Sorry, you need to enable JavaScript to visit this website.

Speech Synthesis and Generation, including TTS (SPE-SYNT)

NATURAL TTS SYNTHESIS BY CONDITIONING WAVENET ON MEL SPECTROGRAM PREDICTIONS

Paper Details

Authors:
Submitted On:
17 April 2018 - 8:46pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP 2018 - Tacotron 2.pdf

(28 downloads)

Keywords

Subscribe

[1] , "NATURAL TTS SYNTHESIS BY CONDITIONING WAVENET ON MEL SPECTROGRAM PREDICTIONS", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2953. Accessed: Apr. 23, 2018.
@article{2953-18,
url = {http://sigport.org/2953},
author = { },
publisher = {IEEE SigPort},
title = {NATURAL TTS SYNTHESIS BY CONDITIONING WAVENET ON MEL SPECTROGRAM PREDICTIONS},
year = {2018} }
TY - EJOUR
T1 - NATURAL TTS SYNTHESIS BY CONDITIONING WAVENET ON MEL SPECTROGRAM PREDICTIONS
AU -
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2953
ER -
. (2018). NATURAL TTS SYNTHESIS BY CONDITIONING WAVENET ON MEL SPECTROGRAM PREDICTIONS. IEEE SigPort. http://sigport.org/2953
, 2018. NATURAL TTS SYNTHESIS BY CONDITIONING WAVENET ON MEL SPECTROGRAM PREDICTIONS. Available at: http://sigport.org/2953.
. (2018). "NATURAL TTS SYNTHESIS BY CONDITIONING WAVENET ON MEL SPECTROGRAM PREDICTIONS." Web.
1. . NATURAL TTS SYNTHESIS BY CONDITIONING WAVENET ON MEL SPECTROGRAM PREDICTIONS [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2953

TEXT-TO-SPEECH SYNTHESIS USING STFT SPECTRA BASED ON LOW-/MULTI-RESOLUTION GENERATIVE ADVERSARIAL NETWORKS

Paper Details

Authors:
Yuki Saito, Shinnosuke Takamichi, Hiroshi Saruwatari
Submitted On:
17 April 2018 - 4:50pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

saito18icassp_tts.pdf

(19 downloads)

Keywords

Subscribe

[1] Yuki Saito, Shinnosuke Takamichi, Hiroshi Saruwatari, "TEXT-TO-SPEECH SYNTHESIS USING STFT SPECTRA BASED ON LOW-/MULTI-RESOLUTION GENERATIVE ADVERSARIAL NETWORKS", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2946. Accessed: Apr. 23, 2018.
@article{2946-18,
url = {http://sigport.org/2946},
author = {Yuki Saito; Shinnosuke Takamichi; Hiroshi Saruwatari },
publisher = {IEEE SigPort},
title = {TEXT-TO-SPEECH SYNTHESIS USING STFT SPECTRA BASED ON LOW-/MULTI-RESOLUTION GENERATIVE ADVERSARIAL NETWORKS},
year = {2018} }
TY - EJOUR
T1 - TEXT-TO-SPEECH SYNTHESIS USING STFT SPECTRA BASED ON LOW-/MULTI-RESOLUTION GENERATIVE ADVERSARIAL NETWORKS
AU - Yuki Saito; Shinnosuke Takamichi; Hiroshi Saruwatari
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2946
ER -
Yuki Saito, Shinnosuke Takamichi, Hiroshi Saruwatari. (2018). TEXT-TO-SPEECH SYNTHESIS USING STFT SPECTRA BASED ON LOW-/MULTI-RESOLUTION GENERATIVE ADVERSARIAL NETWORKS. IEEE SigPort. http://sigport.org/2946
Yuki Saito, Shinnosuke Takamichi, Hiroshi Saruwatari, 2018. TEXT-TO-SPEECH SYNTHESIS USING STFT SPECTRA BASED ON LOW-/MULTI-RESOLUTION GENERATIVE ADVERSARIAL NETWORKS. Available at: http://sigport.org/2946.
Yuki Saito, Shinnosuke Takamichi, Hiroshi Saruwatari. (2018). "TEXT-TO-SPEECH SYNTHESIS USING STFT SPECTRA BASED ON LOW-/MULTI-RESOLUTION GENERATIVE ADVERSARIAL NETWORKS." Web.
1. Yuki Saito, Shinnosuke Takamichi, Hiroshi Saruwatari. TEXT-TO-SPEECH SYNTHESIS USING STFT SPECTRA BASED ON LOW-/MULTI-RESOLUTION GENERATIVE ADVERSARIAL NETWORKS [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2946

