Speech Loss Compensation by Generative Adversarial Networks

Shi, Yupeng; Zheng, Nengheng; Kang, Yuyong; Rong, Weicong

doi:10.1109/apsipaasc47483.2019.9023132

Cited by 18 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In particular, we assume that information about packet losses is not available as is customary in typical PCL settings. A notable exception to this is audio inpainting, which can be applied without knowing the position of the missing audio (blind audio inpainting) [16,20], but these works do not use data augmentation and speech recognition for evaluation. Despite the difficulties in making comparisons, we have found that our results are in line with a few recently published works.…”

Section: Word Errormentioning

confidence: 99%

“…Deep learning techniques have proved to be able to extract higher level features from less processed data and to be capable of modeling, predicting, and generalizing better than classical (statistical) techniques. PLC has not been an exception, and several approaches have been proposed in the last few years for deep learning PLC based on regression either in waveform or time-frequency domains [13][14][15][16][17], based on autoencoders [18,19] and based on Generative Adversarial Networks (GANs) [20][21][22][23].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Study of Data Augmentation for ASR Robustness in Low Bit Rate Contact Center Recordings Including Packet Losses

Fernández-Gallego

Toledano²

2022

Applied Sciences

View full text Add to dashboard Cite

Client conversations in contact centers are nowadays routinely recorded for a number of reasons—in many cases, just because it is required by current legislation. However, even if not required, conversations between customers and agents can be a valuable source of information about clients or future clients, call center agents, markets trends, etc. Analyzing these recordings provides an excellent opportunity to be aware about the business and its possibilities. The current state of the art in Automatic Speech Recognition (ASR) allows this information to be effectively extracted and used. However, conversations are usually stored in highly compressed ways to save space and typically contain packet losses that produce short interruptions in the speech signal due to the common use of Voice-over-IP (VoIP) in these systems. These effects, and especially the last one, have a negative impact on ASR performance. This article presents an extensive study on the importance of these effects on modern ASR systems and the effectiveness of using several techniques of data augmentation to increase their robustness. In addition, ITU-T G.711, a well-known Packet Loss Concealment (PLC) method is applied in combination with data augmentation techniques to analyze ASR performance improvement on signals affected by packet losses.

show abstract

Section: Word Errormentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Study of Data Augmentation for ASR Robustness in Low Bit Rate Contact Center Recordings Including Packet Losses

Fernández-Gallego

Toledano²

2022

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…One study created training samples by adding noise with different signal-to-noise (SNR) levels on clean speech signals [41]. Another work on speech bandwidth enhancement included input training samples that are created using low-pass filters with different cut-off frequencies [42]. In all aforementioned examples, the samples that illustrate multiple conditions are perceptually different.…”

Section: A Motivationmentioning

confidence: 99%

On Filter Generalization for Music Bandwidth Extension Using Deep Neural Networks

Sulun

Davies

2021

IEEE J. Sel. Top. Signal Process.

View full text Add to dashboard Cite

In this paper, we address a sub-topic of the broad domain of audio enhancement, namely musical audio bandwidth extension. We formulate the bandwidth extension problem using deep neural networks, where a band-limited signal is provided as input to the network, with the goal of reconstructing a fullbandwidth output. Our main contribution centers on the impact of the choice of low pass filter when training and subsequently testing the network. For two different state of the art deep architectures, ResNet and U-Net, we demonstrate that when the training and testing filters are matched, improvements in signalto-noise ratio (SNR) of up to 7 dB can be obtained. However, when these filters differ, the improvement falls considerably and under some training conditions results in a lower SNR than the bandlimited input. To circumvent this apparent overfitting to filter shape, we propose a data augmentation strategy which utilizes multiple low pass filters during training and leads to improved generalization to unseen filtering conditions at test time.

show abstract

“…The performance of the different networks trained to fill in speech gaps is compared with a state of the art SEGAN baseline [28] trained on our data in Table 3. T-UNet outperforms the baseline, while TF-UNet does not.…”

Section: Gaps In Speechmentioning

confidence: 99%

Cascaded Time + Time-Frequency Unet For Speech Enhancement: Jointly Addressing Clipping, Codec Distortions, And Gaps

Nair

2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Speech enhancement aims to improve speech quality by eliminating noise and distortions. While most speech enhancement methods address signal independent additive sources of noise, several degradations to speech signals are signal dependent and non-additive, like speech clipping, codec distortions, and gaps in speech. In this work, we first systematically study and achieve state of the art results on each of these three distortions individually. Next, we demonstrate a neural network pipeline that cascades a time domain convolutional neural network with a time-frequency domain convolutional neural network to address all three distortions jointly. We observe that such a cascade achieves good performance while also keeping the action of each neural network component interpretable.

show abstract

Speech Loss Compensation by Generative Adversarial Networks

Cited by 18 publications

References 21 publications

A Study of Data Augmentation for ASR Robustness in Low Bit Rate Contact Center Recordings Including Packet Losses

A Study of Data Augmentation for ASR Robustness in Low Bit Rate Contact Center Recordings Including Packet Losses

On Filter Generalization for Music Bandwidth Extension Using Deep Neural Networks

Cascaded Time + Time-Frequency Unet For Speech Enhancement: Jointly Addressing Clipping, Codec Distortions, And Gaps

Contact Info

Product

Resources

About