NDLI: Voice conversion using RNN pre-trained by recurrent temporal restricted boltzmann machines

Please wait, while we are loading the content...

IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP) : Volume 24

IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP) : Volume 23

Issue 12, December 2015

Issue 11, November 2015

Issue 10, Octember 2015

Issue 9, September 2015

Introduction to the special section on continuous space and related methods in natural language processing

Syntactic and semantic features for code-switching factored language models

Graph-based lexicon regularization for PCFG with latent annotations

Distributed feature representations for dependency parsing

Learning semantic hierarchies: a continuous vector space approach

Adequacy-fluency metrics: evaluating MT in the continuous space model framework

Topic-based coherence modeling for statistical machine translation

A sparse plus low-rank exponential language model for limited resource scenarios

Deep learning framework with confused sub-set resolution architecture for automatic Arabic diacritization

From feedforward to recurrent LSTM neural networks for language modeling

Using recurrent neural networks for slot filling in spoken language understanding

Robust sound event classification using deep neural networks

Text search of surnames in some slavic and other morphologically rich languages using rule based phonetic algorithms

Supervised detection and unsupervised discovery of pronunciation error patterns for computer-assisted language learning

Voice conversion using RNN pre-trained by recurrent temporal restricted boltzmann machines

Symbolic modeling of prosody: from linguistics to statistics

Issue 2, February 2015

Issue 1, January 2015

IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP) : Volume 22

Voice conversion using RNN pre-trained by recurrent temporal restricted boltzmann machines

Content Provider	ACM Digital Library
Author	Ariki, Yasuo Nakashika, Toru Takiguchi, Tetsuya
Copyright Year	2016
Abstract	This paper presents a voice conversion (VC) method that utilizes the recently proposed probabilistic models called recurrent temporal restricted Boltzmann machines (RTRBMs). One RTRBM is used for each speaker, with the goal of capturing high-order temporal dependencies in an acoustic sequence. Our algorithm starts from the separate training of one RTRBM for a source speaker and another for a target speaker using speaker-dependent training data. Because each RTRBM attempts to discover abstractions to maximally express the training data at each time step, as well as the temporal dependencies in the training data, we expect that the models represent the linguistic-related latent features in high-order spaces. In our approach, we convert (match) features of emphasis for the source speaker to those of the target speaker using a neural network (NN), so that the entire network (consisting of the two RTRBMs and the NN) acts as a deep recurrent NN and can be fine-tuned. Using VC experiments, we confirm the high performance of our method, especially in terms of objective criteria, relative to conventional VC methods such as approaches based on Gaussian mixture models and on NNs.
Starting Page	580
Ending Page	587
Page Count	8
File Format	PDF
ISSN	23299290
e-ISSN	23299304
DOI	10.1109/TASLP.2014.2379589
Volume Number	23
Issue Number	3
Journal	IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP)
Language	English
Publisher	Association for Computing Machinery (ACM)
Publisher Date	2015-03-01
Access Restriction	One Nation One Subscription (ONOS)
Subject Keyword	Deep Learning Recurrent neural network Recurrent temporal restricted Boltzmann machine (RTRBM) Speaker specific features Voice conversion
Content Type	Text
Resource Type	Article
Subject	Instrumentation Computational Mathematics Signal Processing Electrical and Electronic Engineering Acoustics and Ultrasonics Speech and Hearing Media Technology

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Voice conversion using speaker-dependent conditional restricted Boltzmann machine

Voice conversion in time-invariant speaker-independent space

Voice conversion using deep neural networks with layer-wise generative training

Voice Conversion Using Deep Neural Networks With Layer-Wise Generative Training

Voice conversion using conditional restricted Boltzmann machine

VOICE CONVERSION USING DEEP NEURAL NETWORKS WITH SPEAKER-INDEPENDENT PRE-TRAINING

Speaker Adaptive Training of Deep Neural Network Acoustic Models Using I-Vectors

Voice Conversion Based on Speaker-Dependent Restricted Boltzmann Machines

Speaker adaptive training of deep neural network acoustic models using i-vectors

Voice conversion using RNN pre-trained by recurrent temporal restricted boltzmann machines

Similar Documents

Voice conversion using speaker-dependent conditional restricted Boltzmann machine

Voice conversion in time-invariant speaker-independent space

Voice conversion using deep neural networks with layer-wise generative training

Voice Conversion Using Deep Neural Networks With Layer-Wise Generative Training

Voice conversion using conditional restricted Boltzmann machine

VOICE CONVERSION USING DEEP NEURAL NETWORKS WITH SPEAKER-INDEPENDENT PRE-TRAINING

Speaker Adaptive Training of Deep Neural Network Acoustic Models Using I-Vectors

Voice Conversion Based on Speaker-Dependent Restricted Boltzmann Machines

Speaker adaptive training of deep neural network acoustic models using i-vectors

Voice conversion using RNN pre-trained by recurrent temporal restricted boltzmann machines