Artificial Bandwidth Extension Using H<sup>∞</sup> Optimization and Speech Production Model

Gupta, Deepika; Shekhawat, Hanumant Singh

doi:10.1109/radioelek.2019.8733452

Cited by 5 publications

(5 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, performances are evaluated on the speech files belonging to the RSR15 dataset. Both causal high pass filter (HPF) and non-causal low pass filter (LPF) are the same as characterized in Gupta and Shekhawat [2019b].…”

Section: Experimental Set-upmentioning

confidence: 99%

Artificial bandwidth extension using deep neural network and $H^\infty$ sampled-data control theory

Gupta,

Shekhawat

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Artificial bandwidth extension is applied to speech signals to improve their quality in narrowband telephonic communication. For accomplishing this, the missing high-frequency (high-band) components of speech signals are recovered by utilizing a new extrapolation process based on sampleddata control theory and deep neural network (DNN). The H ∞ sampled-data control theory helps in designing of a high-band filter to recover the high-frequency signals by optimally utilizing the inter-sample signals. Non-stationary (time-varying) characteristics of speech signals forces to use numerous high-band filters. Hence, we use a deep neural network for estimating the high-band filter information and a gain factor for a specified narrowband information of the unseen signal. The objective analysis is done on the TIMIT dataset and RSR15 dataset. Additionally, the objective analysis is performed separately for the voiced speech as well as for the unvoiced speech as generally needed in speech processing. Subjective analysis is done on the RSR15 dataset.

show abstract

Section: Experimental Set-upmentioning

confidence: 99%

Artificial bandwidth extension using deep neural network and $H^\infty$ sampled-data control theory

Gupta,

Shekhawat

2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…In [42], the standard transmitter set‐up is needed to be changed, which makes it costly and is not feasible in general. Hence, we extended that work in [43] for the standard transmitter set‐up. In [43], the obtained infinite impulse response (IIR) synthesis filter contains the WB characteristics of the signal.…”

Section: Introductionmentioning

confidence: 98%

“…Hence, we extended that work in [43] for the standard transmitter set‐up. In [43], the obtained infinite impulse response (IIR) synthesis filter contains the WB characteristics of the signal. More filter coefficients are needed to represent the IIR synthesis filter for taking it in practical usage.…”

Section: Introductionmentioning

confidence: 98%

“…This optimisation has been used for a linear time‐invariant model [41]. We have also used it for ABE of the speech signal in [42, 43] using GMM modelling. In [42], the standard transmitter set‐up is needed to be changed, which makes it costly and is not feasible in general.…”

Section: Introductionmentioning

confidence: 99%

“…The benefit of utilising the DFT addition is in removal of the leaked information in these signals from the synthesis filter and LPF. In our prior works [42, 43], performances are analysed on a single data set by using the GMM modelling technique. In current work, we analysed the performances on two data sets using the DNN modelling technique.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

High‐band feature extraction for artificial bandwidth extension using deep neural network andH^∞optimisation

Gupta

Shekhawat

2020

IET signal process.

Self Cite

View full text Add to dashboard Cite

This work aims to enhance the quality of narrowband (0–4 kHz) voice signal in terms of frequency components, i.e. missing high‐frequency components in a range of 4–8 kHz. The proposed artificial bandwidth extension framework uses the H∞ optimisation. In this context, a signal model is used to get a better representation of wideband (0–8 kHz) information of a signal. The H∞ optimisation is used to obtain the synthesis filter for a given signal model, which is used to synthesise the high‐band (4–8 kHz) signal. The discrete Fourier transform addition is performed to add the narrowband signal and estimated high‐band signal for removing the leaked information from the synthesis filter and non‐ideal low pass filter. Gain adjustment is performed on the estimated high‐band signal to make its energy equal to the true high‐band signal. Non‐stationary characteristics of speech signals generate an assorted variety in synthesis filters and corresponding gain. For this, a deep neural network (DNN) is used to estimate the synthesis filter and gain by using the given narrowband information. The authors analyse the performances of the DNN model on two data sets. Objective and subjective analyses are carried out on these data sets.

show abstract

A New Framework for Artificial Bandwidth Extension Using $$H^\infty $$ Filtering

Gupta

Shekhawat

Sinha

2022

Circuits Syst Signal Process

View full text Add to dashboard Cite

Artificial Bandwidth Extension Using H^∞ Optimization and Speech Production Model

Cited by 5 publications

References 22 publications

Artificial bandwidth extension using deep neural network and $H^\infty$ sampled-data control theory

Artificial bandwidth extension using deep neural network and $H^\infty$ sampled-data control theory

High‐band feature extraction for artificial bandwidth extension using deep neural network andH^∞optimisation

A New Framework for Artificial Bandwidth Extension Using $$H^\infty $$ Filtering

Contact Info

Product

Resources

About

Artificial Bandwidth Extension Using H∞ Optimization and Speech Production Model

Cited by 5 publications

References 22 publications

Artificial bandwidth extension using deep neural network and $H^\infty$ sampled-data control theory

Artificial bandwidth extension using deep neural network and $H^\infty$ sampled-data control theory

High‐band feature extraction for artificial bandwidth extension using deep neural network andH∞optimisation

A New Framework for Artificial Bandwidth Extension Using $$H^\infty $$ Filtering

Contact Info

Product

Resources

About

Artificial Bandwidth Extension Using H^∞ Optimization and Speech Production Model

High‐band feature extraction for artificial bandwidth extension using deep neural network andH^∞optimisation