A summary of the REVERB challenge: state-of-the-art and remaining challenges in reverberant speech processing research

Kinoshita, Keisuke; Delcroix, Marc; Gannot, Sharon; Habets, Emanuël A. P.; Haeb‐Umbach, Reinhold; Kellermann, Walter; Leutnant, Volker; Maas, Roland; Nakatani, Tomohiro; Raj, Bhiksha; Sehr, Armin; Yoshioka, Takuya

doi:10.1186/s13634-016-0306-6

Cited by 299 publications

(220 citation statements)

References 18 publications

Supporting

Mentioning

219

Contrasting

Unclassified

Order By: Relevance

“…Listening tests for speech quality have previously been reported in the literature with positive results [5,7,8]. Quality is however highly subjective, since whether a signal sounds 'good' or 'poor' is based on listeners' preferences.…”

Section: Introductionmentioning

confidence: 99%

“…In the past few years, deep neural networks (DNNs) [2,3] have emerged as a promising approach for SE, outperforming earlier approaches. SE has been proven useful as a preprocessing step for automatic speech recognition systems to decrease their word error rates [4,5,6], but the field also aims to make degraded speech easier to understand and/or more comfortable to listen to for humans [5,7,8].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Subjective Intelligibility of Deep Neural Network-Based Speech Enhancement

Gelderblom¹,

Tronstad²,

Viggen³

2017

Interspeech 2017

View full text Add to dashboard Cite

Recent literature indicates increasing interest in deep neural networks for use in speech enhancement systems. Currently, these systems are mostly evaluated through objective measures of speech quality and/or intelligibility. Subjective intelligibility evaluations of these systems have so far not been reported. In this paper we report the results of a speech recognition test with 15 participants, where the participants were asked to pick out words in background noise before and after enhancement using a common deep neural network approach. We found that, although the objective measure STOI predicts that intelligibility should improve or at the very least stay the same, the speech recognition threshold, which is a measure of intelligibility, deteriorated by 4 dB. These results indicate that STOI is not a good predictor for the subjective intelligibility of deep neural network-based speech enhancement systems. We also found that the postprocessing technique of global variance normalisation does not significantly affect subjective intelligibility.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Subjective Intelligibility of Deep Neural Network-Based Speech Enhancement

Gelderblom¹,

Tronstad²,

Viggen³

2017

Interspeech 2017

View full text Add to dashboard Cite

show abstract

“…In [44], it has been shown that measures such as fSNR and CD can exhibit a high correlation with subjective listening tests when evaluating the overall quality and the perceived amount of reverberation for a wide range of state-of-theart dereverberation (and noise reduction) techniques. These signal-based measures are intrusive measures, generating a similarity score between a test signal and a reference signal.…”

Section: Acoustic Systems Instrumental Performance Measures and Algmentioning

confidence: 99%

Improving the conditioning of the optimization criterion in acoustic multi-channel equalization using shorter reshaping filters

Kodrasi

Doclo

2018

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

In acoustic multi-channel equalization techniques, such as complete multi-channel equalization based on the multiple-input/output inverse theorem (MINT), relaxed multi-channel least-squares (RMCLS), and partial multi-channel equalization based on MINT (PMINT), the length of the reshaping filters is generally chosen such that perfect dereverberation can be achieved for perfectly estimated room impulse responses (RIRs). However, since in practice the available RIRs typically differ from the true RIRs, this reshaping filter length may not be optimal. This paper provides a mathematical analysis of the robustness increase of equalization techniques against RIR perturbations when using a shorter reshaping filter length than conventionally used. Based on the condition number of the (weighted) convolution matrix of the RIRs, a mathematical relationship between the reshaping filter length and the robustness against RIR perturbations is established. It is shown that shorter reshaping filters than conventionally used yield a smaller condition number, i.e., a higher robustness against RIR perturbations. In addition, we propose an automatic non-intrusive procedure for determining the reshaping filter length based on the L-curve. Simulation results confirm that using a shorter reshaping filter length than conventionally used yields a significant increase in robustness against RIR perturbations for MINT, RMCLS, and PMINT. Furthermore, it is shown that PMINT using an optimal intrusively determined reshaping filter length outperforms all other considered techniques. Finally, it is shown that the automatic non-intrusively determined reshaping filter length in PMINT yields a similar performance as the optimal intrusively determined reshaping filter length.

show abstract

“…Excerpts of real ambient noise from the voiceHome corpus [36] were included in the test set instead of SSN. These stationary diffuse noises were recorded using a microphone pair with 10 cm spacing in three different apartments in a similar fashion as in [37]. Nonoverlapping time frames with 100 ms duration containing unique but nonidentical phonemes for target and interference were extracted to compute the features.…”

Section: Signal Generation and Feature Extractionmentioning

confidence: 99%

Keyword Based Speaker Localization: Localizing a Target Speaker in a Multi-speaker Environment

Sivasankaran¹,

Fohr²

2018

Interspeech 2018

View full text Add to dashboard Cite

To cite this version:Sunit Sivasankaran, Emmanuel Vincent, Dominique Fohr. Keyword-based speaker localization: Localizing a target speaker in a multi-speaker environment. Interspeech 2018 -19th AbstractSpeaker localization is a hard task, especially in adverse environmental conditions involving reverberation and noise. In this work we introduce the new task of localizing the speaker who uttered a given keyword, e.g., the wake-up word of a distantmicrophone voice command system, in the presence of overlapping speech. We employ a convolutional neural network based localization system and investigate multiple identifiers as additional inputs to the system in order to characterize this speaker.We conduct experiments using ground truth identifiers which are obtained assuming the availability of clean speech and also in realistic conditions where the identifiers are computed from the corrupted speech. We find that the identifier consisting of the ground truth time-frequency mask corresponding to the target speaker provides the best localization performance and we propose methods to estimate such a mask in adverse reverberant and noisy conditions using the considered keyword.

show abstract

A summary of the REVERB challenge: state-of-the-art and remaining challenges in reverberant speech processing research

Cited by 299 publications

References 18 publications

Subjective Intelligibility of Deep Neural Network-Based Speech Enhancement

Subjective Intelligibility of Deep Neural Network-Based Speech Enhancement

Improving the conditioning of the optimization criterion in acoustic multi-channel equalization using shorter reshaping filters

Keyword Based Speaker Localization: Localizing a Target Speaker in a Multi-speaker Environment

Contact Info

Product

Resources

About