NON-PARALLEL VOICE CONVERSION USING VARIATIONAL AUTOENCODERS CONDITIONED BY PHONETIC POSTERIORGRAMS AND D-VECTORS

Paper Details

Authors:
Yuki Saito, Yusuke Ijima, Kyosuke Nishida, Shinnosuke Takamichi
Submitted On:
17 April 2018 - 4:47pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

saito18icassp_vc_v2.pdf

(20 downloads)

Keywords

Subscribe

[1] Yuki Saito, Yusuke Ijima, Kyosuke Nishida, Shinnosuke Takamichi, "NON-PARALLEL VOICE CONVERSION USING VARIATIONAL AUTOENCODERS CONDITIONED BY PHONETIC POSTERIORGRAMS AND D-VECTORS", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2945. Accessed: Apr. 23, 2018.
@article{2945-18,
url = {http://sigport.org/2945},
author = {Yuki Saito; Yusuke Ijima; Kyosuke Nishida; Shinnosuke Takamichi },
publisher = {IEEE SigPort},
title = {NON-PARALLEL VOICE CONVERSION USING VARIATIONAL AUTOENCODERS CONDITIONED BY PHONETIC POSTERIORGRAMS AND D-VECTORS},
year = {2018} }
TY - EJOUR
T1 - NON-PARALLEL VOICE CONVERSION USING VARIATIONAL AUTOENCODERS CONDITIONED BY PHONETIC POSTERIORGRAMS AND D-VECTORS
AU - Yuki Saito; Yusuke Ijima; Kyosuke Nishida; Shinnosuke Takamichi
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2945
ER -
Yuki Saito, Yusuke Ijima, Kyosuke Nishida, Shinnosuke Takamichi. (2018). NON-PARALLEL VOICE CONVERSION USING VARIATIONAL AUTOENCODERS CONDITIONED BY PHONETIC POSTERIORGRAMS AND D-VECTORS. IEEE SigPort. http://sigport.org/2945
Yuki Saito, Yusuke Ijima, Kyosuke Nishida, Shinnosuke Takamichi, 2018. NON-PARALLEL VOICE CONVERSION USING VARIATIONAL AUTOENCODERS CONDITIONED BY PHONETIC POSTERIORGRAMS AND D-VECTORS. Available at: http://sigport.org/2945.
Yuki Saito, Yusuke Ijima, Kyosuke Nishida, Shinnosuke Takamichi. (2018). "NON-PARALLEL VOICE CONVERSION USING VARIATIONAL AUTOENCODERS CONDITIONED BY PHONETIC POSTERIORGRAMS AND D-VECTORS." Web.
1. Yuki Saito, Yusuke Ijima, Kyosuke Nishida, Shinnosuke Takamichi. NON-PARALLEL VOICE CONVERSION USING VARIATIONAL AUTOENCODERS CONDITIONED BY PHONETIC POSTERIORGRAMS AND D-VECTORS [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2945

On the use of WaveNet as a Statistical Vocoder

Paper Details

Authors:
Submitted On:
17 April 2018 - 5:40am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

WaveNet_Vocoder_Poster_4cols_v2.pdf

(34 downloads)

Keywords

Subscribe

[1] , "On the use of WaveNet as a Statistical Vocoder", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2931. Accessed: Apr. 23, 2018.
@article{2931-18,
url = {http://sigport.org/2931},
author = { },
publisher = {IEEE SigPort},
title = {On the use of WaveNet as a Statistical Vocoder},
year = {2018} }
TY - EJOUR
T1 - On the use of WaveNet as a Statistical Vocoder
AU -
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2931
ER -
. (2018). On the use of WaveNet as a Statistical Vocoder. IEEE SigPort. http://sigport.org/2931
, 2018. On the use of WaveNet as a Statistical Vocoder. Available at: http://sigport.org/2931.
. (2018). "On the use of WaveNet as a Statistical Vocoder." Web.
1. . On the use of WaveNet as a Statistical Vocoder [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2931

