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

Speech Enhancement (SPE-ENHA)

ICASSP 2019 Paper #4001: INCREASE APPARENT PUBLIC SPEAKING FLUENCY BY SPEECH AUGMENTATION

Sagnik Das

Fluent and confident speech is desirable to every speaker. But professional speech delivering requires a great deal of experience and practice. In this paper, we propose a speech stream manipulation system which can help non-professional speakers to produce fluent, professional-like speech content, in turn contributing towards better listener engagement and comprehension. We propose to achieve this task by manipulating the disfluencies in human speech, like the sounds uh and um, the filler words and awkward long silences.

Paper Details

Authors:
Sagnik Das
Nisha Gandhi, Tejas Naik, Roy Shilkrot
Submitted On:
12 May 2019 - 12:38pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

poster_v2.0.pdf

(30)

Keywords

Subscribe

Send Author a Private Message
[1] Nisha Gandhi, Tejas Naik, Roy Shilkrot, "ICASSP 2019 Paper #4001: INCREASE APPARENT PUBLIC SPEAKING FLUENCY BY SPEECH AUGMENTATION", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4466. Accessed: Oct. 17, 2019.
@article{4466-19,
url = {http://sigport.org/4466},
author = {Nisha Gandhi; Tejas Naik; Roy Shilkrot },
publisher = {IEEE SigPort},
title = {ICASSP 2019 Paper #4001: INCREASE APPARENT PUBLIC SPEAKING FLUENCY BY SPEECH AUGMENTATION},
year = {2019} }
TY - EJOUR
T1 - ICASSP 2019 Paper #4001: INCREASE APPARENT PUBLIC SPEAKING FLUENCY BY SPEECH AUGMENTATION
AU - Nisha Gandhi; Tejas Naik; Roy Shilkrot
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4466
ER -
Nisha Gandhi, Tejas Naik, Roy Shilkrot. (2019). ICASSP 2019 Paper #4001: INCREASE APPARENT PUBLIC SPEAKING FLUENCY BY SPEECH AUGMENTATION. IEEE SigPort. http://sigport.org/4466
Nisha Gandhi, Tejas Naik, Roy Shilkrot, 2019. ICASSP 2019 Paper #4001: INCREASE APPARENT PUBLIC SPEAKING FLUENCY BY SPEECH AUGMENTATION. Available at: http://sigport.org/4466.
Nisha Gandhi, Tejas Naik, Roy Shilkrot. (2019). "ICASSP 2019 Paper #4001: INCREASE APPARENT PUBLIC SPEAKING FLUENCY BY SPEECH AUGMENTATION." Web.
1. Nisha Gandhi, Tejas Naik, Roy Shilkrot. ICASSP 2019 Paper #4001: INCREASE APPARENT PUBLIC SPEAKING FLUENCY BY SPEECH AUGMENTATION [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4466

Learning to Dequantize Speech Signals by Primal-Dual Networks: An Approach for Acoustic Sensor Networks

Christoph Brauer

We introduce a method to improve the quality of simple scalar quantization in the context of acoustic sensor networks by combining ideas from sparse reconstruction, artificial neural networks and weighting filters. We start from the observation that optimization methods based on sparse reconstruction resemble the structure of a neural network. Hence, building upon a successful enhancement method, we unroll the algorithms and use this to build a neural network which we train to obtain enhanced decoding.

Paper Details

Authors:
Christoph Brauer
Ziyue Zhao, Dirk Lorenz, Tim Fingscheidt
Submitted On:
12 May 2019 - 6:42pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

icassp_poster.pdf

(54)

