Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Cardiomyopathy VII: Pre and Post Operative Nursing Management01:28

Cardiomyopathy VII: Pre and Post Operative Nursing Management

307
Patients with hypertrophic cardiomyopathy (HCM) and left ventricular outflow tract (LVOT) obstruction who remain symptomatic despite optimal medical therapy may undergo a septal myectomy (Morrow procedure). This procedure involves excising a portion of the hypertrophied septum below the aortic valve using a heart-lung machine to improve blood flow through the LVOT. Effective preoperative and postoperative nursing management ensures successful patient outcomes, minimizes complications, and...
307
Passive Filters01:27

Passive Filters

971
Passive filters are utilized to shape the frequency spectrum of signals across a diverse array of applications. These filters, using only passive elements like resistors (R), inductors (L), and capacitors (C), are capable of selectively allowing or blocking certain frequency ranges without the need for external power sources.
Low-Pass Filters
Low-pass filters are designed to transmit signals with frequencies lower than the cutoff frequency, ωc, and attenuate those above it. The cutoff...
971
Active Filters01:25

Active Filters

1.3K
Active filters are electronic circuits that use operational amplifiers (op-amps), resistors, and capacitors to filter out unwanted frequency components from a signal. A first-order low-pass active filter is designed to pass signals with a frequency lower than a certain cutoff frequency and attenuate frequencies higher than that cutoff frequency. The transfer function for a first-order low-pass active filter is:
1.3K
Protein Networks02:26

Protein Networks

4.5K
An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
4.5K
pre-mRNA Processing02:01

pre-mRNA Processing

57.2K
In eukaryotic cells, transcripts made by RNA polymerase are modified and processed before exiting the nucleus. Unprocessed RNA is called precursor mRNA or pre-mRNA to distinguish it from mature mRNA.
Once about 20-40 ribonucleotides have been joined together by RNA polymerase, a group of enzymes adds a “cap” to the 5’ end of the growing transcript. In this process, a 5’ phosphate is replaced by modified guanosine that has a methyl group attached to it (7-Methyl...
57.2K
Network Covalent Solids02:18

Network Covalent Solids

16.1K
Network covalent solids contain a three-dimensional network of covalently bonded atoms as found in the crystal structures of nonmetals like diamond, graphite, silicon, and some covalent compounds, such as silicon dioxide (sand) and silicon carbide (carborundum, the abrasive on sandpaper). Many minerals have networks of covalent bonds.
To break or to melt a covalent network solid, covalent bonds must be broken. Because covalent bonds are relatively strong, covalent network solids are typically...
16.1K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

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

Biomimetics (Basel, Switzerland)·2021
Same author

Evaluation of Mixed Deep Neural Networks for Reverberant Speech Enhancement.

Biomimetics (Basel, Switzerland)·2019
See all related articles

Related Experiment Video

Updated: Jan 24, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.0K

Improving Post-Filtering of Artificial Speech Using Pre-Trained LSTM Neural Networks.

Marvin Coto-Jiménez1

  • 1Escuela de Ingeniería Eléctrica, Universidad de Costa Rica, San José 11501-2060, Costa Rica. marvin.coto@ucr.ac.cr.

Biomimetics (Basel, Switzerland)
|May 31, 2019
PubMed
Summary

This study introduces a novel pre-training method for Long Short-term Memory (LSTM) networks to improve statistical parametric speech synthesis quality. The auto-associative pre-training enhances Mel-Frequency Cepstral parameters more effectively than random initialization.

Keywords:
LSTMdeep learningmachine learningpost-filteringsignal processingspeech synthesis

More Related Videos

A Neural Network-Based Identification of Developmentally Competent or Incompetent Mouse Fully-Grown Oocytes
10:04

A Neural Network-Based Identification of Developmentally Competent or Incompetent Mouse Fully-Grown Oocytes

Published on: March 3, 2018

7.1K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.9K

Related Experiment Videos

Last Updated: Jan 24, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.0K
A Neural Network-Based Identification of Developmentally Competent or Incompetent Mouse Fully-Grown Oocytes
10:04

A Neural Network-Based Identification of Developmentally Competent or Incompetent Mouse Fully-Grown Oocytes

Published on: March 3, 2018

7.1K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.9K

Area of Science:

  • Speech Synthesis
  • Deep Learning
  • Signal Processing

Background:

  • Deep learning post-filters aim to improve statistical parametric speech synthesis by mapping synthetic to natural speech.
  • Long Short-term Memory (LSTM) networks are effective but have room for improvement in quality and efficiency.
  • Current methods often use random initialization for LSTM networks in speech synthesis.

Purpose of the Study:

  • To introduce a new pre-training approach for LSTM networks to enhance synthesized speech quality, particularly spectral characteristics.
  • To improve the efficiency of speech synthesis enhancement processes.
  • To evaluate the effectiveness of auto-associative pre-training for LSTM-based speech synthesis.

Main Methods:

  • Implemented an auto-associative pre-training method for a single LSTM network.
  • Utilized the pre-trained LSTM as an initialization strategy for post-filters in speech synthesis.
  • Focused on enhancing Mel-Frequency Cepstral (MFC) parameters of synthetic speech.

Main Results:

  • The proposed auto-associative pre-training initialization demonstrated advantages in enhancing MFC parameters.
  • The pre-training approach achieved superior results in improving the statistical parametric speech spectrum compared to random initialization.
  • Effectiveness was observed in most tested scenarios.

Conclusions:

  • Auto-associative pre-training is a viable and effective method for initializing LSTMs in speech synthesis.
  • This approach offers a more efficient way to enhance spectral quality in synthesized speech.
  • The findings suggest a significant improvement over traditional random initialization techniques.