Browse
Submit Data
Databases
API
Help

Dataset Information

20 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Discriminative Multi-Stream Postfilters Based on Deep Learning for Enhancing Statistical Parametric Speech Synthesis.

ABSTRACT: Statistical parametric speech synthesis based on Hidden Markov Models has been an important technique for the production of artificial voices, due to its ability to produce results with high intelligibility and sophisticated features such as voice conversion and accent modification with a small footprint, particularly for low-resource languages where deep learning-based techniques remain unexplored. Despite the progress, the quality of the results, mainly based on Hidden Markov Models (HMM) does not reach those of the predominant approaches, based on unit selection of speech segments of deep learning. One of the proposals to improve the quality of HMM-based speech has been incorporating postfiltering stages, which pretend to increase the quality while preserving the advantages of the process. In this paper, we present a new approach to postfiltering synthesized voices with the application of discriminative postfilters, with several long short-term memory (LSTM) deep neural networks. Our motivation stems from modeling specific mapping from synthesized to natural speech on those segments corresponding to voiced or unvoiced sounds, due to the different qualities of those sounds and how HMM-based voices can present distinct degradation on each one. The paper analyses the discriminative postfilters obtained using five voices, evaluated using three objective measures, Mel cepstral distance and subjective tests. The results indicate the advantages of the discriminative postilters in comparison with the HTS voice and the non-discriminative postfilters.

SUBMITTER: Coto-Jimenez M

PROVIDER: S-EPMC7985793 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

Audio Augmentation for Non-Native Children's Speech Recognition through Discriminative Learning.

Project description:Automatic speech recognition (ASR) in children is a rapidly evolving field, as children become more accustomed to interacting with virtual assistants, such as Amazon Echo, Cortana, and other smart speakers, and it has advanced the human-computer interaction in recent generations. Furthermore, non-native children are observed to exhibit a diverse range of reading errors during second language (L2) acquisition, such as lexical disfluency, hesitations, intra-word switching, and word repetitions, which are not yet addressed, resulting in ASR's struggle to recognize non-native children's speech. The main objective of this study is to develop a non-native children's speech recognition system on top of feature-space discriminative models, such as feature-space maximum mutual information (fMMI) and boosted feature-space maximum mutual information (fbMMI). Harnessing the collaborative power of speed perturbation-based data augmentation on the original children's speech corpora yields an effective performance. The corpus focuses on different speaking styles of children, together with read speech and spontaneous speech, in order to investigate the impact of non-native children's L2 speaking proficiency on speech recognition systems. The experiments revealed that feature-space MMI models with steadily increasing speed perturbation factors outperform traditional ASR baseline models.

| S-EPMC9601443 | biostudies-literature

Deep learning encodes robust discriminative neuroimaging representations to outperform standard machine learning.

Project description:Recent critical commentaries unfavorably compare deep learning (DL) with standard machine learning (SML) approaches for brain imaging data analysis. However, their conclusions are often based on pre-engineered features depriving DL of its main advantage - representation learning. We conduct a large-scale systematic comparison profiled in multiple classification and regression tasks on structural MRI images and show the importance of representation learning for DL. Results show that if trained following prevalent DL practices, DL methods have the potential to scale particularly well and substantially improve compared to SML methods, while also presenting a lower asymptotic complexity in relative computational time, despite being more complex. We also demonstrate that DL embeddings span comprehensible task-specific projection spectra and that DL consistently localizes task-discriminative brain biomarkers. Our findings highlight the presence of nonlinearities in neuroimaging data that DL can exploit to generate superior task-discriminative representations for characterizing the human brain.

| S-EPMC7806588 | biostudies-literature

Enhancing the Classification of Aphasia: A Statistical Analysis Using Connected Speech.

Project description:BackgroundLarge shared databases and automated language analyses allow for the application of new data analysis techniques that can shed new light on the connected speech of people with aphasia (PWA).AimsTo identify coherent clusters of PWA based on language output using unsupervised statistical algorithms and to identify features that are most strongly associated with those clusters.Methods & proceduresClustering and classification methods were applied to language production data from 168 PWA. Language samples were from a standard discourse protocol tapping four genres: free speech personal narratives, picture descriptions, Cinderella storytelling, procedural discourse.Outcomes & resultsSeven distinct clusters of PWA were identified by the K-means algorithm. Using the random forests algorithm, a classification tree was proposed and validated, showing 91% agreement with the cluster assignments. This representative tree used only two variables to divide the data into distinct groups: total words from free speech tasks and total closed class words from the Cinderella storytelling task.ConclusionConnected speech data can be used to distinguish PWA into coherent groups, providing insight into traditional aphasia classifications, factors that may guide discourse research and clinical work.

| S-EPMC9708051 | biostudies-literature

Discriminating pseudoprogression and true progression in diffuse infiltrating glioma using multi-parametric MRI data through deep learning.

