained, one for each VTL factor, and score-level fusion is applied to make a…
State-of-the-art neural language models (LMs) represented by Transformers are highly complex. Their use of fixed, deterministic parameter estimates fail to account for model uncertainty and lead to over-fitting and poor generalization when…
State-of-the-art neural network language models (NNLMs) represented by long short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming highly complex. They are prone to overfitting and poor generalization when…
In this article, we first establish the theory of optimal scores for speaker recognition. Our analysis shows that the minimum Bayes risk (MBR) decisions for both the speaker identification and speaker verification tasks can be based on a…
A key task for speech recognition systems is to reduce the mismatch between training and evaluation data that is often attributable to speaker differences. Speaker adaptation techniques play a vital role to reduce the mismatch. Model-based…
Most speaker verification tasks are studied as an open-set evaluation scenario considering the real-world condition. Thus, the generalization power to unseen speakers is of paramount important to the performance of the speaker verification…
This paper presents a speech enhancement method, where an adaptive threshold is statistically determined based on Gaussian modeling of Teager energy (TE) operated perceptual wavelet packet (PWP) coefficients of noisy speech. In order to…
While the use of deep neural networks has significantly boosted speaker recognition performance, it is still challenging to separate speakers in poor acoustic environments. Here speech enhancement methods have traditionally allowed improved…
For speaker recognition, it is difficult to extract an accurate speaker representation from speech because of its mixture of speaker traits and content. This paper proposes a disentanglement framework that simultaneously models speaker…
Traditional speech enhancement techniques modify the magnitude of a speech in time-frequency domain, and use the phase of a noisy speech to resynthesize a time domain speech. This work proposes a complex-valued Gaussian process latent…
Deep speaker embedding has demonstrated state-of-the-art performance in speaker recognition tasks. However, one potential issue with this approach is that the speaker vectors derived from deep embedding models tend to be non-Gaussian for…
In this paper, we propose several methods that incorporate vocal tract length (VTL) warped features for spoken keyword spotting (KWS). The first method, VTL-independent KWS, involves training a single deep neural network (DNN) that utilizes…
Deep speaker embedding represents the state-of-the-art technique for speaker recognition. A key problem with this approach is that the resulting deep speaker vectors tend to be irregularly distributed. In previous research, we proposed a…
In recent years there have been many deep learning approaches towards the multi-speaker source separation problem. Most use Long Short-Term Memory - Recurrent Neural Networks (LSTM-RNN) or Convolutional Neural Networks (CNN) to model the…
Disentangling speaker and content attributes of a speech signal into separate latent representations followed by decoding the content with an exchanged speaker representation is a popular approach for voice conversion, which can be trained…
We propose a variational Bayesian (VB) approach to learning distributions of latent variables in deep neural network (DNN) models for cross-domain knowledge transfer, to address acoustic mismatches between training and testing conditions.…
Speaker adaptation methods aim to create fair quality synthesis speech voice font for target speakers while only limited resources available. Recently, as deep neural networks based statistical parametric speech synthesis (SPSS) methods…
This paper proposes a novel Wavelet Packet based feature extraction approach for the task of text independent speaker recognition. The features are extracted by using the combination of Mel Frequency Cepstral Coefficient (MFCC) and Wavelet…
This paper presents a statistical method of single-channel speech enhancement that uses a variational autoencoder (VAE) as a prior distribution on clean speech. A standard approach to speech enhancement is to train a deep neural network…
Speaker verification systems usually suffer from the mismatch problem between training and evaluation data, such as speaker population mismatch, the channel and environment variations. In order to address this issue, it requires the system…