1. A method for using a film formation apparatus for a semiconductor process, the method comprising:
setting an idling state where a reaction chamber of the film formation apparatus accommodates no product target substrate therein; and
then, performing a purging process of removing a contaminant present in an inner surface of the reaction chamber by causing radicals to act on the inner surface of the reaction chamber, the radicals being generated by activating a purging process gas containing oxygen and hydrogen as elements.
2. The method according to claim 1, wherein the purging process comprises supplying the purging process gas into the reaction chamber while exhausting gas from inside the reaction chamber, and setting a temperature and a pressure inside the reaction chamber to activate the purging process gas.
3. The method according to claim 1, wherein the purging process comprises activating the purging process gas outside the reaction chamber.
4. The method according to claim 1, wherein the purging process gas is activated by use of one or more media selected from the group consisting of heat, plasma, light, and catalyst.
5. The method according to claim 1, wherein, between said setting the idling state and said performing the purging process, the method further comprises performing a cleaning process of removing a by-product film from the inner surface of the reaction chamber by a cleaning gas different from the purging process gas
6. The method according to claim 5, wherein the cleaning process comprises supplying the cleaning gas into the reaction chamber while exhausting gas from inside the reaction chamber, and setting a temperature and a pressure inside the reaction chamber to activate the cleaning gas.
7. The method according to claim 5, wherein the by-product film contains as a main component a substance selected from the group consisting of silicon nitride, silicon oxide, silicon oxynitride, and poly-crystalline silicon, and the cleaning gas contains halogen gas and hydrogen gas as elements.
8. The method according to claim 7, wherein, before said setting the idling state, the method further comprises performing a film formation process of forming a film of a material selected from the group consisting of silicon nitride, silicon oxide, silicon oxynitride, and poly-crystalline silicon on a target substrate by CVD inside the reaction chamber, and the by-product film contains, as a main component, a substance derived from a film formation gas used in the film formation process.
9. The method according to claim 1, wherein the purging process gas contains oxygen gas and hydrogen gas, and a ratio of a flow rate of the hydrogen gas relative to a combined flow rate of the oxygen gas and the hydrogen gas is set to be 30% to 70%.
10. The method according to claim 9, wherein the ratio of the flow rate of the hydrogen gas relative to the combined flow rate of the oxygen gas and the hydrogen gas is set to be 50% or more.
11. The method according to claim 1, wherein the contaminant contains a metal as an element and the purging process is performed under conditions set to remove the metal of the contaminant.
12. The method according to claim 11, wherein the contaminant contains one or more metals selected from the group consisting of iron, copper, nickel, aluminum, cobalt, sodium, and calcium.
13. The method according to claim 7, wherein the cleaning gas contains fluorine as an element.
14. The method according to claim 13, wherein the contaminant contains fluorine derived from the cleaning gas, and the purging process is performed under conditions set to remove the fluorine of the contaminant.
15. The method according to claim 2, wherein the purging process is arranged to use a temperature of 400\xb0 C. to 1,050\xb0 C. inside the reaction chamber.
16. The method according to claim 2, wherein the purging process is arranged to use a pressure of 13.3 Pa to 931 Pa inside the reaction chamber.
17. The method according to claim 1, wherein the inner surface of the reaction chamber contains as a main component a material selected from the group consisting of quartz and silicon carbide.
18. A film formation apparatus for a semiconductor process, comprising:
a reaction chamber configured to accommodate a target substrate;
an exhaust system configured to exhaust gas from inside the reaction chamber;
a film formation gas supply circuit configured to supply a film formation gas, for forming a film on the target substrate, into the reaction chamber;
a cleaning gas supply circuit configured to supply a cleaning gas, for removing a by-product film derived from the film formation gas from an inner surface of the reaction chamber, into the reaction chamber;
a purging process gas supply circuit configured to supply a purging process gas, for removing a contaminant from the inner surface of the reaction chamber, into the reaction chamber, the purging process gas containing oxygen and hydrogen as elements; and
a control section configured to control an operation of the apparatus,
wherein the control section executes
setting an idling state where the reaction chamber accommodates no product target substrate therein; and
then, performing a purging process of removing a contaminant present in the inner surface of the reaction chamber by causing radicals to act on the inner surface of the reaction chamber, the radicals being generated by activating the purging process gas.
19. The apparatus according to claim 18, wherein, between said setting the idling state and said performing the purging process, the control section executes performing a cleaning process of removing a by-product film from the inner surface of the reaction chamber by the cleaning gas.
20. A computer readable medium containing program instructions for execution on a processor, which, when executed by the processor, cause a film formation apparatus for a semiconductor process to execute
setting an idling state where a reaction chamber of the film formation apparatus accommodates no product target substrate therein; and
then, performing a purging process of removing a contaminant present in an inner surface of the reaction chamber by causing radicals to act on the inner surface of the reaction chamber, the radicals being generated by activating a purging process gas containing oxygen and hydrogen as elements.
