A postfiltering approach for dual-microphone smartphones

Martín-Doñas, Juan M.; López-Espejo, Iván; Gómez, Ángel M.; Peinado, Antonio M.

doi:10.21437/iberspeech.2018-30

Cited by 3 publications

(7 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The MCRA framework was extended to multi-channel speech signals in Reference [4]. This is the SPP estimator that we used in our previous works [15,27]. A major drawback of the MCRA scheme is the lack of robustness in case of a time-varying SNR, which makes noise changes to be detected as speech presence.…”

Section: A Priori Sap Estimationmentioning

confidence: 99%

“…On the other hand, a clean speech PSD estimate is more difficult to obtain because of its higher variability. In Reference [27], we proposed two different estimators that make use of the noisy speech and noise statistics and the RTF between microphones. In the following, we describe both clean speech PSD estimators, omitting time and frequency indices for simplicity.…”

Section: Single-channel Speech and Noise Psd Estimatorsmentioning

confidence: 99%

“…The postfiltering approach has also been studied on dual-microphone scenarios [25,26]. For example, in Reference [27] we extended our eKF-RTF framework with the use of postfilters along with MVDR beamforming and the SPP estimator of Reference [4] in order to improve noise reduction. These postfilters exploit the SPP and the RTFs previously obtained to estimate the required single-channel statistics.…”

Section: Introductionmentioning

confidence: 99%

“…In this work we analyze and further extend our dual-microphone speech enhancement eKF-RTF framework presented in References [15,27]. This extension is developed in a threefold way.…”

Section: Introductionmentioning

confidence: 99%

“…Then, we propose a novel SAP estimator suitable for dual-microphone smartphones, which exploits the spatial structure of the noise and the power differences between microphones, showing improvements with respect to the estimator used in our previous work. Third, we take advantage of the better estimates of SPP, RTFs and single-channel statistics to redefine the postfilters described in Reference [27] and propose new ones. As a result, we end up with a comprehensive dual-microphone speech enhancement system for smartphones that shows a great performance in terms of both speech quality and intelligibility when compared to other state-of-the-art approaches.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Dual-Channel Speech Enhancement Based on Extended Kalman Filter Relative Transfer Function Estimation

et al. 2019

Self Cite

View full text Add to dashboard Cite

This paper deals with speech enhancement in dual-microphone smartphones using beamforming along with postfiltering techniques. The performance of these algorithms relies on a good estimation of the acoustic channel and speech and noise statistics. In this work we present a speech enhancement system that combines the estimation of the relative transfer function (RTF) between microphones using an extended Kalman filter framework with a novel speech presence probability estimator intended to track the noise statistics' variability. The available dual-channel information is exploited to obtain more reliable estimates of clean speech statistics. Noise reduction is further improved by means of postfiltering techniques that take advantage of the speech presence estimation. Our proposal is evaluated in different reverberant and noisy environments when the smartphone is used in both close-talk and far-talk positions. The experimental results show that our system achieves improvements in terms of noise reduction, low speech distortion and better speech intelligibility compared to other state-of-the-art approaches.

show abstract

Section: A Priori Sap Estimationmentioning

confidence: 99%

Section: Single-channel Speech and Noise Psd Estimatorsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…In this work we analyze and further extend our dual-microphone speech enhancement eKF-RTF framework presented in References [15,27]. This extension is developed in a threefold way.…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Dual-Channel Speech Enhancement Based on Extended Kalman Filter Relative Transfer Function Estimation

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

Opportunities and limitations: A comparative analysis of citizen science and expert recordings for bioacoustic research

et al. 2021

View full text Add to dashboard Cite

Citizen science is an approach that has become increasingly popular in recent years. Despite this growing popularity, there still is widespread scepticism in the academic world about the validity and quality of data from citizen science projects. And although there might be great potential, citizen science is a rarely used approach in the field of bioacoustics. To better understand the possibilities, but also the limitations, we here evaluated data generated in a citizen science project on nightingale song as a case study. We analysed the quantity and quality of song recordings made in a non-standardized way with a smartphone app by citizen scientists and the standardized recordings made with professional equipment by academic researchers. We made comparisons between the recordings of the two approaches and among the user types of the app to gain insights into the temporal recording patterns, the quantity and quality of the data. To compare the deviation of the acoustic parameters in the recordings with smartphones and professional devices from the original song recordings, we conducted a playback test. Our results showed that depending on the user group, citizen scientists produced many to a lot of recordings of valid quality for further bioacoustic research. Differences between the recordings provided by the citizen and the expert group were mainly caused by the technical quality of the devices used—and to a lesser extent by the citizen scientists themselves. Especially when differences in spectral parameters are to be investigated, our results demonstrate that the use of the same high-quality recording devices and calibrated external microphones would most likely improve data quality. We conclude that many bioacoustic research questions may be carried out with the recordings of citizen scientists. We want to encourage academic researchers to get more involved in participatory projects to harness the potential of citizen science—and to share scientific curiosity and discoveries more directly with society.

show abstract

Dual-channel eKF-RTF framework for speech enhancement with DNN-based speech presence estimation

Martín-Doñas¹,

Peinado²,

Espejo³

et al. 2021

IberSPEECH 2021

View full text Add to dashboard Cite

This paper presents a dual-channel speech enhancement framework that effectively integrates deep neural network (DNN) mask estimators. Our framework follows a beamforming-plus-postfiltering approach intended for noise reduction on dual-microphone smartphones. An extended Kalman filter is used for the estimation of the relative acoustic channel between microphones, while the noise estimation is performed using a speech presence probability estimator. We propose the use of a DNN estimator to improve the prediction of the speech presence probabilities without making any assumption about the statistics of the signals. We evaluate and compare different dual-channel features to improve the accuracy of this estimator, including the power and phase difference between the speech signals at the two microphones. The proposed integrated scheme is evaluated in different reverberant and noisy environments when the smartphone is used in both close-and far-talk positions. The experimental results show that our approach achieves significant improvements in terms of speech quality, intelligibility, and distortion when compared to other approaches based only on statistical signal processing.

show abstract

A postfiltering approach for dual-microphone smartphones

Cited by 3 publications

References 18 publications

Dual-Channel Speech Enhancement Based on Extended Kalman Filter Relative Transfer Function Estimation

Dual-Channel Speech Enhancement Based on Extended Kalman Filter Relative Transfer Function Estimation

Opportunities and limitations: A comparative analysis of citizen science and expert recordings for bioacoustic research

Dual-channel eKF-RTF framework for speech enhancement with DNN-based speech presence estimation

Contact Info

Product

Resources

About