Keywords

Subscribe

Send Author a Private Message
[1] Ziyue Zhao, Dirk Lorenz, Tim Fingscheidt, "Learning to Dequantize Speech Signals by Primal-Dual Networks: An Approach for Acoustic Sensor Networks", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4462. Accessed: Oct. 17, 2019.
@article{4462-19,
url = {http://sigport.org/4462},
author = {Ziyue Zhao; Dirk Lorenz; Tim Fingscheidt },
publisher = {IEEE SigPort},
title = {Learning to Dequantize Speech Signals by Primal-Dual Networks: An Approach for Acoustic Sensor Networks},
year = {2019} }
TY - EJOUR
T1 - Learning to Dequantize Speech Signals by Primal-Dual Networks: An Approach for Acoustic Sensor Networks
AU - Ziyue Zhao; Dirk Lorenz; Tim Fingscheidt
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4462
ER -
Ziyue Zhao, Dirk Lorenz, Tim Fingscheidt. (2019). Learning to Dequantize Speech Signals by Primal-Dual Networks: An Approach for Acoustic Sensor Networks. IEEE SigPort. http://sigport.org/4462
Ziyue Zhao, Dirk Lorenz, Tim Fingscheidt, 2019. Learning to Dequantize Speech Signals by Primal-Dual Networks: An Approach for Acoustic Sensor Networks. Available at: http://sigport.org/4462.
Ziyue Zhao, Dirk Lorenz, Tim Fingscheidt. (2019). "Learning to Dequantize Speech Signals by Primal-Dual Networks: An Approach for Acoustic Sensor Networks." Web.
1. Ziyue Zhao, Dirk Lorenz, Tim Fingscheidt. Learning to Dequantize Speech Signals by Primal-Dual Networks: An Approach for Acoustic Sensor Networks [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4462

Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation

Sunwoo Kim

This paper proposes a Bitwise Gated Recurrent Unit (BGRU) network for the single-channel source separation task. Recurrent Neural Networks (RNN) require several sets of weights within its cells, which significantly increases the computational cost compared to the fully-connected networks. To mitigate this increased computation, we focus on the GRU cells and quantize the feedforward procedure with binarized values and bitwise operations. The BGRU network is trained in two stages.

Paper Details

Authors:
Sunwoo Kim
Sunwoo Kim, Mrinmoy Maity, Minje Kim
Submitted On:
10 May 2019 - 7:46pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Bitwise Gated Recurrent Units

(29)

Keywords

Subscribe

Send Author a Private Message
[1] Sunwoo Kim, Mrinmoy Maity, Minje Kim, "Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4425. Accessed: Oct. 17, 2019.
@article{4425-19,
url = {http://sigport.org/4425},
author = {Sunwoo Kim; Mrinmoy Maity; Minje Kim },
publisher = {IEEE SigPort},
title = {Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation},
year = {2019} }
TY - EJOUR
T1 - Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation
AU - Sunwoo Kim; Mrinmoy Maity; Minje Kim
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4425
ER -
Sunwoo Kim, Mrinmoy Maity, Minje Kim. (2019). Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation. IEEE SigPort. http://sigport.org/4425
Sunwoo Kim, Mrinmoy Maity, Minje Kim, 2019. Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation. Available at: http://sigport.org/4425.
Sunwoo Kim, Mrinmoy Maity, Minje Kim. (2019). "Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation." Web.
1. Sunwoo Kim, Mrinmoy Maity, Minje Kim. Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4425

Perceptually-motivated environment-specific speech enhancement

Jiaqi Su
Zeyu Jin

This paper introduces a deep learning approach to enhance speech recordings made in a specific environment. A single neural network learns to ameliorate several types of recording artifacts, including noise, reverberation, and non-linear equalization. The method relies on a new perceptual loss function that combines adversarial loss with spectrogram features. Both subjective and objective evaluations show that the proposed approach improves on state-of-the-art baseline methods.

Paper Details

Authors:
Jiaqi Su
Zeyu Jin
Jiaqi Su, Adam Finkelstein, Zeyu Jin
Submitted On:
10 May 2019 - 1:40am
Short Link:
Type:
Event:
Paper Code:
Document Year:
Cite

Document Files

ICASSP2019_SU_SE_poster

(25)

ICASSP2019_SU_SE_poster

(25)

