1. A telephone system having a message recording function, comprising:
a main body connected to a telephone line; and
at least one handset placed on a cradle, said at least one handset being connectable to the main body via wireless communication, said at least one handset having an input unit configured to accept an external input therethrough;
wherein the main body includes:
a message receiving system that is connectable to a calling station through the telephone line and capable of receiving a message transmitted from the calling station through the telephone line when in a connected state;
a message storage in which the message received by the message receiving system is stored;
a message reproducing system that retrieves a message stored in the message storage and outputs the message to said at least one handset via the wireless communication;
an off-hook setting system that sets the telephone line to an off-hook state;
a calling system that makes a call to an external device via the telephone line; and
a control system,
wherein said at least one handset includes an instructing system:
the instructing system issuing a first command that instructs the main body to set the telephone line to the off-hook state to the main body via the wireless communication when said at least one handset is picked up from the cradle,
the instructing system issuing a second command that instructs the main body to make a call to the main body via the wireless communication when the input unit accepts therethrough an external input for making the call, and
the instructing system issuing a third command that instructs said message reproducing system to output a message to the main body via the wireless communication when the input unit accepts there through an external input for reproducing the message through the input unit,
wherein the main body receives any one of the first command, the second command and the third command from said at least one handset via the wireless communication while keeping said telephone line in the off-hook state once the telephone line is set in the off-hook state,
wherein the control system controlling the off-hook setting system to set the telephone line to the off-hook state when judging that the main body receives the first command from said at least one handset via the wireless communication,
wherein the control system controlling the calling system to make the call via the telephone line when judging that the main body receives the second command from said at least one handset via the wireless communication, and
wherein the control system controlling the message reproducing system to reproduce the message without being interrupted, with the telephone line kept in the off-hook state to avoid receiving incoming calls, when judging that the main body receives the third command from said at least one handset via the wireless communication.
2. The telephone system according to claim 1, wherein the telephone line is in an on-hook state when said at least one handset is placed on the cradle.
3. The telephone system according to claim 1, wherein said message reproducing system sets the telephone line in the off-hook state when the message stored therein is reproduced.
4. The telephone system according to claim 1, further comprising:
a caller telephone number storage that stores the telephone numbers of caller stations corresponding to the message stored in said message storage, the telephone numbers of caller stations being stored in relationship to the messages corresponding thereto; and
a calling system that makes a call with reference to a telephone number stored in said caller telephone number storage when a message is reproduced and an instruction to make a call to the caller station corresponding to the reproduce message is made.
5. The telephone system according to claim 4, wherein said at least one handset further includes a displaying system configured to display the telephone numbers of caller stations.
6. The telephone system according to claim 5, wherein said at least one handset further includes an operable member, said at least one handset being configured to make a call to a telephone number displayed on said displaying system when said operable member is operated.
7. The telephone system according to claim 1, further comprising:
numeral keys through which numerals are input;
a dial input recognizing system that recognizes an operation of a numeral key as a part of dial number input;
a command input recognizing system that recognizes an operation of a numeral key as a command input; and
an output controlling system that actuates said message reproducing system when a key input is recognized as the command input by said command input recognizing system.
8. The telephone system according to claim 7, wherein said command input recognizing system recognizes a key input as the command input when the key is operated for not less than a predetermined time period.
9. A telephone system having a message recording function, comprising:
a main body connected to a telephone line;
at least one handset placed on a cradle, said at least one handset being connectable to the main body, said at least one handset being connectable to the telephone line through the main body;
a message receiving system that is connectable to a calling station through a telephone line and capable of receiving a message transmitted from the calling station through the telephone line when in a connected state;
a message storage in which the message received by the message receiving system is stored; and
a message reproducing system that retrieves and outputs the message stored in the message storage,
wherein the telephone line is set to an off-hook state when said at least one handset is picked up from the cradle; and
wherein said at least one handset includes:
a first instructing system that instructs said message reproducing system to output the message when the at least one handset is placed on the cradle; and
a second instructing system that instructs said message reproducing system to output the message when the at least one handset is picked up from the cradle
wherein said message reproducing system reproduces the message with the telephone line being in the off-hook state regardless whether the reproduction of the message is instructed by the first instructing system or the second instructing system.