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. A method comprising:
receiving, by a computing device, an acoustic input signal at a speech recognizer;
identifying, by the computing device, a user that is speaking based on the acoustic input signal;
recognizing, by the computing device via the speech recognizer, speech uttered by the user in the acoustic input signal;
determining, by the computing device, speaker-specific information previously stored for the user;
determining, by the computing device, a set of potential responses based on the recognized speech and the speaker-specific information for the user;
ranking, by the computing device, the set of potential responses based on one or more criteria and the speaker-specific information;
determining, by the computing device for each response in the set of potential responses, whether the response should be output or should not be output based on the response’s ranking; and
if the response should be output:
selecting, by the computing device from among a plurality of preconfigured output methods, an output method for outputting the response to the user, the selecting being based on the response’s ranking; and
outputting, by the computing device, the response to the user using the selected output method.
2. The method of claim 1 wherein the speech recognizer is configured to recognize the acoustic input signal in an always on mode, and wherein the response is outputted without touching the computing device or speaking a trigger phrase to activate the speech recognizer.
3. The method of claim 1 wherein the response is outputted after a user speaks a trigger phrase to activate the speech recognizer.
4. The method of claim 1 wherein the speech recognizer operates in an always on mode, and wherein the speech recognizer identifies the user upon receiving a trigger phrase.
5. The method of claim 1 wherein the speaker-specific information is associated with previous speech recognition of speech from the user.
6. The method of claim 1 further comprising:
determining a set of classifications based on the speaker-specific information;
classifying portions of the acoustic input signal into different classifications in the set of classifications;
selecting a classification in the set of classifications based on a criterion associated with the classification; and
using the classification to determine the set of potential responses.
7. The method of claim 6 wherein the speaker-specific information is used to modify a classification in the set of classifications based on a preference of the user in the speaker-specific information.
8. The method of claim 7 wherein a set of keywords associated with the speaker-specific information is used in the classification.
9. The method of claim 6 wherein classifying portions of the acoustic input signal is performed in an always on mode, and wherein identifying the user that is speaking is performed after receiving a trigger phrase to activate the speech recognizer.
10. The method of claim 6 wherein classifying portions of the acoustic input signal is not performed until receiving a trigger phrase to activate the speech recognizer.
11. The method of claim 1 further comprising training the speech recognizer to recognize different users’ speech signatures.
12. The method of claim 1 further comprising storing speaker-specific information for the user based on the response for use in determining additional responses.
13. The method of claim 1 wherein determining the set of potential responses comprises:
determining user preferences in the speaker-specific information; and
performing a search using the user preferences and the recognized acoustic input signal.
14. The method of claim 13
wherein the set of potential responses are ranked based on the user preferences.
15. The method of claim 9 further comprising verifying who is speaking after receiving the trigger phrase to determine if the identified user that is speaking is still speaking.
16. The method of claim 15, wherein the verifying is performed periodically.
17. The method of claim 15 wherein a second verification of who is speaking is performed when a higher security is deemed necessary.
18. The method of claim 17 wherein a manual login is not required if the second verification is performed.
19. The method of claim 1 further comprising, if it is determined that no response in the set of potential responses should be output:
refraining from outputting anything to the user.
20. A non-transitory computer readable medium having stored thereon program code executable by a processor, the program code comprising:
code that causes the processor to receive an acoustic input signal at a speech recognizer;
code that causes the processor to identify a user that is speaking based on the acoustic input signal;
code that causes the processor to recognize, via the speech recognizer, speech uttered by the user in the acoustic input signal;
code that causes the processor to determine speaker-specific information previously stored for the user;
code that causes the processor to determine a set of potential responses based on the recognized speech and the speaker-specific information for the user;
code that causes the processor to rank the set of potential responses based on one or more criteria and the speaker-specific information;
code that causes the processor to determine, for each response in the set of potential responses, whether the response should be output or should not be output based on the response’s ranking; and
if the response should be output:
code that causes the processor to select, from among a plurality of preconfigured output methods, an output method for outputting the response to the user, the selecting being based on the response’s ranking; and
code that causes the processor to output the response to the user using the selected output method.
21. A system comprising:
a processor; and
a non-transitory computer readable medium having stored thereon program code that, when executed by the processor, causes the processor to;
receive an acoustic input signal at a speech recognizer;
identify a user that is speaking based on the acoustic input signal;
recognize, via the speech recognizer, speech uttered by the user in the acoustic input signal;
determine speaker-specific information previously stored for the user;
determine a set of potential responses based on the recognized speech and the speaker-specific information for the user;
rank the set of potential responses based on one or more criteria and the speaker-specific information;
determine, for each response in the set of potential responses, whether the response should be output or should not be output based on the response’s ranking; and
if the response should be output:
select, from among a plurality of preconfigured output methods, an output method for outputting the response to the user, the selecting being based on the response’s ranking; and
output the response to the user using the selected output method.