Related papers: Feature Joint-State Posterior Estimation in Factor…
In typical multi-talker speech recognition systems, a neural network-based acoustic model predicts senone state posteriors for each speaker. These are later used by a single-talker decoder which is applied on each speaker-specific output…
A Pascal challenge entitled monaural multi-talker speech recognition was developed, targeting the problem of robust automatic speech recognition against speech like noises which significantly degrades the performance of automatic speech…
Many application studies rely on audio DNN models pre-trained on a large-scale dataset as essential feature extractors, and they extract features from the last layers. In this study, we focus on our finding that the middle layer features of…
Monaural source separation is important for many real world applications. It is challenging because, with only a single channel of information available, without any constraints, an infinite number of solutions are possible. In this paper,…
Recently, neural network models for natural language processing tasks have been increasingly focused on for their ability of alleviating the burden of manual feature engineering. However, the previous neural models cannot extract the…
This paper investigates the effectiveness of factorial speech processing models in noise-robust automatic speech recognition tasks. For this purpose, the paper proposes an idealistic approach for modeling state-conditional observation…
While traditional statistical signal processing model-based methods can derive the optimal estimators relying on specific statistical assumptions, current learning-based methods further promote the performance upper bound via deep neural…
Modern automatic speaker verification relies largely on deep neural networks (DNNs) trained on mel-frequency cepstral coefficient (MFCC) features. While there are alternative feature extraction methods based on phase, prosody and long-term…
Deep learning is still not a very common tool in speaker verification field. We study deep convolutional neural network performance in the text-prompted speaker verification task. The prompted passphrase is segmented into word states - i.e.…
We propose to model the acoustic space of deep neural network (DNN) class-conditional posterior probabilities as a union of low-dimensional subspaces. To that end, the training posteriors are used for dictionary learning and sparse coding.…
Deep neural networks have shown excellent performance in stereo matching task. Recently CNN-based methods have shown that stereo matching can be formulated as a supervised learning task. However, less attention is paid on the fusion of…
This paper proposes a deep denoising auto-encoder technique to extract better acoustic features for speech synthesis. The technique allows us to automatically extract low-dimensional features from high dimensional spectral features in a…
Recently deep neural networks (DNNs) have been used to learn speaker features. However, the quality of the learned features is not sufficiently good, so a complex back-end model, either neural or probabilistic, has to be used to address the…
Monaural singing voice separation task focuses on the prediction of the singing voice from a single channel music mixture signal. Current state of the art (SOTA) results in monaural singing voice separation are obtained with deep learning…
Distant speech recognition is a challenge, particularly due to the corruption of speech signals by reverberation caused by large distances between the speaker and microphone. In order to cope with a wide range of reverberations in…
Various informative factors mixed in speech signals, leading to great difficulty when decoding any of the factors. An intuitive idea is to factorize each speech frame into individual informative factors, though it turns out to be highly…
In this paper, we propose an end-to-end post-filter method with deep attention fusion features for monaural speaker-independent speech separation. At first, a time-frequency domain speech separation method is applied as the pre-separation…
One of the biggest challenges for deep learning algorithms in medical image analysis is the indiscriminate mixing of image properties, e.g. artifacts and anatomy. These entangled image properties lead to a semantically redundant feature…
Federated Bayesian neural networks require fixing a prior on the model parameters together with a likelihood. Eliciting meaningful priors on the weight space of modern overparameterized models is notoriously difficult, and misspecification…
In this paper we propose a method to model speaker and session variability and able to generate likelihood ratios using neural networks in an end-to-end phrase dependent speaker verification system. As in Joint Factor Analysis, the model…