Hearing device and method of operating a hearing device
A hearing device includes a receiving unit for receiving speech information and transforming it into a speech signal, a signal processing unit for signal-processing of the speech signal and generating an output signal, and an output unit for outputting an output signal to a hearing device user. A method of operating the hearing device includes transforming speech information into a speech signal. The speech signal is processed into an output signal by the signal processing unit for output to the hearing device user. At least one emotion-correlated feature is determined from each of the speech signal and the output signal. The emotion-correlated features determined from the speech signal and the output signal are compared to one another. A comparison result is determined, and the signal processing unit is set as a function of the comparison result. A hearing device is also provided.
1 . A method of operating a hearing device, the method comprising:
receiving speech information from a user and transforming the speech information into a speech signal;
processing the speech signal, by a signal processing unit, and generating an output signal;
determining at least two respective Geneva Minimalistic Acoustic Parameter Set (GeMAPS) parameters from each of the speech signal and the output signal;
extracting feature vectors of the speech signal and the output signal, each feature vector including the at least two respective GeMAPS parameters as vector entries;
determining a length of the feature vector of the speech signal and a length of the feature vector of the output signal;
comparing the length of the feature vector of the speech signal to the length of the feature vector of the output signal; and
changing parameters of the signal processing unit using a control signal generated as a function of the comparison result if the length of the feature vector of the output signal is less than or equal to the length of the feature vector of the speech signal.
2 . The method according to claim 1 , which further comprises comparing the comparison result to a stored threshold, and setting parameters of the signal processing unit as a function of the comparison of the comparison result to the stored threshold.
3 . The method according to claim 1 , which further comprises:
determining a deviation between the GeMAPS parameters of the speech signal and the the GeMAPS parameters of the output signal as the comparison result; and
setting parameters of the signal processing unit to minimize the deviation.
4 . The method according to claim 1 , which further comprises setting parameters of the signal processing unit to amplify at least one of the at least two respective GeMAPS parameters in the output signal.
5 . The method according to claim 1 , which further comprises using a square of a Euclidean norm as the comparison result.
6 . A hearing device, comprising:
a receiving unit for receiving speech information and transforming the speech information into a speech signal;
a signal processing unit for processing the speech signal and generating an output signal;
a feature extractor for extracting feature vectors from each of the speech signal and the output signal, each feature vector including as vector entries at least two GeMAPS parameters determined from the respective speech signal or output signal;
a comparing unit for comparing a length of the feature vector of the speech signal and a length of the feature vector of the output signal to determine a comparison result;
an output unit for outputting an output signal to the hearing device; and
a controller configured to carry out the method according to claim 1 .
7 . A method of operating a hearing device, the method comprising:
receiving speech information from a user and transforming the speech information into a speech signal;
processing the speech signal, by a signal processing unit, and generating an output signal;
determining at least two respective Geneva Minimalistic Acoustic Parameter Set (GeMAPS) parameters from each of the speech signal and the output signal;
extracting feature vectors of the speech signal and the output signal, each feature vector including the at least two respective GeMAPS parameters as vector entries;
determining a deviation between the feature vector of the speech signal and the feature vector of the output signal;
comparing the deviation to a stored threshold value; and
changing parameters of the signal processing unit using a control signal generated as a function of the comparison result if the deviation exceeds the stored threshold value.
8 . A hearing device, comprising:
a receiving unit for receiving speech information and transforming the speech information into a speech signal;
a signal processing unit for signal-processing the speech signal and generating an output signal;
a feature extractor for extracting feature vectors from each of the speech signal and the output signal, each feature vector including as vector entries at least two GeMAPS parameters determined from the respective speech signal or output signal;
a comparing unit for comparing the feature vectors extracted from the speech signal and the output signal to determine a deviation between the feature vector of the speech signal and the feature vector of the output signal;
an output unit for outputting an output signal to the hearing device; and
a controller configured to carry out the method according to claim 7 .