Automatic estimation of the first three subglottal resonances from adults’ speech signals with application to speaker height estimation

Arsikere, Harish; Leung, Gary K. F.; Alwan, Abeer

doi:10.1016/j.specom.2012.06.004

Cited by 20 publications

(50 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [16], we showed that Snack is sufficiently accurate for SGR estimation in quiet environments. Here, we evaluate the performance of Snack in noise and show that it is reasonably accurate for the purpose of noise-robust SGR estimation as well.…”

Section: Noise Robustness Of the Sgr Estimation Algorithm In [16]mentioning

confidence: 95%

“…In SGR warping on the other hand, the reference SGRs are determined a priori (using a database of accelerometer recordings of subglottal acoustics), while the target SGRs are estimated from the given utterance in two steps. First, initial estimates (Sg1 i t , Sg2 i t , Sg3 i t ) are obtained using our SGR estimation algorithm [16]. Then, refined estimates (Sg1t,Sg2t andSg3t) are obtained by applying corrections as per Eq.…”

Section: Vtln Versus Sgr Warpingmentioning

confidence: 99%

“…In [16], we proposed an algorithm to estimate SGRs from speech signals in quiet. We showed in [3] that the algorithm can be used for SGR warping in clean conditions.…”

Section: Sgr Warping In Additive Noisementioning

confidence: 99%

“…For the purposes of this paper, it suffices to know that the algorithm in [16] depends on 5 speech parameters:…”

Section: Noise Robustness Of the Sgr Estimation Algorithm In [16]mentioning

confidence: 99%

“…Here, we evaluate the performance of Snack in noise and show that it is reasonably accurate for the purpose of noise-robust SGR estimation as well. Since SGR estimation happens at the utterance level and not at the frame level (SGRs of a given speaker are almost time invariant [16]), it does not demand very accurate F 0 and formant tracking.…”

Section: Noise Robustness Of the Sgr Estimation Algorithm In [16]mentioning

confidence: 99%

See 4 more Smart Citations

Frequency warping using subglottal resonances: Complementarity with VTLN and robustness to additive noise

Arsikere

Alwan

2014

2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

Based on our recently-proposed frequency-warping scheme using subglottal resonances (SGRs), this paper addresses two wellknown limitations of conventional vocal-tract length normalization (VTLN): (1) its sub-optimal nature owing to the lack of frequencydependent scaling, and (2) sensitivity to noise. Based on the idea of filter-bank interpolation, a novel approach is proposed to realize the combined effect of VTLN and SGR-based warping (which provides frequency-dependent scaling). Using the Wall Street Journal database and the conventional MFCC front end, SGR warping is shown to be complementary to VTLN in performance. Since SGR warping depends more on the given signal and less on models trained a priori, we argue that SGR warping is less sensitive to noise than VTLN. Through experiments on the AURORA-4 database with power-normalized cepstral coefficients as noise-robust front-end features, we show that SGR warping is better than VTLN, in clean as well as multi-conditional training.

show abstract

Section: Noise Robustness Of the Sgr Estimation Algorithm In [16]mentioning

confidence: 95%

Section: Vtln Versus Sgr Warpingmentioning

confidence: 99%

“…In [16], we proposed an algorithm to estimate SGRs from speech signals in quiet. We showed in [3] that the algorithm can be used for SGR warping in clean conditions.…”

Section: Sgr Warping In Additive Noisementioning

confidence: 99%

“…For the purposes of this paper, it suffices to know that the algorithm in [16] depends on 5 speech parameters:…”

Section: Noise Robustness Of the Sgr Estimation Algorithm In [16]mentioning

confidence: 99%

Section: Noise Robustness Of the Sgr Estimation Algorithm In [16]mentioning

confidence: 99%

See 3 more Smart Citations