Qian-Jie Fu

Research Professor
Department of Biomedical Engineering
Viterbi School of Engineering
University of Southern California

Scientist III and Laboratory Head
Speech Processing and Auditory Perception Lab
Communication & Auditory Neuroscience Division
House Ear Institute

Research Topics

1. To understand the mechanisms involved in speech pattern recognition by the electrically stimulated auditory system, and further, the plasticity of the auditory cortex.
2. To develop assessment and training strategies that maximize speech recognition in adults and children fitted with a cochlear implant or a hearing aid.
3. To provide innovative speech software to people with hearing problems based on the state-of-art speech technology and recent research findings in cochlear implants, hearing aid, speech and hearing science, language development, and auditory plasticity. Please visit TigerSpeech Technology for more information.

Research Overview

Project 1: Effects of Training on Adult Cochlear Implant Users (Supported by NIDCD-R01-DC004792)
For most cochlear implant (CI) patients, the greatest gains in speech understanding occur within the first three months of implant use, after which performance typically levels off. However, our recent research shows that targeted auditory training can greatly improve CI patients' speech recognition in quiet, even for patients with years of CI experience. Many challenges remain in developing auditory training tools for CI patients. Can auditory training improve performance for more difficult tasks (e.g., speech in noise, music appreciation, telephone use, etc)? How might individual patients differ in terms of the benefits of auditory training? What are the most effective training approaches and materials? How well do laboratory results translate into "real-world" benefits? Our long-term goals are to develop efficient and effective training protocols and materials to maximize CI patient performance in real-world listening conditions. We hypothesize that targeted contrast training can greatly improve CI patients' performance for a variety of listening conditions, and that individualized training protocols and materials may be necessary to maximize training outcomes. We further hypothesize that passive learning may not allow CI patients to receive the full benefit of advanced coding strategies, and that targeted auditory training may help patients access the additional cues provided by novel processing schemes. We expect that these training approaches, if successful in real-world simulations, will generalize to improved performance outside the lab. As recent advances in implant technology seem to be reaching a point of diminishing returns, auditory training may provide the most cost-effective approach for CI patients to maximize the benefit of the implant device.


Project 2: Audio Processing in Cochlear Implants (Supported by NIDCD R01-DC004993)
The long-term goal of this research is to improve cochlear implant patient performance by maximizing both the transmission and reception of acoustic patterns. We hypothesize that, due to the loss of fine spectral details, cochlear implant patients have great difficulty understanding speech in challenging listening conditions (e.g., background noise, competing speech, reverberation, etc.) and appreciating music. We propose to optimize the input acoustic signal in response to the acoustic environment, or to different speaker characteristics, thereby improving the transmission of acoustic patterns. We further hypothesize that poor patient performance may be partly due to sub-optimal settings of important processor parameters (e.g., stimulation mode, frequency allocation, stimulation rate, etc.). We propose to optimize these parameters according to individual patients' psychophysical capabilities, thereby improving the reception of acoustic patterns. Combining these two approaches - pre-processing the acoustic input signal and optimizing processor parameters - will maximize both the transmission and reception of acoustic patterns, and thus provide the greatest benefit to patient performance for a variety of listening conditions.