An FPGA Based VQ for Speaker Identification

Speaker identification is a challenging pattern classification task. It is used enormously in many applications such as security systems, information retrieved services, etc. portable identification systems are expected to be widely used in future in many purposes, such as mobile applications. Implementing the identification technique using a dedicated hardware could be very useful to achieve smart units. In this context, the Field Programmable Gate Array (FPGA) offer an efficient technology to realize a pattern classification strategy. A speaker identification system can be implemented using many classification approaches, one of these, the vector quantization technique (VQ), which is considered one of the most powerful classification techniques. In this paper a vector quantization is implemented in an FPGA. We have reached almost 100% identification rate in 18.8 μs using only 22% of the slices inside the spartan 3 chip.