Model-based approaches to handling additive noise in reverberant environments

Gales, Mark J. F.; Wang, Y.-Q.

doi:10.1109/hscma.2011.5942377

Cited by 18 publications

(27 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As expected, these results do not differ much between the two considered observation models and compare favorably with the results presented in [9]. Briefly looking at the recursive variants of the observation models, we observed that they again performed slightly worse than the non-recursive variants (best results with 41.67% and 42.35% for the BFE-TI and the BFE-TV, respectively).…”

Section: ) Presence Of Reverberation and Noisesupporting

confidence: 88%

“…Using interacting sub-models, the predictive PDF may be approximated by the following weighted sum of submodel specific predictive PDFs: (9) Here, indicates the index of the active submodel at time instant . Due to the definition of our state vector in (5), the sub-model specific PDF is completely determined by the PDF , which is approximated by (10) (11) In (10), denotes a GAUSSIAN PDF with mean vector and covariance matrix .…”

Section: A a Priori Speech Modelmentioning

confidence: 99%

“…Several authors have published recognition results on this database [9], [25], [26]. While they mostly experimented with microphone array techniques to reduce the impact of reverberation, only [9] has been found to also work on the single-channel setup considered in this contribution.…”

Section: A Databases 1) Connected Digits Recognition Taskmentioning

confidence: 99%

“…The approach proposed by Wang and Gales [8], [9] also attempts a dynamic compensation, however, quite differently. By defining a spliced vector comprising several adjacent feature vectors, a frame-by-frame compensation is achieved, thus reducing the computational effort.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Bayesian Feature Enhancement for Reverberation and Noise Robust Speech Recognition

Leutnant

Krueger

Haeb‐Umbach

2013

IEEE Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

Abstract-In this contribution we extend a previously proposed BAYESIAN approach for the enhancement of reverberant logarithmic mel power spectral coefficients for robust automatic speech recognition to the additional compensation of background noise. A recently proposed observation model is employed whose time-variant observation error statistics are obtained as a side product of the inference of the a posteriori probability density function of the clean speech feature vectors. Further a reduction of the computational effort and the memory requirements are achieved by using a recursive formulation of the observation model. The performance of the proposed algorithms is first experimentally studied on a connected digits recognition task with artificially created noisy reverberant data. It is shown that the use of the time-variant observation error model leads to a significant error rate reduction at low signal-to-noise ratios compared to a time-invariant model. Further experiments were conducted on a 5000 word task recorded in a reverberant and noisy environment. A significant word error rate reduction was obtained demonstrating the effectiveness of the approach on real-world data.Index Terms-Robust automatic speech recognition, modelbased BAYESIAN feature enhancement, observation model for reverberant and noisy speech, recursive observation model.

show abstract

Section: ) Presence Of Reverberation and Noisesupporting

confidence: 88%

Section: A a Priori Speech Modelmentioning

confidence: 99%

Section: A Databases 1) Connected Digits Recognition Taskmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Bayesian Feature Enhancement for Reverberation and Noise Robust Speech Recognition

Leutnant

Krueger

Haeb‐Umbach

2013

IEEE Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

show abstract

“…Model-based approaches have also been extended to deal with the reverberant noise, e.g., in [7], [8] and [9], acoustic models are compensated using PMC. In [10], Reverberant VTS (RVTS) was proposed, where model-based VTS compensation was extended to handle the reverberant noise, as well as the background noise. RVTS allows the compensation formula for all the model parameters to be defined, and the parameters of the reverberant noise model can be estimated using maximum likelihood (ML) criterion.…”

Section: Introductionmentioning

confidence: 99%

Improving reverberant VTS for hands-free robust speech recognition

Wang

Gales

2011

2011 IEEE Workshop on Automatic Speech Recognition &Amp; Understanding

Self Cite

View full text Add to dashboard Cite

Abstract-Model-based approaches to handling additive background noise and channel distortion, such as Vector Taylor Series (VTS), have been intensively studied and extended in a number of ways. In previous work, VTS has been extended to handle both reverberant and background noise, yielding the Reverberant VTS (RVTS) scheme. In this work, rather than assuming the observation vector is generated by the reverberation of a sequence of background noise corrupted speech vectors, as in RVTS, the observation vector is modelled as a superposition of the background noise and the reverberation of clean speech. This yields a new compensation scheme RVTS Joint (RVTSJ), which allows an easy formulation for joint estimation of both additive and reverberation noise parameters. These two compensation schemes were evaluated and compared on a simulated reverberant noise corrupted AURORA4 task. Both yielded large gains over VTS baseline system, with RVTSJ outperforming the previous RVTS scheme.

show abstract

Robust coherence-based spectral enhancement for speech recognition in adverse real-world environments

Barfuss

Huemmer

Schwarz

et al. 2017

Computer Speech & Language

View full text Add to dashboard Cite

Speech recognition in adverse real-world environments is highly affected by reverberation and non-stationary background noise. A well-known strategy to reduce such undesired signal components in multi-microphone scenarios is spatial filtering of the microphone signals. In this article, we demonstrate that an additional coherence-based postfilter, which is applied to the beamformer output signal to remove diffuse interference components from the latter, is an effective means to further improve the recognition accuracy of modern deep learning speech recognition systems. To this end, the 3rd CHiME Speech Separation and Recognition Challenge (CHiME-3) baseline speech enhancement system is extended by a coherence-based postfilter and the postfilter's impact on the Word Error Rates (WERs) of a state-of-the-art automatic speech recognition system is investigated for the realistic noisy environments provided by CHiME-3. To determine the time-and frequency-dependent postfilter gains, we use Direction-of-Arrival (DOA)-dependent and DOA-independent estimators of the coherent-to-diffuse power ratio as an approximation of the short-time signal-to-noise ratio. Our experiments show that incorporating coherence-based postfiltering into the CHiME-3 baseline speech enhancement system leads to a significant reduction of the WERs, with relative improvements of up to 11.31%. 1 A. Schwarz was with the Friedrich-Alexander University of Erlangen-Nürnberg while the work has been conducted. He is now with Amazon

show abstract

Model-based approaches to handling additive noise in reverberant environments

Cited by 18 publications

References 17 publications

Bayesian Feature Enhancement for Reverberation and Noise Robust Speech Recognition

Bayesian Feature Enhancement for Reverberation and Noise Robust Speech Recognition

Improving reverberant VTS for hands-free robust speech recognition

Robust coherence-based spectral enhancement for speech recognition in adverse real-world environments

Contact Info

Product

Resources

About