An Investigation of Noise Shaping with Perceptual Weighting for WaveNet-based Speech Generation


We propose a noise shaping method to improve the sound quality of speech signals generated by WaveNet, which is a convolutional neural network (CNN) that predicts a waveform sample sequence as a discrete symbol sequence. Speech signals generated by WaveNet often suffer from noise signals caused by the quantization error generated by representing waveform samples as discrete symbols and the prediction error of the CNN.

ICASSP2018_NS.pdf

PDF icon Poster pdf (21 downloads)

Paper Details

Authors:
Kentaro Tachibana, Tomoki Toda, Yoshinori Shiga, Hisashi Kawai
Submitted On:
15 April 2018 - 1:02am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Poster pdf

(21 downloads)

Keywords

Subscribe

[1] Kentaro Tachibana, Tomoki Toda, Yoshinori Shiga, Hisashi Kawai, "An Investigation of Noise Shaping with Perceptual Weighting for WaveNet-based Speech Generation", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2880. Accessed: Apr. 23, 2018.
@article{2880-18,
url = {http://sigport.org/2880},
author = {Kentaro Tachibana; Tomoki Toda; Yoshinori Shiga; Hisashi Kawai },
publisher = {IEEE SigPort},
title = {An Investigation of Noise Shaping with Perceptual Weighting for WaveNet-based Speech Generation},
year = {2018} }
TY - EJOUR
T1 - An Investigation of Noise Shaping with Perceptual Weighting for WaveNet-based Speech Generation
AU - Kentaro Tachibana; Tomoki Toda; Yoshinori Shiga; Hisashi Kawai
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2880
ER -
Kentaro Tachibana, Tomoki Toda, Yoshinori Shiga, Hisashi Kawai. (2018). An Investigation of Noise Shaping with Perceptual Weighting for WaveNet-based Speech Generation. IEEE SigPort. http://sigport.org/2880
Kentaro Tachibana, Tomoki Toda, Yoshinori Shiga, Hisashi Kawai, 2018. An Investigation of Noise Shaping with Perceptual Weighting for WaveNet-based Speech Generation. Available at: http://sigport.org/2880.
Kentaro Tachibana, Tomoki Toda, Yoshinori Shiga, Hisashi Kawai. (2018). "An Investigation of Noise Shaping with Perceptual Weighting for WaveNet-based Speech Generation." Web.
1. Kentaro Tachibana, Tomoki Toda, Yoshinori Shiga, Hisashi Kawai. An Investigation of Noise Shaping with Perceptual Weighting for WaveNet-based Speech Generation [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2880

On the analysis of training data for wavenet-based speech synthesis


In this paper, we analyze how much, how consistent and how accurate data WaveNet-based speech synthesis method needs to be abletogeneratespeechofgoodquality. Wedothisbyaddingartificial noise to the description of our training data and observing how well WaveNet trains and produces speech. More specifically, we add noise to both phonetic segmentation and annotation accuracy, and we also reduce the size of training data by using a fewer number of sentences during training of a WaveNet model.

poster.pdf

PDF icon poster.pdf (27 downloads)

Paper Details

Authors:
Zdeněk Hanzlíček, Jindřich Matoušek
Submitted On:
13 April 2018 - 4:16pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

poster.pdf

(27 downloads)