Keywords

Subscribe

Send Author a Private Message
[1] Jiaqi Su, Adam Finkelstein, Zeyu Jin, "Perceptually-motivated environment-specific speech enhancement", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4272. Accessed: Oct. 17, 2019.
@article{4272-19,
url = {http://sigport.org/4272},
author = {Jiaqi Su; Adam Finkelstein; Zeyu Jin },
publisher = {IEEE SigPort},
title = {Perceptually-motivated environment-specific speech enhancement},
year = {2019} }
TY - EJOUR
T1 - Perceptually-motivated environment-specific speech enhancement
AU - Jiaqi Su; Adam Finkelstein; Zeyu Jin
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4272
ER -
Jiaqi Su, Adam Finkelstein, Zeyu Jin. (2019). Perceptually-motivated environment-specific speech enhancement. IEEE SigPort. http://sigport.org/4272
Jiaqi Su, Adam Finkelstein, Zeyu Jin, 2019. Perceptually-motivated environment-specific speech enhancement. Available at: http://sigport.org/4272.
Jiaqi Su, Adam Finkelstein, Zeyu Jin. (2019). "Perceptually-motivated environment-specific speech enhancement." Web.
1. Jiaqi Su, Adam Finkelstein, Zeyu Jin. Perceptually-motivated environment-specific speech enhancement [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4272

Face Landmark-based Speaker-Independent Audio-Visual Speech Enhancement in Multi-Talker Environments

Giovanni Morrone

In this paper, we address the problem of enhancing the speech of a speaker of interest in a cocktail party scenario when visual information of the speaker of interest is available.Contrary to most previous studies, we do not learn visual features on the typically small audio-visual datasets, but use an already available face landmark detector (trained on a separate image dataset).The landmarks are used by LSTM-based models to generate time-frequency masks which are applied to the acoustic mixed-speech spectrogram.

Paper Details

Authors:
Giovanni Morrone
Luca Pasa, Vadim Tikhanoff, Sonia Bergamaschi, Luciano Fadiga, Leonardo Badino
Submitted On:
9 May 2019 - 12:23pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Morrone_ICASSP_Poster.pdf

(32)

Keywords

Subscribe

Send Author a Private Message
[1] Luca Pasa, Vadim Tikhanoff, Sonia Bergamaschi, Luciano Fadiga, Leonardo Badino, "Face Landmark-based Speaker-Independent Audio-Visual Speech Enhancement in Multi-Talker Environments", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4219. Accessed: Oct. 17, 2019.
@article{4219-19,
url = {http://sigport.org/4219},
author = {Luca Pasa; Vadim Tikhanoff; Sonia Bergamaschi; Luciano Fadiga; Leonardo Badino },
publisher = {IEEE SigPort},
title = {Face Landmark-based Speaker-Independent Audio-Visual Speech Enhancement in Multi-Talker Environments},
year = {2019} }
TY - EJOUR
T1 - Face Landmark-based Speaker-Independent Audio-Visual Speech Enhancement in Multi-Talker Environments
AU - Luca Pasa; Vadim Tikhanoff; Sonia Bergamaschi; Luciano Fadiga; Leonardo Badino
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4219
ER -
Luca Pasa, Vadim Tikhanoff, Sonia Bergamaschi, Luciano Fadiga, Leonardo Badino. (2019). Face Landmark-based Speaker-Independent Audio-Visual Speech Enhancement in Multi-Talker Environments. IEEE SigPort. http://sigport.org/4219
Luca Pasa, Vadim Tikhanoff, Sonia Bergamaschi, Luciano Fadiga, Leonardo Badino, 2019. Face Landmark-based Speaker-Independent Audio-Visual Speech Enhancement in Multi-Talker Environments. Available at: http://sigport.org/4219.
Luca Pasa, Vadim Tikhanoff, Sonia Bergamaschi, Luciano Fadiga, Leonardo Badino. (2019). "Face Landmark-based Speaker-Independent Audio-Visual Speech Enhancement in Multi-Talker Environments." Web.
1. Luca Pasa, Vadim Tikhanoff, Sonia Bergamaschi, Luciano Fadiga, Leonardo Badino. Face Landmark-based Speaker-Independent Audio-Visual Speech Enhancement in Multi-Talker Environments [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4219

Using recurrences in time and frequency within U-net architecture for speech enhancement

Tomasz Grzywalski

When designing fully-convolutional neural network, there is a trade-off between receptive field size, number of parameters and spatial resolution of features in deeper layers of the network. In this work we present a novel network design based on combination of many convolutional and recurrent layers that solves these dilemmas. We compare our solution with U-nets based models known from the literature and other baseline models on speech enhancement task.

