• Corpus ID: 18328317

Joint Estimation of Reverberation Time and Direct-to-Reverberation Ratio from Speech using Auditory-Inspired Features

@article{Xiong2015JointEO,
  title={Joint Estimation of Reverberation Time and Direct-to-Reverberation Ratio from Speech using Auditory-Inspired Features},
  author={Feifei Xiong and Stefan Goetze and Bernd T. Meyer},
  journal={ArXiv},
  year={2015},
  volume={abs/1510.04620}
}
Blind estimation of acoustic room parameters such as the reverberation time $T_\mathrm{60}$ and the direct-to-reverberation ratio ($\mathrm{DRR}$) is still a challenging task, especially in case of blind estimation from reverberant speech signals. In this work, a novel approach is proposed for joint estimation of $T_\mathrm{60}$ and $\mathrm{DRR}$ from wideband speech in noisy conditions. 2D Gabor filters arranged in a filterbank are exploited for extracting features, which are then used as… 

Figures from this paper

Joint Estimation of Reverberation Time and Early-To-Late Reverberation Ratio From Single-Channel Speech Signals
TLDR
From state-of-the-art algorithms that were tested in the acoustic characterization of environments challenge, jROPE achieves comparable results among the best for all individual tasks (RT and ELR estimation from full-band and sub-band signals).
Single-Channel Blind Direct-to-Reverberation Ratio Estimation Using Masking
TLDR
Single-channel DRR estimation is formulated as an extraction task of two signal components from the recorded audio and outperforms state-of-the-art singleand multi-channel methods on the ACE challenge data corpus.
Exploring Auditory-Inspired Acoustic Features for Room Acoustic Parameter Estimation From Monaural Speech
TLDR
Compared to state-of-the-art algorithms that were tested in the acoustic characterisation of environments (ACE) challenge, the ROPE model is the only one that is among the best for all individual tasks (RT and ELR estimation from fullband and subband signals).
Estimation of Room Acoustic Parameters: The ACE Challenge
TLDR
The acoustic characterization of environments (ACE) challenge showed that T60 estimation is a mature field where analytical approaches dominate whilst DRR estimation is one of the less mature fields where machine learning approaches are currently more successful.
Binaural Direct-to-Reverberant Energy Ratio and Speaker Distance Estimation
TLDR
Two novel approaches to estimate the direct-to-reverberant energy ratio (DRR) of binaural signals are presented, based on the interaural magnitude-squared coherence and stochastic maximum likelihood beamforming.
Joint Estimation Of Acoustic Parameters From Single-Microphone Speech Observations
  • D. Looney, N. Gaubitch
  • Physics, Computer Science
    ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2020
TLDR
Results show the estimator compares favourably with respect to the state-of-the-art for unseen and real acoustic scenarios.
Online Blind Reverberation Time Estimation Using CRNNs
TLDR
This work proposes to use a convolutional recurrent neural network (CRNN) for blind T60 estimation as it combines the parametric efficiency of CNNs with the online estimation of recurrent neural networks and, in contrast to CNNs, can process time-sequences of variable length.
Combination strategy based on relative performance monitoring for multi-stream reverberant speech recognition
TLDR
A room parameter estimation model is proposed to establish a reliable combination strategy which performs on either DNN posterior probabilities or word lattices which is highly correlated to ASR performances between multiple streams, i.e., relative performance monitoring.
Performance comparison of real-time single-channel speech dereverberation algorithms
TLDR
Experimental results show that all four algorithms are capable of providing benefits in reverberant environments even with moderate background noises, and low complexity and latency indicate their potential for real-time applications.
...
1
2
...

References

SHOWING 1-10 OF 42 REFERENCES
Noise-robust reverberation time estimation using spectral decay distributions with reduced computational cost
TLDR
A novel T60 estimation algorithm based on spectral decay distributions that provides robustness to additive noise for a range of realistic noise types for signal-to-noise ratios in the range 0 to 35 dB and T60s between 200 and 950 ms is described.
Temporal Dynamics for Blind Measurement of Room Acoustical Parameters
  • T. Falk, W. Chan
  • Physics
    IEEE Transactions on Instrumentation and Measurement
  • 2010
TLDR
Experiments suggest that estimators of subjective perception of spectral coloration, reverberant tail effect, and overall speech quality can be obtained with an adaptive speech-to-reverberation modulation energy ratio measure.
Blind estimation of reverberation time.
TLDR
A method for estimating RT without prior knowledge of sound sources or room geometry is presented, and results obtained for simulated and real room data are in good agreement with the real RT values.
Monaural room acoustic parameters from music and speech.
TLDR
An approach which uses statistical machine learning, previously developed for speech, is extended to work with music to estimate parameters relating to the balance of early and late energies in the impulse response.
Blind estimation of reverberation time based on the distribution of signal decay rates
TLDR
A method to estimate the reverberation time using a property of the distribution of the decay rates in the short-time Fourier transform domain and results using simulated and real reverberant speech signals are demonstrated.
Direct-to-Reverberant Ratio estimation using a null-steered beamformer
TLDR
A novel DRR estimation algorithm applicable where the signal was recorded with two or more microphones, such as mobile communications devices and laptops is described, which yields accurate DRR estimates to within ±4 dB across a wide variety of room sizes, reverberation times and source-receiver distances.
Extracting Room Reverberation Time from Speech Using Artificial Neural Networks
A novel method to extract the reverberation time from reverberated speech utterances is presented. In this study, speech utterances are restricted to pronounced digits; uncontrolled discourse is not
Single-Microphone LP Residual Skewness-Based Inverse Filtering of the Room Impulse Response
TLDR
The proposed method is shown to be superior to the method by Wu and Wang, particularly in terms of reducing the coloration effect, and the effectiveness of the proposed method for time delay estimation (TDE).
Blind estimation of reverberation time based on spectro-temporal modulation filtering
A novel method for blind estimation of the reverberation time (RT60) is proposed based on applying spectro-temporal modulation filters to time-frequency representations. 2D-Gabor filters arranged in
An Improved Algorithm for Blind Reverberation Time Estimation
TLDR
An improved algorithm for the estimation of the reverberation time (RT) from reverberant speech signals is presented, based on a simple statistical model for the sound decay such that the RT can be estimated by means of a maximum-likelihood (ML) estimator.
...
1
2
3
4
5
...