Keywords

Subscribe

[1] Zdeněk Hanzlíček, Jindřich Matoušek, "On the analysis of training data for wavenet-based speech synthesis", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2759. Accessed: Apr. 23, 2018.
@article{2759-18,
url = {http://sigport.org/2759},
author = {Zdeněk Hanzlíček; Jindřich Matoušek },
publisher = {IEEE SigPort},
title = {On the analysis of training data for wavenet-based speech synthesis},
year = {2018} }
TY - EJOUR
T1 - On the analysis of training data for wavenet-based speech synthesis
AU - Zdeněk Hanzlíček; Jindřich Matoušek
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2759
ER -
Zdeněk Hanzlíček, Jindřich Matoušek. (2018). On the analysis of training data for wavenet-based speech synthesis. IEEE SigPort. http://sigport.org/2759
Zdeněk Hanzlíček, Jindřich Matoušek, 2018. On the analysis of training data for wavenet-based speech synthesis. Available at: http://sigport.org/2759.
Zdeněk Hanzlíček, Jindřich Matoušek. (2018). "On the analysis of training data for wavenet-based speech synthesis." Web.
1. Zdeněk Hanzlíček, Jindřich Matoušek. On the analysis of training data for wavenet-based speech synthesis [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2759

MODELING-BY-GENERATION-STRUCTURED NOISE COMPENSATION ALGORITHM FOR GLOTTAL VOCODING SPEECH SYNTHESIS SYSTEM


This paper proposes a novel noise compensation algorithm for a glottal excitation model in a deep learning (DL)-based speech synthesis system.
To generate high-quality speech synthesis outputs, the balance between harmonic and noise components of the glottal excitation signal should be well-represented by the DL network.
However, it is hard to accurately model the noise component because the DL training process inevitably results in statistically smoothed outputs; thus, it is essential to introduce an additional noise compensation process.

Paper Details

Authors:
Submitted On:
13 April 2018 - 1:15am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP2018_MbG_glottal.pdf

(9 downloads)

ICASSP2018_MbG_glottal.pdf

(6 downloads)

Keywords

Subscribe

[1] , "MODELING-BY-GENERATION-STRUCTURED NOISE COMPENSATION ALGORITHM FOR GLOTTAL VOCODING SPEECH SYNTHESIS SYSTEM", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2602. Accessed: Apr. 23, 2018.
@article{2602-18,
url = {http://sigport.org/2602},
author = { },
publisher = {IEEE SigPort},
title = {MODELING-BY-GENERATION-STRUCTURED NOISE COMPENSATION ALGORITHM FOR GLOTTAL VOCODING SPEECH SYNTHESIS SYSTEM},
year = {2018} }
TY - EJOUR
T1 - MODELING-BY-GENERATION-STRUCTURED NOISE COMPENSATION ALGORITHM FOR GLOTTAL VOCODING SPEECH SYNTHESIS SYSTEM
AU -
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2602
ER -
. (2018). MODELING-BY-GENERATION-STRUCTURED NOISE COMPENSATION ALGORITHM FOR GLOTTAL VOCODING SPEECH SYNTHESIS SYSTEM. IEEE SigPort. http://sigport.org/2602
, 2018. MODELING-BY-GENERATION-STRUCTURED NOISE COMPENSATION ALGORITHM FOR GLOTTAL VOCODING SPEECH SYNTHESIS SYSTEM. Available at: http://sigport.org/2602.
. (2018). "MODELING-BY-GENERATION-STRUCTURED NOISE COMPENSATION ALGORITHM FOR GLOTTAL VOCODING SPEECH SYNTHESIS SYSTEM." Web.
1. . MODELING-BY-GENERATION-STRUCTURED NOISE COMPENSATION ALGORITHM FOR GLOTTAL VOCODING SPEECH SYNTHESIS SYSTEM [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2602

CONVOLUTIONAL SEQUENCE TO SEQUENCE MODEL WITH NON-SEQUENTIAL GREEDY DECODING FOR GRAPHEME TO PHONEME CONVERSION


The greedy decoding method used in the conventional sequence-to-sequence models is prone to producing a model with a compounding
of errors, mainly because it makes inferences in a fixed order, regardless of whether or not the model’s previous guesses are correct.
We propose a non-sequential greedy decoding method that generalizes the greedy decoding schemes proposed in the past. The proposed
method determines not only which token to consider, but also which position in the output sequence to infer at each inference step.

