Speech Intelligibility Prediction Based on the Envelope Power Spectrum Model with the Dynamic Compressive Gammachirp Auditory Filterbank

Yamamoto, Kazumasa; Matsui, Toshie; Araki, Shoko; Kinoshita, Keisuke; Nakatani, Tomohiro

doi:10.21437/interspeech.2016-652

Cited by 7 publications

(27 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are seven modulation filters whose power spectra are W f c env (fenv) for the modulation center frequency of f c env , as illustrated in Fig. 2 and described in [5,9].…”

Section: Sdr In the Envelope Modulation Domainmentioning

confidence: 99%

“…The following procedure is the same as that used in the sEPSM algorithm [5,9], except that SDRenv is used instead of SNRenv.…”

Section: Transformation From Sdrenv To Percent Correctmentioning

confidence: 99%

“…We compared the proposed GEDI with the competitive models, i.e., dcGC-sEPSM, original sEPSM, and the STOI, CSII, and HASPI. The conditions of these enhanced algorithms are described in [9].…”

Section: Evaluation Of the Speech Enhancement Algorithmsmentioning

confidence: 99%

“…The sEPSM is intended to assess the intelligibility of speech sounds processed by spectral subtraction (SS). The sEPSM was then extended in several directions [7,8,9]. Yamamoto et al [9] extended the sEPSM with the dynamic compressive gammachirp filterbank (dcGC-FB) [10], in which the level-dependent frequency selectivity and gain of the auditory filter were reasonably determined by the data obtained from psychoacoustic masking experiments.…”

Section: Introductionmentioning

confidence: 99%

“…The sEPSM was then extended in several directions [7,8,9]. Yamamoto et al [9] extended the sEPSM with the dynamic compressive gammachirp filterbank (dcGC-FB) [10], in which the level-dependent frequency selectivity and gain of the auditory filter were reasonably determined by the data obtained from psychoacoustic masking experiments. It was demonstrated that the dcGC-sEPSM predicted the subjective results of the Wiener filtering better than the original sEPSM, CSII [4], and STOI [2] measures.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Predicting Speech Intelligibility Using a Gammachirp Envelope Distortion Index Based on the Signal-to-Distortion Ratio

Yamamoto¹,

Matsui²,

Araki³

et al. 2017

Interspeech 2017

Self Cite

View full text Add to dashboard Cite

A new intelligibility prediction measure, called "Gammachirp Envelope Distortion Index (GEDI)" is proposed for the evaluation of speech enhancement algorithms. This model calculates the signal-to-distortion ratio (SDR) in envelope responses SDR env derived from the gammachirp filterbank outputs of clean and enhanced speech, and is an extension of the speech based envelope power spectrum model (sEPSM) to improve prediction and usability. An evaluation was performed by comparing human subjective results and model predictions for the speech intelligibility of noise-reduced sounds processed by spectral subtraction and a recent Wiener filtering technique. The proposed GEDI predicted the subjective results of the Wiener filtering better than those predicted by the original sEPSM and well-known conventional measures, i.e., STOI, CSII, and HASPI.

show abstract

“…There are seven modulation filters whose power spectra are W f c env (fenv) for the modulation center frequency of f c env , as illustrated in Fig. 2 and described in [5,9].…”

Section: Sdr In the Envelope Modulation Domainmentioning

confidence: 99%

“…The following procedure is the same as that used in the sEPSM algorithm [5,9], except that SDRenv is used instead of SNRenv.…”

Section: Transformation From Sdrenv To Percent Correctmentioning

confidence: 99%

Section: Evaluation Of the Speech Enhancement Algorithmsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Predicting Speech Intelligibility Using a Gammachirp Envelope Distortion Index Based on the Signal-to-Distortion Ratio

Yamamoto¹,

Matsui²,

Araki³

et al. 2017

Interspeech 2017

Self Cite

View full text Add to dashboard Cite

show abstract

GEDI: Gammachirp envelope distortion index for predicting intelligibility of enhanced speech

Yamamoto

Araki²,

Kinoshita³

et al. 2020

Speech Communication

View full text Add to dashboard Cite

Speech intelligibility prediction with the dynamic compressive gammachirp filterbank and modulation power spectrum

Yamamoto

Matsui

Araki³

et al. 2019

Acoust. Sci. & Tech.

Self Cite

View full text Add to dashboard Cite

The speech-based envelope power spectrum model (sEPSM) was developed to predict the speech intelligibility of sounds produced by nonlinear speech enhancement algorithms such as spectral subtraction. It is a linear model with a linear, level-independent gammatone (GT) filterbank as the front-end. Therefore, it seems difficult to evaluate speech sounds with low and high sound pressure levels (SPLs) consistently because the intelligibility of the speech is dependent on the SPL as well as the signal-to-noise ratio. In this study, the sEPSM was extended with the dynamic compressive gammachirp (dcGC) auditory filterbank and a ''common'' normalization factor of the modulation power spectrum component to improve the predictability of the model. For evaluating the proposed model, we performed subjective experiments on the intelligibility of speech sounds enhanced by spectral subtraction and a Wiener filter algorithm. We compared the subjective speech intelligibility scores with the objective scores predicted by the proposed dcGC-sEPSM, original GT-sEPSM, and other well-known conventional methods such as the short-time objective intelligibility measure (STOI), coherence speech intelligibility index (CSII), and hearing aid speech perception index (HASPI). The result shows that the proposed dcGC-sEPSM predicted the subjective results better did than the other methods.

show abstract

Speech Intelligibility Prediction Based on the Envelope Power Spectrum Model with the Dynamic Compressive Gammachirp Auditory Filterbank

Cited by 7 publications

References 0 publications

Predicting Speech Intelligibility Using a Gammachirp Envelope Distortion Index Based on the Signal-to-Distortion Ratio

Predicting Speech Intelligibility Using a Gammachirp Envelope Distortion Index Based on the Signal-to-Distortion Ratio

GEDI: Gammachirp envelope distortion index for predicting intelligibility of enhanced speech

Speech intelligibility prediction with the dynamic compressive gammachirp filterbank and modulation power spectrum

Contact Info

Product

Resources

About