Epoch Extraction Based on Integrated Linear Prediction Residual Using Plosion Index

Prathosh, A P; Ananthapadmanabha, T.; Ramakrishnan, A. G.

doi:10.1109/tasl.2013.2273717

Cited by 106 publications

(56 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The DPI algorithm used here for epoch extraction is shown to place the epochs accurately at instants of significant excitation for voiced phones and at random locations for unvoiced phones. 15 The DPI algorithm has been shown to be temporally very accurate up to 0.25 ms of the true epochs. 15 However since the value of the WIP depends largely on the temporal alignment of the vectors, the error made by the epoch extraction algorithm may affect the value of WIP even when the vectors are "similar."…”

Section: Maximum Weighted Inner-product (Mwip)mentioning

confidence: 97%

Estimation of voice-onset time in continuous speech using temporal measures

Prathosh

Ramakrishnan

Ananthapadmanabha³

2014

The Journal of the Acoustical Society of America

Self Cite

View full text Add to dashboard Cite

This paper proposes an automatic acoustic-phonetic method for estimating voice-onset time of stops. This method requires neither transcription of the utterance nor training of a classifier. It makes use of the plosion index for the automatic detection of burst onsets of stops. Having detected the burst onset, the onset of the voicing following the burst is detected using the epochal information and a temporal measure named the maximum weighted inner product. For validation, several experiments are carried out on the entire TIMIT database and two of the CMU Arctic corpora. The performance of the proposed method compares well with three state-of-the-art techniques.

show abstract

Section: Maximum Weighted Inner-product (Mwip)mentioning

confidence: 97%

Estimation of voice-onset time in continuous speech using temporal measures

Prathosh

Ramakrishnan

Ananthapadmanabha³

2014

The Journal of the Acoustical Society of America

Self Cite

View full text Add to dashboard Cite

show abstract

“…the ground truth) after adjusting larynx-to-microphone delay of 0.7 ms for CMU DB [4]. Algorithms were evaluated in the voiced regions with voicedunvoiced decision made by applying threshold of 1/9 on maximum negative value of DEGG [12]. MOCHA speech and DEGG files were already synchronized and voicing decision was made by applying threshold of 1/6 on maximum positive value of DEGG after passing through 15-point moving average (MA) filter.…”

Section: A Experimental Setupmentioning

confidence: 99%

“…All utterances were resampled at 32 kHz. Table 2 compares the performance of the proposed GCI estimation method on clean speech with three state-of-the art methods, DPI [12], SEDREAMS [10], ZFR [4] and our recently proposed FBA [11]. The evaluation was carried on 7 speakers In addition, performance of the proposed algorithm was studied on the degraded speech signals, for its robustness against noise, at various Signal-to-Noise Ratio (SNR) levels.…”

Section: A Experimental Setupmentioning

confidence: 99%

“…for few cases. This is because these methods do not refine the estimated epoch locations using LPR or voice source [12]. The combined effect of MR and FA reflects on the IDR, both being the least, give the higher IDR.…”

Section: B Performance Analysismentioning

confidence: 99%

“…However, the performance of ZFR and SEDREMS depend on accuracy of average pitch period estimation, which might fail in severely degraded noisy conditions. Therefore, estimation of epochs is a challenging task if average pitch period is unknown and hence, study reported in [12] proposes dynamic plosion index (DPI)-based epoch extraction algorithm. Even though it is threshold-independent, its performance might be affected by the erroneous estimation of the integrated linear prediction residual (ILPR) [13].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A novel filterbank for epoch estimation

Bachhav

Fatil

2017

2017 25th European Signal Processing Conference (EUSIPCO)

View full text Add to dashboard Cite

Abstract-We present a novel approach for epoch estimation from the simple observation of the speech spectrum. Fundamental frequency (F 0 ) of the speech signal and local variations around F 0 are the characteristics of glottal excitation source. Extraction of this information from the speech spectrum can be used to estimate epochs (since higher harmonics interact with the vocal tract characteristics, they no longer represent the true glottal source). In this paper, we bandpass filter the speech signal through a novel Gaussian filterbank followed by simple peak detection to extract epochs. We do not attempt any post processing to study the effectiveness of F 0 on epoch estimation in the proposed method. The algorithm is validated on various databases and compared with four state-of-the-art methods. The method has shown better or comparable results on the clean speech and found to be highly robust to the additive white noise giving highest IDR at various SNR levels.

show abstract

Analysis of Speech Source Signals for Detection of Out-of-breath Condition

Sahoo

Dandapat

2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Epoch Extraction Based on Integrated Linear Prediction Residual Using Plosion Index

Cited by 106 publications

References 25 publications

Estimation of voice-onset time in continuous speech using temporal measures

Estimation of voice-onset time in continuous speech using temporal measures

A novel filterbank for epoch estimation

Analysis of Speech Source Signals for Detection of Out-of-breath Condition

Contact Info

Product

Resources

About