10. The telephone system according to claim 9, wherein the telephone line is in an on-hook state when said at least one handset is placed on the cradle.
11. The telephone system according to claim 9, wherein said at least one handset is connectable to the main body through wireless communication.
12. The telephone system according to claim 9, further comprising:
a caller telephone number storage that stores the telephone numbers of caller stations corresponding to message stored in said message storage, the telephone numbers of caller stations being stored in relationship to the messages corresponding thereto; and
a calling system that makes a call with reference to a telephone number stored in said caller telephone number storage when a message is reproduced and an instruction to make a call to the caller station corresponding to the reproduce message is made.
13. The telephone system according to claim 12, wherein said at least one handset further includes a displaying system configured to display the telephone numbers of caller stations.
14. The telephone system according to claim 13, wherein said at least one handset further includes an operable member, said at least one handset being configured to make a call to a telephone number displayed on said displaying system when said operable member is operated.
15. The telephone system according to claim 9, further comprising:
numeral keys through which numerals are input;
a dial input recognizing system that recognizes an operation of a numeral key as a part of dial number input;
a command input recognizing system that recognizes an operation of a numeral key as a command input; and
an output controlling system that actuates said message reproducing system when a key input is recognized as the command input by said command input recognizing system.
16. The telephone system according to claim 15, wherein said command input recognizing system recognizes a key input as the command input when the key is operated for not less than a predetermined time period.
17. The telephone system according to claim 1, wherein said telephone system is configured to keep said telephone line in the off-hook state once the telephone line is set in the off-hook state and after the at least one handset finishes receiving the message from the message reproducing system.
The claims below are in addition to those above.
All refrences to claim(s) which appear below refer to the numbering after this setence.
1. An emotion recognition method, comprising the steps of:
(b) inputting at least two unknown data to be identified while enabling each unknown data to correspond to a hyperplane whereas there are two emotion category being defined in the hyperplane, and each unknown data being a data selected from an image data and a vocal data;
(c) respectively performing a calculation process upon the at least two unknown data for assigning each with a weight;
(d) comparing the assigned weight of the two unknown data while using the comparison as base for selecting one emotion category out of those emotion categories as an emotion recognition result.
2. The emotion recognition method of claim 1, wherein each emotion categories is an emotion selected from the group consisting of happiness, sadness, surprise, neutral and anger.
3. The emotion recognition method of claim 1, further comprises a step of: (a) establishing a hyperplane, and the step (a) further comprises the steps:
(a1) establishing a plurality of training samples; and
(a2) using a means of support vector machine (SVM) to establish the hyperplanes basing upon the plural training samples.
4. The emotion recognition method of claim 3, wherein the establishing of the plural training samples further comprises the steps of:
(a11) selecting one emotion category out of the two emotion categories;
(a12) acquiring a plurality of feature values according to the selected emotion category so as to form a training sample;
(a13) selecting another emotion category;
(a14) acquiring a plurality of feature values according to the newly selected emotion category so as to form another training sample; and
(a15) repeating steps (a13) to (a14) and thus forming the plural training samples.
5. The emotion recognition method of claim 1, wherein the image data is an image selected from the group consisting of a facial image and a gesture image.
6. The emotion recognition method of claim 1, wherein the image data is comprised of a plurality of feature values, each being defined as the distance between two specific features detected in the image data.
7. The emotion recognition method of claim 1, wherein the vocal data is comprised of a plurality feature values, each being defined as the combination of pitch and energy.
8. The emotion recognition method of claim 3, wherein the calculation process is comprised of the steps of:
basing upon the plural training samples used for establishing the corresponding hyperplane to acquire the standard deviation and the mean distance between the plural training samples and the hyperplane;
respectively calculating feature distances between the hyperplane and the at least two unknown data to be identified; and
obtaining the weights of the at least two unknown data by performing a mathematic operation upon the feature distances, the plural training samples, the mean distance and the standard deviation.
