Automated method of classifying and suppressing noise in hearing devices
The claimed invention is directed to a real-time noise classification and tuning system for cochlear implant and other hearing device applications. The system is capable of automatically selecting the optimized parameters of a noise suppression algorithm in response to different noisy environments. The feature vector and the classifier deployed in the system to automatically identify the background noise environment are selected so that the computation burden is kept low to achieve a real-time throughput. The results reported herein indicate improvement in speech enhancement when using this intelligent real-time hearing device system.
1. An audio device system comprising an audio device and a control device,
the control device comprising: a signal interface that is adapted to receive data representing the acoustic environment external to the ear, and transmit parameters of a noise suppression algorithm to the audio device; and a module for analyzing the data representing the acoustic environment external to the ear, and calculating the noise suppression algorithm for digital signal processing, the control device being operable to be responsive to the acoustic environment data transmitted thereto to automatically select optimized parameters of the noise suppression algorithm based upon the data and to transmit the algorithm parameters to the audio device, wherein instructions executed by the control device, and which enable the control device to perform the audiometric process in cooperation with the audio device, are stored within the control device;
wherein the audio device is adapted to receive the algorithm parameters transmitted thereto by the control device and to perform speech enhancement automatically in real time using the received algorithm parameters without user intervention, and wherein the audio device is a cochlear implant.
2. The audio device system according to claim 1 further comprising a computer in communication with the control device for at least one of signal analysis, algorithm processing, and audiometric examination.
3. The audio device system in accordance with claim 1 , wherein the system is implemented on a smartphone platform.
4. The audio device system of claim 1 further comprising a feature vector and a classifier.
5. A method of operating an audio device, the method comprising: providing an audio device and a control device, the control device comprising a signal interface that is adapted to receive data representing the acoustic environment external to the ear, and transmit parameters of a noise suppression algorithm to the audio device, and wherein the audio device is a cochlear implant; and a module for analyzing the data representing the acoustic environment external to the ear, and calculating the noise suppression algorithm for digital signal processing, the control device being operable to be responsive to the acoustic environment data transmitted thereto to automatically derive the noise suppression algorithm parameters based upon the data and to transmit the noise suppression algorithm parameters to the audio device; wherein the audio device is adapted to receive the noise suppression algorithm parameters transmitted thereto by the control device and to perform speech enhancement in real time using the received noise suppression algorithm, wherein instructions executed by the control device, and which enable the control device to perform the audiometric process in cooperation with the audio device, are stored within the control device; the method further comprising the steps of:
adjusting the audio device in an audiometric process to adapt the audio device to the hearing loss of the user;
deriving data representing the acoustic environment external to the ear;
transmitting the data representing the acoustic environment external to the ear to the control device;
analyzing the data representing the acoustic environment external to the ear and automatically selecting optimized parameters of the noise suppression algorithm for performing speech enhancement automatically in real time;
transmitting the noise suppression algorithm parameters to the audio device; and
performing speech enhancement using the received noise suppression algorithm parameters without user intervention.
6. The method according to claim 5 and further comprising providing a computer in communication with the control device for at least one of signal analysis, algorithm processing, and audiometric examination.