Project description:Differentiating pseudoprogression from true tumor progression has become a significant challenge in follow-up of diffuse infiltrating gliomas, particularly high grade, which leads to a potential treatment delay for patients with early glioma recurrence. In this study, we proposed to use a multiparametric MRI data as a sequence input for the convolutional neural network with the recurrent neural network based deep learning structure to discriminate between pseudoprogression and true tumor progression. In this study, 43 biopsy-proven patient data identified as diffuse infiltrating glioma patients whose disease progressed/recurred were used. The dataset consists of five original MRI sequences; pre-contrast T1-weighted, post-contrast T1-weighted, T2-weighted, FLAIR, and ADC images as well as two engineered sequences; T1post-T1pre and T2-FLAIR. Next, we used three CNN-LSTM models with a different set of sequences as input sequences to pass through CNN-LSTM layers. We performed threefold cross-validation in the training dataset and generated the boxplot, accuracy, and ROC curve, AUC from each trained model with the test dataset to evaluate models. The mean accuracy for VGG16 models ranged from 0.44 to 0.60 and the mean AUC ranged from 0.47 to 0.59. For CNN-LSTM model, the mean accuracy ranged from 0.62 to 0.75 and the mean AUC ranged from 0.64 to 0.81. The performance of the proposed CNN-LSTM with multiparametric sequence data was found to outperform the popular convolutional CNN with a single MRI sequence. In conclusion, incorporating all available MRI sequences into a sequence input for a CNN-LSTM model improved diagnostic performance for discriminating between pseudoprogression and true tumor progression.

| S-EPMC7683728 | biostudies-literature

Unsupervised single-particle deep classification via statistical manifold learning

Project description: Not available

| EMPIAR-10069 | biostudies-other

Neural processes underlying statistical learning for speech segmentation in dogs.

Project description:To learn words, humans extract statistical regularities from speech. Multiple species use statistical learning also to process speech, but the neural underpinnings of speech segmentation in non-humans remain largely unknown. Here, we investigated computational and neural markers of speech segmentation in dogs, a phylogenetically distant mammal that efficiently navigates humans' social and linguistic environment. Using electroencephalography (EEG), we compared event-related responses (ERPs) for artificial words previously presented in a continuous speech stream with different distributional statistics. Results revealed an early effect (220-470 ms) of transitional probability and a late component (590-790 ms) modulated by both word frequency and transitional probability. Using fMRI, we searched for brain regions sensitive to statistical regularities in speech. Structured speech elicited lower activity in the basal ganglia, a region involved in sequence learning, and repetition enhancement in the auditory cortex. Speech segmentation in dogs, similar to that of humans, involves complex computations, engaging both domain-general and modality-specific brain areas. VIDEO ABSTRACT.

| S-EPMC7612233 | biostudies-literature

Discriminative Learning for Automatic Staging of Placental Maturity via Multi-layer Fisher Vector.

Project description:Currently, placental maturity is performed using subjective evaluation, which can be unreliable as it is highly dependent on the observations and experiences of clinicians. To address this problem, this paper proposes a method to automatically stage placenta maturity from B-mode ultrasound (US) images based on dense sampling and novel feature descriptors. Specifically, our proposed method first densely extracts features with a regular grid based on dense sampling instead of a few unreliable interest points. Followed by, these features are clustered using generative Gaussian mixture model (GMM) to obtain high order statistics of the features. The clustering representatives (i.e., cluster means) are encoded by Fisher vector (FV) for staging accuracy enhancement. Differing from the previous studies, a multi-layer FV is investigated to exploit the spatial information rather than the single layer FV. Experimental results show that the proposed method with the dense FV has achieved an area under the receiver of characteristics (AUC) of 96.77%, sensitivity and specificity of 98.04% and 93.75% for the placental maturity staging, respectively. Our experimental results also demonstrate that the dense feature outperforms the traditional sparse feature for placental maturity staging.

| S-EPMC4533167 | biostudies-other

Relationship between perceptual learning in speech and statistical learning in younger and older adults.

