作者: Pablo Perez Zarazaga , Tom Buackstrom , Stephan Sigg
DOI: 10.23919/EUSIPCO.2019.8903125
关键词:
摘要: Voice user interfaces have increased in popularity, as they enable natural interaction with different applications using one’s voice. To improve their usability and audio quality, several devices could interact to provide a unified voice interface. However, cooperating sharing voice-related information, privacy may be at risk. Therefore, access management rules that preserve are important. State-of-the-art methods for acoustic pairing of fingerprinting based on the time-frequency representation signal error-correction. We propose use such authorise which acoustically close. aim obtain fingerprints ambient adapted requirements interfaces. Our experiments show responsiveness robustness is improved by combining overlapping windows decorrelating transforms.