Abstract
In this paper, the turning point algorithm has applied on the input speech signal from International Phonetic Alphabet database in the form of vowels, consonants and narratives of American-English. From this algorithm, the input speech signal is compressed by reducing the sampling rate by half of the input sampling rate. After that, the compressed speech signal is played back. The compressed speech signal now has far much better hearing quality as compared to the hearing quality of the input speech signal. This observation is true for all the categories of the input speech signals taken into consideration judged on the basis of both MOS and Average MOS. Finally, the compression performance is also computed for all the category of the speech signals.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have