Paper Details

Authors:
Tomasz Grzywalski
Szymon Drgas
Submitted On:
8 May 2019 - 9:13am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Grzywalski_Drgas.pdf

(41)

Keywords

Subscribe

Send Author a Private Message
[1] Szymon Drgas, "Using recurrences in time and frequency within U-net architecture for speech enhancement", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4091. Accessed: Oct. 17, 2019.
@article{4091-19,
url = {http://sigport.org/4091},
author = {Szymon Drgas },
publisher = {IEEE SigPort},
title = {Using recurrences in time and frequency within U-net architecture for speech enhancement},
year = {2019} }
TY - EJOUR
T1 - Using recurrences in time and frequency within U-net architecture for speech enhancement
AU - Szymon Drgas
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4091
ER -
Szymon Drgas. (2019). Using recurrences in time and frequency within U-net architecture for speech enhancement. IEEE SigPort. http://sigport.org/4091
Szymon Drgas, 2019. Using recurrences in time and frequency within U-net architecture for speech enhancement. Available at: http://sigport.org/4091.
Szymon Drgas. (2019). "Using recurrences in time and frequency within U-net architecture for speech enhancement." Web.
1. Szymon Drgas. Using recurrences in time and frequency within U-net architecture for speech enhancement [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4091

Artificial Bandwidth Extension of Narrowband Speech Using Generative Adversarial Networks

Jonas Sautter

The aim of artificial bandwidth extension is to recreate wideband speech (0 - 8 kHz) from a narrowband speech signal (0 - 4 kHz). State-of-the-art approaches use neural networks for this task. As a loss function during training, they employ the mean squared error between true and estimated wideband spectra. This, however, comes with the drawback of over-smoothing, which expresses itself in strongly underestimated dynamics of the upper frequency band.

Paper Details

Authors:
Jonas Sautter
Jonas Sautter, Friedrich Faubel, Markus Buck, Gerhard Schmidt
Submitted On:
8 May 2019 - 2:16am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

ICASSP2019_Sautter_Poster.pdf

(32)

Keywords

Subscribe

Send Author a Private Message
[1] Jonas Sautter, Friedrich Faubel, Markus Buck, Gerhard Schmidt, "Artificial Bandwidth Extension of Narrowband Speech Using Generative Adversarial Networks", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4018. Accessed: Oct. 17, 2019.
@article{4018-19,
url = {http://sigport.org/4018},
author = {Jonas Sautter; Friedrich Faubel; Markus Buck; Gerhard Schmidt },
publisher = {IEEE SigPort},
title = {Artificial Bandwidth Extension of Narrowband Speech Using Generative Adversarial Networks},
year = {2019} }
TY - EJOUR
T1 - Artificial Bandwidth Extension of Narrowband Speech Using Generative Adversarial Networks
AU - Jonas Sautter; Friedrich Faubel; Markus Buck; Gerhard Schmidt
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4018
ER -
Jonas Sautter, Friedrich Faubel, Markus Buck, Gerhard Schmidt. (2019). Artificial Bandwidth Extension of Narrowband Speech Using Generative Adversarial Networks. IEEE SigPort. http://sigport.org/4018
Jonas Sautter, Friedrich Faubel, Markus Buck, Gerhard Schmidt, 2019. Artificial Bandwidth Extension of Narrowband Speech Using Generative Adversarial Networks. Available at: http://sigport.org/4018.
Jonas Sautter, Friedrich Faubel, Markus Buck, Gerhard Schmidt. (2019). "Artificial Bandwidth Extension of Narrowband Speech Using Generative Adversarial Networks." Web.
1. Jonas Sautter, Friedrich Faubel, Markus Buck, Gerhard Schmidt. Artificial Bandwidth Extension of Narrowband Speech Using Generative Adversarial Networks [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4018

