Related papers: Bayesian Learning for Deep Neural Network Adaptati…
This work presents a broad study on the adaptation of neural network acoustic models by means of learning hidden unit contributions (LHUC) -- a method that linearly re-combines hidden units in a speaker- or environment-dependent manner…
Discriminative training techniques define state-of-the-art performance for automatic speech recognition systems. However, they are inherently prone to overfitting, leading to poor generalization performance when using limited training data.…
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…
This paper investigates a self-adaptation method for speech enhancement using auxiliary speaker-aware features; we extract a speaker representation used for adaptation directly from the test utterance. Conventional studies of deep neural…
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…
A speaker cluster-based speaker adaptive training (SAT) method under deep neural network-hidden Markov model (DNN-HMM) framework is presented in this paper. During training, speakers that are acoustically adjacent to each other are…
The performance of automatic speech recognition systems can be improved by adapting an acoustic model to compensate for the mismatch between training and testing conditions, for example by adapting to unseen speakers. The success of speaker…
Most neural-network based speaker-adaptive acoustic models for speech synthesis can be categorized into either layer-based or input-code approaches. Although both approaches have their own pros and cons, most existing works on speaker…
Speaker adaptation aims to estimate a speaker specific acoustic model from a speaker independent one to minimize the mismatch between the training and testing conditions arisen from speaker variabilities. A variety of neural network…
Rich sources of variability in natural speech present significant challenges to current data intensive speech recognition technologies. To model both speaker and environment level diversity, this paper proposes a novel Bayesian factorised…
In this work, we aim to establish a Bayesian adaptive learning framework by focusing on estimating latent variables in deep neural network (DNN) models. Latent variables indeed encode both transferable distributional information and…
The development of deep neural networks (DNN) has significantly enhanced the performance of speaker verification (SV) systems in recent years. However, a critical issue that persists when applying DNN-based SV systems in practical…
Learned feature representations and sub-phoneme posteriors from Deep Neural Networks (DNNs) have been used separately to produce significant performance gains for speaker and language recognition tasks. In this work we show how these gains…
The promising performance of Deep Learning (DL) in speech recognition has motivated the use of DL in other speech technology applications such as speaker recognition. Given i-vectors as inputs, the authors proposed an impostor selection…
This paper proposes novel algorithms for speaker embedding using subjective inter-speaker similarity based on deep neural networks (DNNs). Although conventional DNN-based speaker embedding such as a $d$-vector can be applied to…
We present a deep neural network (DNN) acoustic model that includes parametrised and differentiable pooling operators. Unsupervised acoustic model adaptation is cast as the problem of updating the decision boundaries implemented by each…
Automatic recognition of disordered speech remains a highly challenging task to date. Sources of variability commonly found in normal speech including accent, age or gender, when further compounded with the underlying causes of speech…
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…
We propose a novel adversarial speaker adaptation (ASA) scheme, in which adversarial learning is applied to regularize the distribution of deep hidden features in a speaker-dependent (SD) deep neural network (DNN) acoustic model to be close…
Despite speaker verification has achieved significant performance improvement with the development of deep neural networks, domain mismatch is still a challenging problem in this field. In this study, we propose a novel framework to…