Paper Details

Authors:
Moon-jung Chae, Kyubyong Park, Jinhyun Bang, Soobin Suh, Jonghyuk Park, Namju Kim, Jonghun Park
Submitted On:
13 April 2018 - 12:22am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

NSGD_poster_at_ICASSP2018_v1.1.pdf

(9 downloads)

Keywords

Subscribe

[1] Moon-jung Chae, Kyubyong Park, Jinhyun Bang, Soobin Suh, Jonghyuk Park, Namju Kim, Jonghun Park, "CONVOLUTIONAL SEQUENCE TO SEQUENCE MODEL WITH NON-SEQUENTIAL GREEDY DECODING FOR GRAPHEME TO PHONEME CONVERSION", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2586. Accessed: Apr. 23, 2018.
@article{2586-18,
url = {http://sigport.org/2586},
author = {Moon-jung Chae; Kyubyong Park; Jinhyun Bang; Soobin Suh; Jonghyuk Park; Namju Kim; Jonghun Park },
publisher = {IEEE SigPort},
title = {CONVOLUTIONAL SEQUENCE TO SEQUENCE MODEL WITH NON-SEQUENTIAL GREEDY DECODING FOR GRAPHEME TO PHONEME CONVERSION},
year = {2018} }
TY - EJOUR
T1 - CONVOLUTIONAL SEQUENCE TO SEQUENCE MODEL WITH NON-SEQUENTIAL GREEDY DECODING FOR GRAPHEME TO PHONEME CONVERSION
AU - Moon-jung Chae; Kyubyong Park; Jinhyun Bang; Soobin Suh; Jonghyuk Park; Namju Kim; Jonghun Park
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2586
ER -
Moon-jung Chae, Kyubyong Park, Jinhyun Bang, Soobin Suh, Jonghyuk Park, Namju Kim, Jonghun Park. (2018). CONVOLUTIONAL SEQUENCE TO SEQUENCE MODEL WITH NON-SEQUENTIAL GREEDY DECODING FOR GRAPHEME TO PHONEME CONVERSION. IEEE SigPort. http://sigport.org/2586
Moon-jung Chae, Kyubyong Park, Jinhyun Bang, Soobin Suh, Jonghyuk Park, Namju Kim, Jonghun Park, 2018. CONVOLUTIONAL SEQUENCE TO SEQUENCE MODEL WITH NON-SEQUENTIAL GREEDY DECODING FOR GRAPHEME TO PHONEME CONVERSION. Available at: http://sigport.org/2586.
Moon-jung Chae, Kyubyong Park, Jinhyun Bang, Soobin Suh, Jonghyuk Park, Namju Kim, Jonghun Park. (2018). "CONVOLUTIONAL SEQUENCE TO SEQUENCE MODEL WITH NON-SEQUENTIAL GREEDY DECODING FOR GRAPHEME TO PHONEME CONVERSION." Web.
1. Moon-jung Chae, Kyubyong Park, Jinhyun Bang, Soobin Suh, Jonghyuk Park, Namju Kim, Jonghun Park. CONVOLUTIONAL SEQUENCE TO SEQUENCE MODEL WITH NON-SEQUENTIAL GREEDY DECODING FOR GRAPHEME TO PHONEME CONVERSION [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2586

Feature Based Adaptation For Speaking Style Synthesis


Speaking style plays an important role in the expressivity of speech for communication. Hence speaking style is very important for synthetic speech as well. Speaking style adaptation faces the difficulty that the data of specific styles may be limited and difficult to obtain in large amounts. A possible solution is to leverage data from speaking styles that are more available, to train the speech synthesizer and then adapt it to the target style for which the data is scarce.

Paper Details

Authors:
Lifa Sun, Shiyin Kang, Songxiang Liu, Zhiyong Wu, Xunying Liu, Helen Meng
Submitted On:
12 April 2018 - 10:14pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Style adaptation

(8 downloads)

