Outcome measures based on classification performance fail to predict the intelligibility of binary-masked speech

Kressner, Abigail A.; May, Tim; Rozell, Christopher J.

doi:10.1121/1.4952439

Cited by 9 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In general, these results suggest that the STOI tends to underestimate human performance for unprocessed reverberant-noisy speech and overestimate human performance for processed speech. The current observation is somewhat different from those for noisy speech enhancement, for which the STOI overpredicts intelligibility for both unprocessed and processed signals (Healy et al, 2015;Kressner et al, 2016). Figure 10 compares ESTOI-predicted recognition scores and actual recognition scores.…”

Section: B Objective Measures Of Intelligibilitycontrasting

confidence: 56%

A deep learning based segregation algorithm to increase speech intelligibility for hearing-impaired listeners in reverberant-noisy conditions

Zhao

Wang

Johnson

et al. 2018

The Journal of the Acoustical Society of America

View full text Add to dashboard Cite

Recently, deep learning based speech segregation has been shown to improve human speech intelligibility in noisy environments. However, one important factor not yet considered is room reverberation, which characterizes typical daily environments. The combination of reverberation and background noise can severely degrade speech intelligibility for hearing-impaired (HI) listeners. In the current study, a deep learning based time-frequency masking algorithm was proposed to address both room reverberation and background noise. Specifically, a deep neural network was trained to estimate the ideal ratio mask, where anechoic-clean speech was considered as the desired signal. Intelligibility testing was conducted under reverberant-noisy conditions with reverberation time T 60 ¼ 0.6 s, plus speech-shaped noise or babble noise at various signal-to-noise ratios. The experiments demonstrated that substantial speech intelligibility improvements were obtained for HI listeners. The algorithm was also somewhat beneficial for normal-hearing (NH) listeners. In addition, sentence intelligibility scores for HI listeners with algorithm processing approached or matched those of young-adult NH listeners without processing. The current study represents a step toward deploying deep learning algorithms to help the speech understanding of HI listeners in everyday conditions. V

show abstract

Section: B Objective Measures Of Intelligibilitycontrasting

confidence: 56%

A deep learning based segregation algorithm to increase speech intelligibility for hearing-impaired listeners in reverberant-noisy conditions

Zhao

Wang

Johnson

et al. 2018

The Journal of the Acoustical Society of America

View full text Add to dashboard Cite

show abstract

“…A recent study highlighted potential limitations of STOI in predicting the intelligibility of binary-masked speech [22]. Two observations from this study support these findings.…”

Section: Discussionsupporting

confidence: 83%

Comparing the Influence of Spectro-Temporal Integration in Computational Speech Segregation

et al. 2016

Self Cite

View full text Add to dashboard Cite

The goal of computational speech segregation systems is to automatically segregate a target speaker from interfering maskers. Typically, these systems include a feature extraction stage in the front-end and a classification stage in the back-end. A spectrotemporal integration strategy can be applied in either the frontend, using the so-called delta features, or in the back-end, using a second classifier that exploits the posterior probability of speech from the first classifier across a spectro-temporal window. This study systematically analyzes the influence of such stages on segregation performance, the error distributions and intelligibility predictions. Results indicated that it could be problematic to exploit context in the back-end, even though such a spectro-temporal integration stage improves the segregation performance. Also, the results emphasized the potential need of a single metric that comprehensively predicts computational segregation performance and correlates well with intelligibility. The outcome of this study could help to identify the most effective spectro-temporal integration strategy for computational segregation systems.

show abstract

“…The value range of STOI is typically between 0 and 1, which can be interpreted as percent correct. Although STOI tends to overpredict intelligibility scores [64], [102], no alternative metric has been shown to consistently correlate with human intelligibility better. For speech quality, PESQ (perceptual evaluation of speech quality) is the standard metric [140] and recommended by the International Telecommunication Union (ITU) [87].…”

Section: Training Targetsmentioning

confidence: 99%

Supervised Speech Separation Based on Deep Learning: An Overview

Wang

Chen

2018

IEEE/ACM Trans. Audio Speech Lang. Process.

1,267

683

View full text Add to dashboard Cite

Speech separation is the task of separating target speech from background interference. Traditionally, speech separation is studied as a signal processing problem. A more recent approach formulates speech separation as a supervised learning problem, where the discriminative patterns of speech, speakers, and background noise are learned from training data. Over the past decade, many supervised separation algorithms have been put forward. In particular, the recent introduction of deep learning to supervised speech separation has dramatically accelerated progress and boosted separation performance. This paper provides a comprehensive overview of the research on deep learning based supervised speech separation in the last several years. We first introduce the background of speech separation and the formulation of supervised separation. Then, we discuss three main components of supervised separation: learning machines, training targets, and acoustic features. Much of the overview is on separation algorithms where we review monaural methods, including speech enhancement (speech-nonspeech separation), speaker separation (multitalker separation), and speech dereverberation, as well as multimicrophone techniques. The important issue of generalization, unique to supervised learning, is discussed. This overview provides a historical perspective on how advances are made. In addition, we discuss a number of conceptual issues, including what constitutes the target source.

show abstract

Outcome measures based on classification performance fail to predict the intelligibility of binary-masked speech

Cited by 9 publications

References 21 publications

A deep learning based segregation algorithm to increase speech intelligibility for hearing-impaired listeners in reverberant-noisy conditions

A deep learning based segregation algorithm to increase speech intelligibility for hearing-impaired listeners in reverberant-noisy conditions

Comparing the Influence of Spectro-Temporal Integration in Computational Speech Segregation

Supervised Speech Separation Based on Deep Learning: An Overview

Contact Info

Product

Resources

About