LATENT REPRESENTATION LEARNING FOR ARTIFICIAL BANDWIDTH EXTENSION USING A CONDITIONAL VARIATIONAL AUTO-ENCODER

Pramod Bachhav

Artificial bandwidth extension (ABE) algorithms can improve speech quality when wideband devices are used with narrowband

Paper Details

Authors:
Pramod Bachhav
Pramod Bachhav, Massimiliano Todisco, Nicholas Evans
Submitted On:
7 May 2019 - 1:32pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP2019.pdf

(39)

Keywords

Subscribe

Send Author a Private Message
[1] Pramod Bachhav, Massimiliano Todisco, Nicholas Evans, "LATENT REPRESENTATION LEARNING FOR ARTIFICIAL BANDWIDTH EXTENSION USING A CONDITIONAL VARIATIONAL AUTO-ENCODER", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/3932. Accessed: Oct. 17, 2019.
@article{3932-19,
url = {http://sigport.org/3932},
author = {Pramod Bachhav; Massimiliano Todisco; Nicholas Evans },
publisher = {IEEE SigPort},
title = {LATENT REPRESENTATION LEARNING FOR ARTIFICIAL BANDWIDTH EXTENSION USING A CONDITIONAL VARIATIONAL AUTO-ENCODER},
year = {2019} }
TY - EJOUR
T1 - LATENT REPRESENTATION LEARNING FOR ARTIFICIAL BANDWIDTH EXTENSION USING A CONDITIONAL VARIATIONAL AUTO-ENCODER
AU - Pramod Bachhav; Massimiliano Todisco; Nicholas Evans
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/3932
ER -
Pramod Bachhav, Massimiliano Todisco, Nicholas Evans. (2019). LATENT REPRESENTATION LEARNING FOR ARTIFICIAL BANDWIDTH EXTENSION USING A CONDITIONAL VARIATIONAL AUTO-ENCODER. IEEE SigPort. http://sigport.org/3932
Pramod Bachhav, Massimiliano Todisco, Nicholas Evans, 2019. LATENT REPRESENTATION LEARNING FOR ARTIFICIAL BANDWIDTH EXTENSION USING A CONDITIONAL VARIATIONAL AUTO-ENCODER. Available at: http://sigport.org/3932.
Pramod Bachhav, Massimiliano Todisco, Nicholas Evans. (2019). "LATENT REPRESENTATION LEARNING FOR ARTIFICIAL BANDWIDTH EXTENSION USING A CONDITIONAL VARIATIONAL AUTO-ENCODER." Web.
1. Pramod Bachhav, Massimiliano Todisco, Nicholas Evans. LATENT REPRESENTATION LEARNING FOR ARTIFICIAL BANDWIDTH EXTENSION USING A CONDITIONAL VARIATIONAL AUTO-ENCODER [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/3932

OBJECTIVE COMPARISON OF SPEECH ENHANCEMENT ALGORITHMS WITH HEARING LOSS SIMULATION

Zhuohuang Zhang

Many speech enhancement algorithms have been proposed over the years and it has been shown that deep neural networks can lead to significant improvements. These algorithms, however, have not been validated for hearing-impaired listeners. Additionally, these algorithms are often evaluated under a limited range of signal-to-noise ratios (SNR). Here, we construct a diverse speech dataset with a broad range of SNRs and noises.

Paper Details

Authors:
Zhuohuang Zhang
Zhuohuang Zhang, Yi Shen, Donald S. Williamson
Submitted On:
7 May 2019 - 1:03pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP 2019 Zhang.pdf

(26)