Keywords

Subscribe

[1] Lifa Sun, Shiyin Kang, Songxiang Liu, Zhiyong Wu, Xunying Liu, Helen Meng, "Feature Based Adaptation For Speaking Style Synthesis", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2553. Accessed: Apr. 23, 2018.
@article{2553-18,
url = {http://sigport.org/2553},
author = { Lifa Sun; Shiyin Kang; Songxiang Liu; Zhiyong Wu; Xunying Liu; Helen Meng },
publisher = {IEEE SigPort},
title = {Feature Based Adaptation For Speaking Style Synthesis},
year = {2018} }
TY - EJOUR
T1 - Feature Based Adaptation For Speaking Style Synthesis
AU - Lifa Sun; Shiyin Kang; Songxiang Liu; Zhiyong Wu; Xunying Liu; Helen Meng
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2553
ER -
Lifa Sun, Shiyin Kang, Songxiang Liu, Zhiyong Wu, Xunying Liu, Helen Meng. (2018). Feature Based Adaptation For Speaking Style Synthesis. IEEE SigPort. http://sigport.org/2553
Lifa Sun, Shiyin Kang, Songxiang Liu, Zhiyong Wu, Xunying Liu, Helen Meng, 2018. Feature Based Adaptation For Speaking Style Synthesis. Available at: http://sigport.org/2553.
Lifa Sun, Shiyin Kang, Songxiang Liu, Zhiyong Wu, Xunying Liu, Helen Meng. (2018). "Feature Based Adaptation For Speaking Style Synthesis." Web.
1. Lifa Sun, Shiyin Kang, Songxiang Liu, Zhiyong Wu, Xunying Liu, Helen Meng. Feature Based Adaptation For Speaking Style Synthesis [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2553

VOICE CONVERSION THROUGH RESIDUAL WARPING IN A SPARSE, ANCHOR-BASED REPRESENTATION OF SPEECH


In previous work we presented a Sparse, Anchor-Based Representation of speech (SABR) that uses phonemic “anchors” to represent an utterance with a set of sparse non-negative weights. SABR is speaker-independent: combining weights from a source speaker with anchors from a target speaker can be used for voice conversion. Here, we present an extension of the original SABR that significantly improves voice conversion synthesis.

Paper Details

Authors:
Christopher Liberatore, Guanlong Zhao, Ricardo Gutierrez-Osuna
Submitted On:
12 April 2018 - 7:47pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP2018Poster.v4.pdf

(6 downloads)

Keywords

Subscribe

[1] Christopher Liberatore, Guanlong Zhao, Ricardo Gutierrez-Osuna, "VOICE CONVERSION THROUGH RESIDUAL WARPING IN A SPARSE, ANCHOR-BASED REPRESENTATION OF SPEECH", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2519. Accessed: Apr. 23, 2018.
@article{2519-18,
url = {http://sigport.org/2519},
author = {Christopher Liberatore; Guanlong Zhao; Ricardo Gutierrez-Osuna },
publisher = {IEEE SigPort},
title = {VOICE CONVERSION THROUGH RESIDUAL WARPING IN A SPARSE, ANCHOR-BASED REPRESENTATION OF SPEECH},
year = {2018} }
TY - EJOUR
T1 - VOICE CONVERSION THROUGH RESIDUAL WARPING IN A SPARSE, ANCHOR-BASED REPRESENTATION OF SPEECH
AU - Christopher Liberatore; Guanlong Zhao; Ricardo Gutierrez-Osuna
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2519
ER -
Christopher Liberatore, Guanlong Zhao, Ricardo Gutierrez-Osuna. (2018). VOICE CONVERSION THROUGH RESIDUAL WARPING IN A SPARSE, ANCHOR-BASED REPRESENTATION OF SPEECH. IEEE SigPort. http://sigport.org/2519
Christopher Liberatore, Guanlong Zhao, Ricardo Gutierrez-Osuna, 2018. VOICE CONVERSION THROUGH RESIDUAL WARPING IN A SPARSE, ANCHOR-BASED REPRESENTATION OF SPEECH. Available at: http://sigport.org/2519.
Christopher Liberatore, Guanlong Zhao, Ricardo Gutierrez-Osuna. (2018). "VOICE CONVERSION THROUGH RESIDUAL WARPING IN A SPARSE, ANCHOR-BASED REPRESENTATION OF SPEECH." Web.
1. Christopher Liberatore, Guanlong Zhao, Ricardo Gutierrez-Osuna. VOICE CONVERSION THROUGH RESIDUAL WARPING IN A SPARSE, ANCHOR-BASED REPRESENTATION OF SPEECH [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2519

Pages