This paper proposed a correlation based method
using the auto-correlation function . The
auto-correlation function is a popular measurement
in estimating pitch in time domain. The performance of this method, however, is effected due to the position of dominant
harmonics (usually called as the first formant) and the presence of
spurious peaks introduced in noisy conditions.
The aim is to detect the pitch information of noiseless and noisy speech. The experimental results of computer simulations on male and female voices in white noise perform that the gross pitch errors are lower in proposed method as compared to other related method in different types of signal to noise ratio conditions.
To evaluate the proposed method, natural speech signals spoken by two Japanese female and male speakers are examined. Speech signals are taken from a particular database . The reference file is constructed by computing the pitch frequency every 10 ms using a semi automatic technique based on visual inspection. White Gaussian noise is added to these speech signals before the simulations. Pitch estimation error is calculated as the difference between the reference and estimated pitch frequency. If the estimated pitch for a frame deviates from the reference by > 20%, it is recognized as a gross pitch error (GPE) . Otherwise, a fine pitch error (FPE). For the GPE, proportion of the error was calculated. The possible sources of GPE are pitch doubling, halving and inadequate suppression of formants to affect the estimation. In summary, the proposed method can estimate stable pitch with high accuracy not only in a clean speech but also in heavy noisy conditions.
The aim is to detect the pitch information of noiseless and noisy speech. The experimental results of computer simulations on male and female voices in white noise perform that the gross pitch errors are lower in proposed method as compared to other related method in different types of signal to noise ratio conditions.
To evaluate the proposed method, natural speech signals spoken by two Japanese female and male speakers are examined. Speech signals are taken from a particular database . The reference file is constructed by computing the pitch frequency every 10 ms using a semi automatic technique based on visual inspection. White Gaussian noise is added to these speech signals before the simulations. Pitch estimation error is calculated as the difference between the reference and estimated pitch frequency. If the estimated pitch for a frame deviates from the reference by > 20%, it is recognized as a gross pitch error (GPE) . Otherwise, a fine pitch error (FPE). For the GPE, proportion of the error was calculated. The possible sources of GPE are pitch doubling, halving and inadequate suppression of formants to affect the estimation. In summary, the proposed method can estimate stable pitch with high accuracy not only in a clean speech but also in heavy noisy conditions.
Correlation has applications in radar,speech recognition etc
ReplyDeleteNicely explained with an example
ReplyDeleteThanks!!!
Deletegood application of correlation.
ReplyDeleteCan be used to recognise same words from different people.
ReplyDeleteYes,this is possible because their fundamental frequency (or Pitch) will be different.
DeleteAs correlation is used to find degree of similarity between two signal .So it can be used to find similarity between error free signal and a single with error . It's good that you are using it for pitch extraction.Good application.
ReplyDeleteWith such a method we can use this for word recognition
ReplyDeleteYes off course.
DeleteIt seems that efficiency of the system is very good as it is able to estimate stable pitch in heavy noisy condition
ReplyDeleteExtraction of pitch gives this system edge over other techniques
ReplyDeleteActually there are many pitch extraction techniques but the proposed technique is a unique one since it uses a criteria (as mentioned)for estimating the pitch.
DeleteNicely explained
ReplyDeleteCorrelation can be used for noise removal as well
ReplyDeleteWhite Gaussian noise is used for noise analysis of the signal
ReplyDeleteYes it has wide range of applications in communication and signal processing systems.
Delete