Keywords

Subscribe

Send Author a Private Message
[1] Zhuohuang Zhang, Yi Shen, Donald S. Williamson, "OBJECTIVE COMPARISON OF SPEECH ENHANCEMENT ALGORITHMS WITH HEARING LOSS SIMULATION", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/3925. Accessed: Oct. 17, 2019.
@article{3925-19,
url = {http://sigport.org/3925},
author = {Zhuohuang Zhang; Yi Shen; Donald S. Williamson },
publisher = {IEEE SigPort},
title = {OBJECTIVE COMPARISON OF SPEECH ENHANCEMENT ALGORITHMS WITH HEARING LOSS SIMULATION},
year = {2019} }
TY - EJOUR
T1 - OBJECTIVE COMPARISON OF SPEECH ENHANCEMENT ALGORITHMS WITH HEARING LOSS SIMULATION
AU - Zhuohuang Zhang; Yi Shen; Donald S. Williamson
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/3925
ER -
Zhuohuang Zhang, Yi Shen, Donald S. Williamson. (2019). OBJECTIVE COMPARISON OF SPEECH ENHANCEMENT ALGORITHMS WITH HEARING LOSS SIMULATION. IEEE SigPort. http://sigport.org/3925
Zhuohuang Zhang, Yi Shen, Donald S. Williamson, 2019. OBJECTIVE COMPARISON OF SPEECH ENHANCEMENT ALGORITHMS WITH HEARING LOSS SIMULATION. Available at: http://sigport.org/3925.
Zhuohuang Zhang, Yi Shen, Donald S. Williamson. (2019). "OBJECTIVE COMPARISON OF SPEECH ENHANCEMENT ALGORITHMS WITH HEARING LOSS SIMULATION." Web.
1. Zhuohuang Zhang, Yi Shen, Donald S. Williamson. OBJECTIVE COMPARISON OF SPEECH ENHANCEMENT ALGORITHMS WITH HEARING LOSS SIMULATION [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/3925

LINEAR PREDICTION-BASED PART-DEFINED AUTO-ENCODER USED FOR SPEECH ENHANCEMENT

Zihao Cui

This paper proposes a linear prediction-based part-defined auto-encoder (PAE) network to enhance speech signal. The PAE is a defined decoder or an established encoder network, based on an efficient learning algorithm or classical model. In this paper, the PAE utilizes AR-Wiener filter as the decoder part, and the AR-Wiener filter is modified as a linear prediction (LP) model by incorporating the modified factor from the residual signal. The parameters of line spectral frequency (LSF) of speech and noise and the Wiener filtering mask are utilized for training targets.

Paper Details

Authors:
Zihao Cui
Zihao Cui; Changchun Bao
Submitted On:
16 April 2019 - 5:33am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Poster_ICASSP_2019_LPPAE_zihao.pdf

(91)

Keywords

Subscribe

Send Author a Private Message
[1] Zihao Cui; Changchun Bao, "LINEAR PREDICTION-BASED PART-DEFINED AUTO-ENCODER USED FOR SPEECH ENHANCEMENT", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/3894. Accessed: Oct. 17, 2019.
@article{3894-19,
url = {http://sigport.org/3894},
author = {Zihao Cui; Changchun Bao },
publisher = {IEEE SigPort},
title = {LINEAR PREDICTION-BASED PART-DEFINED AUTO-ENCODER USED FOR SPEECH ENHANCEMENT},
year = {2019} }
TY - EJOUR
T1 - LINEAR PREDICTION-BASED PART-DEFINED AUTO-ENCODER USED FOR SPEECH ENHANCEMENT
AU - Zihao Cui; Changchun Bao
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/3894
ER -
Zihao Cui; Changchun Bao. (2019). LINEAR PREDICTION-BASED PART-DEFINED AUTO-ENCODER USED FOR SPEECH ENHANCEMENT. IEEE SigPort. http://sigport.org/3894
Zihao Cui; Changchun Bao, 2019. LINEAR PREDICTION-BASED PART-DEFINED AUTO-ENCODER USED FOR SPEECH ENHANCEMENT. Available at: http://sigport.org/3894.
Zihao Cui; Changchun Bao. (2019). "LINEAR PREDICTION-BASED PART-DEFINED AUTO-ENCODER USED FOR SPEECH ENHANCEMENT." Web.
1. Zihao Cui; Changchun Bao. LINEAR PREDICTION-BASED PART-DEFINED AUTO-ENCODER USED FOR SPEECH ENHANCEMENT [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/3894

Pages