LSTM-Based Pitch Range Estimation from Spectral Information of Brief Speech Input

Wei, Zhang; Zhang, Qi; Xie, Yanlu; Zhang, Jinsong

doi:10.1109/iscslp.2018.8706608

Cited by 4 publications

(15 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The purpose of using LSTM model to estimate pitch range is twofold as described in Ref. 5. First, the characteristic of recurrent neural networks (RNNs) is very similar to the human pitch-range perception, which is known as an online adaptive process with the feedback process.…”

Section: Lstm Modelmentioning

confidence: 99%

“…Inspired by these findings, some studies have proposed to estimate pitch range from spectral information with deep learning model recently. 5,6 For example, Zhang et al 6 have utilized multi-task learning deep neural networks with multi-feature input to estimate pitch-range targets. Different from Ref.…”

Section: Introductionmentioning

confidence: 99%

“…Different from Ref. 6, Zhang et al 5 proposed to deploy LSTM model with only one feature as input, whose experimental results showed that they could still achieve a reliable pitch-level estimation result with low (<2.5%) mean absolute percentage error (MAPE) rate when the speech segments are as brief as 300 ms (about 1-1.5 syllables). Both studies have demonstrated that one can estimate pitch range directly from the spectral structure by means of deep learning methods.…”

Section: Introductionmentioning

confidence: 99%

“…In this paper, we evaluated the method used in Ref. 5 in some more challenging circumstances. We took three different scenarios which may have an influence on this method into account.…”

Section: Introductionmentioning

confidence: 99%

“…In Ref. 5, the number of speakers for training is only more than 100. In view of the linguistic, the variation of training data will increase with a largerscale data due to the speaker-dependent nature of pitch range.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A Study on the Robustness of Pitch-Range Estimation from Brief Speech Segments

Peng

Wei

et al. 2020

Int. J. As. Lang. Proc.

Self Cite

View full text Add to dashboard Cite

Pitch-range estimation from brief speech segments could bring benefits to many tasks like automatic speech recognition and speaker recognition. To estimate pitch range, previous studies have proposed to utilize deep-learning-based models with spectrum information as input. They demonstrated that such method works and could still achieve reliable estimation results when the speech segment is as brief as 300 ms. In this study, we evaluated the robustness of this method. We take the following scenarios into account: (1) a large number of training speakers; (2) different language backgrounds; and (3) monosyllabic utterances with different tones. Experimental results showed that: (1) The use of a large number of training speakers improved the estimation accuracies. (2) The mean absolute percentage error (MAPE) rate evaluated on the L2 speakers is similar to that on the native speakers. (3) Different tonal information will affect the LSTM-based model, but this influence is limited compared to the baseline method which calculates pitch-range targets from the distribution of [Formula: see text]0 values. These experimental results verified the efficiency of the LSTM-based pitch-range estimation method.

show abstract

Section: Lstm Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…In this paper, we evaluated the method used in Ref. 5 in some more challenging circumstances. We took three different scenarios which may have an influence on this method into account.…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations