Missing‐Data Techniques: Feature Reconstruction

Gemmeke, Jort F.; Remes, Ulpu

doi:10.1002/9781118392683.ch15

Cited by 2 publications

(1 citation statement)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Perceptual restoration has also motivated missing data approaches to noise-robust ASR (Cooke et al, 2001). These include techniques that recognise noise-corrupted speech based on observed, incomplete information, and approaches that restore unobserved clean speech information prior to recognition (Barker, 2012;Gemmeke and Remes, 2012).…”

Section: Introductionmentioning

confidence: 99%

Comparing human and automatic speech recognition in a perceptual restoration experiment

Remes

López

Juvela

et al. 2016

Computer Speech & Language

Self Cite

View full text Add to dashboard Cite

Speech that has been distorted by introducing spectral or temporal gaps is still perceived as continuous and complete by human listeners, so long as the gaps are filled with additive noise of sufficient intensity. When such perceptual restoration occurs, the speech is also more intelligible compared to the case in which noise has not been added in the gaps. This observation has motivated so-called 'missing data' systems for automatic speech recognition (ASR), but there have been few attempts to determine whether such systems are a good model of perceptual restoration in human listeners. Accordingly, the current paper evaluates missing data ASR in a perceptual restoration task. We evaluated two systems that use a new approach to bounded marginalisation in the cepstral domain, and a bounded conditional mean imputation method. Both methods model available speech information as a clean-speech posterior distribution that is subsequently passed to an ASR system. The proposed missing data ASR systems were evaluated using distorted speech, in which spectro-temporal gaps were optionally filled with additive noise. Speech recognition performance of the proposed systems was compared against a baseline ASR system, and with human speech recognition performance on the same task. We conclude that missing data methods improve speech recognition performance in a manner that is consistent with perceptual restoration in human listeners.

show abstract

Section: Introductionmentioning

confidence: 99%