Project description:Within a few sentences, listeners learn to understand severely degraded speech such as noise-vocoded speech. However, individuals vary in the amount of such perceptual learning and it is unclear what underlies these differences. The present study investigates whether perceptual learning in speech relates to statistical learning, as sensitivity to probabilistic information may aid identification of relevant cues in novel speech input. If statistical learning and perceptual learning (partly) draw on the same general mechanisms, then statistical learning in a non-auditory modality using non-linguistic sequences should predict adaptation to degraded speech. In the present study, 73 older adults (aged over 60 years) and 60 younger adults (aged between 18 and 30 years) performed a visual artificial grammar learning task and were presented with 60 meaningful noise-vocoded sentences in an auditory recall task. Within age groups, sentence recognition performance over exposure was analyzed as a function of statistical learning performance, and other variables that may predict learning (i.e., hearing, vocabulary, attention switching control, working memory, and processing speed). Younger and older adults showed similar amounts of perceptual learning, but only younger adults showed significant statistical learning. In older adults, improvement in understanding noise-vocoded speech was constrained by age. In younger adults, amount of adaptation was associated with lexical knowledge and with statistical learning ability. Thus, individual differences in general cognitive abilities explain listeners' variability in adapting to noise-vocoded speech. Results suggest that perceptual and statistical learning share mechanisms of implicit regularity detection, but that the ability to detect statistical regularities is impaired in older adults if visual sequences are presented quickly.

| S-EPMC4150448 | biostudies-literature

Statistical learning for speech segmentation: Age-related changes and underlying mechanisms.

Project description:Statistical learning (SL) is a powerful learning mechanism that supports word segmentation and language acquisition in infants and young adults. However, little is known about how this ability changes over the life span and interacts with age-related cognitive decline. The aims of this study were to: (a) examine the effect of aging on speech segmentation by SL, and (b) explore core mechanisms underlying SL. Across four testing sessions, young, middle-aged, and older adults were exposed to continuous speech streams at two different speech rates, both with and without cognitive load. Learning was assessed using a two-alterative forced-choice task in which words from the stream were pitted against either part-words, which occurred across word boundaries in the stream, or nonwords, which never appeared in the stream. Participants also completed a battery of cognitive tests assessing working memory and executive functions. The results showed that speech segmentation by SL was remarkably resilient to aging, although age effects were visible in the more challenging conditions, namely, when words had to be discriminated from part-words, which required the formation of detailed phonological representations, and when SL was performed under cognitive load. Moreover, an analysis of the cognitive test data indicated that performance against part-words was predicted mostly by memory updating, whereas performance against nonwords was predicted mostly by working memory storage capacity. Taken together, the data show that SL relies on a combination of implicit and explicit skills, and that age effects on SL are likely to be linked to an age-related selective decline in memory updating. (PsycINFO Database Record (c) 2018 APA, all rights reserved).

| S-EPMC6233520 | biostudies-literature

Modeling longitudinal imaging biomarkers with parametric Bayesian multi-task learning.

Project description:Longitudinal imaging biomarkers are invaluable for understanding the course of neurodegeneration, promising the ability to track disease progression and to detect disease earlier than cross-sectional biomarkers. To properly realize their potential, biomarker trajectory models must be robust to both under-sampling and measurement errors and should be able to integrate multi-modal information to improve trajectory inference and prediction. Here we present a parametric Bayesian multi-task learning based approach to modeling univariate trajectories across subjects that addresses these criteria. Our approach learns multiple subjects' trajectories within a single model that allows for different types of information sharing, that is, coupling, across subjects. It optimizes a combination of uncoupled, fully coupled and kernel coupled models. Kernel-based coupling allows linking subjects' trajectories based on one or more biomarker measures. We demonstrate this using Alzheimer's Disease Neuroimaging Initiative (ADNI) data, where we model longitudinal trajectories of MRI-derived cortical volumes in neurodegeneration, with coupling based on APOE genotype, cerebrospinal fluid (CSF) and amyloid PET-based biomarkers. In addition to detecting established disease effects, we detect disease related changes within the insula that have not received much attention within the literature. Due to its sensitivity in detecting disease effects, its competitive predictive performance and its ability to learn the optimal parameter covariance from data rather than choosing a specific set of random and fixed effects a priori, we propose that our model can be used in place of or in addition to linear mixed effects models when modeling biomarker trajectories. A software implementation of the method is publicly available.

| S-EPMC6679792 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data