Interactive evolutionary computation-based hearing aid fitting

Hideyuki Takagi, Miho Ohsaki

    Research output: Contribution to journalArticlepeer-review

    70 Citations (Scopus)


    An interactive evolutionary computation (EC) fitting method is proposed that applies interactive EC to hearing aid fitting and the method is evaluated using a hearing aid simulator with human subjects. The advantages of the method are that it can optimize a hearing aid based on how a user hears and that it realizes whatever +whenever +wherever (W3) when fitting. Conventional fitting methods are based on the user's partially measured auditory characteristics, the fitting engineer's experience, and the user's linguistic explanation of his or her hearing. These conventional methods, therefore, suffer from the fundamental problem that no one can experience another person's hearing. However, as interactive EC fitting uses EC to optimize a hearing aid based on the user's evaluation of his or her hearing, this problem is addressed. Moreover, whereas conventional fitting methods must use pure tones and bandpass noise for measuring hearing characteristics, our proposed method has no such restrictions. Evaluating the proposed method using speech sources, we demonstrate that it shows significantly better results than either the conventional method or the unprocessed case in terms of both speech intelligibility and speech quality. We also evaluate our method using musical sources, unusable for evaluation by conventional methods, and demonstrate that its sound quality is preferable to the unprocessed case.

    Original languageEnglish
    Pages (from-to)414-427
    Number of pages14
    JournalIEEE Transactions on Evolutionary Computation
    Issue number3
    Publication statusPublished - Jun 2007

    All Science Journal Classification (ASJC) codes

    • Software
    • Theoretical Computer Science
    • Computational Theory and Mathematics


    Dive into the research topics of 'Interactive evolutionary computation-based hearing aid fitting'. Together they form a unique fingerprint.

    Cite this