9. The emotion recognition method of claim 8, wherein the mathematic operation further comprises the steps of:
obtaining the differences between the feature distances and the standard deviation; and
normalizing the differences for obtaining the weights.
10. The emotion recognition method of claim 1, wherein the acquiring of weights of step (c) further comprises the steps of:
(c1) basing on the hyperplanes corresponding to the two unknown data to determine whether the two unknown data are capable of being labeled to a same emotion category; and
(c2) respectively performing the calculation process upon the two unknown data for assigning each with a weight while the two unknown data are not of the same emotion category.
11. The emotion recognition method of claim 1, further comprises a step of: (e) performing a learning process with respect to a new unknown data for updating the hyperplanes, and the step (e) further comprises the steps of:
(e1) acquiring a parameter of the hyperplane to be updated; and
(e2) using feature values detected from the unknown data and the parameter to update the hyperplanes through an algorithm of iteration.
12. An emotion recognition method, comprising the steps of:
(a\u2032) providing at least two training samples, each being defined in a specified characteristic space established by performing a transformation process upon each training sample with respect to its original space;
(b\u2032) establishing at least two corresponding hyperplanes in the specified characteristic spaces of the at least two training samples, each hyperplane capable of defining two emotion categories;
(c\u2032) inputting at least two unknown data to be identified in correspondence to the at least two hyperplanes, and transforming each unknown data to its corresponding characteristic space by the use of the transformation process while enabling each unknown data to correspond to one emotion category selected from the two emotion categories of the hyperplane corresponding thereto, and each unknown data being a data selected from an image data and a vocal data;
(d\u2032) respectively performing a calculation process upon the two unknown data for assigning each with a weight; and
(e\u2032) comparing the assigned weight of the two unknown data while using the comparison as base for selecting one emotion category out of those emotion categories as an emotion recognition result.
13. The emotion recognition method of claim 12, further comprises a step of: (f\u2032) performing a learning process with respect to a new unknown data for updating the hyperplanes, and the step (f\u2032) further comprises the steps of:
(f1\u2032) acquiring a parameter of the hyperplane to be updated;
(f2\u2032) transforming the new unknown data into its corresponding characteristic space by the use of the transformation process; and
(f3\u2032) using feature values detected from the unknown data and the parameter to update the hyperplanes through an algorithm of iteration.
14. The emotion recognition method of claim 12, wherein the transformation process is a Gaussian Kernel transformation
15. The emotion recognition method of claim 12, wherein each emotion categories is an emotion selected from the group consisting of happiness, sadness, surprise, neutral and anger.
16. The emotion recognition method of claim 12, wherein the hyperplane is established by the use of a means of support vector machine (SVM) basing upon the plural training samples.
17. The emotion recognition method of claim 12, wherein the image data is an image selected from the group consisting of a facial image and a gesture image.
18. The emotion recognition method of claim 12, wherein the image data is comprised of a plurality of feature values, each being defined as the distance between two specific features detected in the image data.
19. The emotion recognition method of claim 12, wherein the vocal data is comprised of a plurality feature values, each being defined as the combination of pitch and energy.
20. The emotion recognition method of claim 12, wherein the calculation process is comprised of the steps of:
basing upon the training samples used for establishing the corresponding hyperplane to acquire the standard deviation and the mean distance between the plural training samples and the hyperplane;
respectively calculating feature distances between the hyperplane and the at least two unknown data to be identified; and
obtaining the weights of the at least two unknown data by normalizing the feature distances, the plural training samples, the mean distance and the standard deviation.
21. The emotion recognition method of claim 12, wherein the acquiring of weights of step (d\u2032) further comprises the steps of:
(d1\u2032) basing on the hyperplanes corresponding to the two unknown data to determine whether the two unknown data are capable of being labeled to a same emotion category; and
(d2\u2032) respectively performing the calculation process upon the two unknown data for assigning each with a weight while the two unknown data are not of the same emotion category.