Speech Signal Processing / Speech Recognition / Speaker Verification

We study speaker verification and speech recognition systems and their applications to the real world. Recently, we can easily utilize some spoken dialog systems which are on robots, smart phones and smart speakers. These spoken dialogue systems consist of some core technologies, such as noise reduction, voice activity detection, speech enhancement, speech recognition, speaker recognition, language understanding, speech synthesize. Particularly, our laboratory focuses on speaker verification, voce liveness detection and speech recognition technologies. We are using speech signal processing and machine leaning technologies for improving their performance and robustness.

• Laboratory website