Kişiye bağımlı ses kodlaması

With the rapid expansion of Internet, it became feasible to have low-cost andsecure telephone calls via internet. New digital speech compression standardswere developed. Digital speech codecs can be used both in regular telephonenetworks and Internet based systems. Thereby, for a secure call, speech data arefirstly compressed by digital speech codecs, and then, these compressedpackages are sent in an encoded way through Data Encryption Standard(3DES) [1], Advanced Encryption Standard (AES) [2] encoding methods.Compressing and encoding processes require high processor performance andthey may even require the use of high frequency processors and DSP?s toencode the binary speech data. Current speech coders are speaker independent,i.e., they don?t perform any speaker specific operations. They do not evendistinguish between male and female speakers. An interesting way to solve thisproblem is to send speech after encoding it with a system that is based on aspecific user. This system, which can be also called as speaker dependent speechencoding, provides a computationally efficient and relatively secure VoIP call,with high quality and without any encoding compared to the same bit ratestandard speech codecs. Despite the disadvantages of requirement of acquiringall the speech characteristics of users and the need for extra data space, it hasadvantages such as providing secure communication because speechcharacteristics of the speaker is unknown to other users and the synthesizedspeech has higher quality compared to a same bit rate LPC compressed speech.iiiKeywords: SDSC, LPC, CELP, VoIP, codebook, speaker-dependent speechcoding, speech encoding, voice compression.iv