Loading...
Please wait, while we are loading the content...
Similar Documents
Voice Interaction Method and Apparatus
| Content Provider | The Lens |
|---|---|
| Abstract | Disclosed is a voice interaction method and apparatus. In the above method, a first voice control instruction is acquired, and a first operation corresponding to the first voice control instruction is executed (S102); mixed audio data are gathered, where the mixed audio data includes: audio data played when the first operation is executed and a second voice control instruction (S104); the played audio data are filtered out from the mixed audio data, and the second voice control instruction is identified (S106); and it is switched from the first operation to a second operation corresponding to the second voice control instruction according to the second voice control instruction (S108). |
| Related Links | https://www.lens.org/lens/patent/011-794-804-560-983/frontpage |
| Language | English |
| Publisher Date | 2017-04-05 |
| Access Restriction | Open |
| Alternative Title | Sprachinteraktionsverfahren Und Vorrichtung Procédé Et Appareil D'interaction Vocale |
| Content Type | Text |
| Resource Type | Patent |
| Date Applied | 2014-07-01 |
| Agent | Winter, Brandl, Fürniss, Hübner, Röss, Kaiser, Polte - Partnerschaft Mbb |
| Applicant | Zte Corp |
| Application No. | 14893326 |
| Claim | A voice interaction method, comprising: acquiring a first voice control instruction, and executing a first operation corresponding to the first voice control instruction; gathering mixed audio data, comprising: audio data played when the first operation is executed and a second voice control instruction; filtering out the played audio data from the mixed audio data, and identifying the second voice control instruction; and switching from the first operation to a second operation corresponding to the second voice control instruction according to the second voice control instruction. The method according to claim 1, wherein, the acquiring the first voice control instruction and executing the first operation comprises: receiving the first voice control instruction, and performing an analog-digital conversion process to the first voice control instruction; and identifying data subjected to the analog-digital conversion process, and executing the first operation according to an identification result. The method according to claim 1, before filtering out the played audio data from the mixed audio data, further comprising: backing up the played audio data, wherein backup data are used for identifying the second voice control instruction from the mixed audio data. The method according to claim 3, wherein, the identifying the second voice control instruction from the mixed audio data, comprises: performing an analog-digital conversion process to the mixed audio data; comparing data subjected to the analog-digital conversion process with the backup data, and filtering out the backup data from the data subjected to the analog-digital conversion process; and identifying the second voice control instruction based on a remaining part of data after filtering out the backup data. The method according to claim 1, after switching to the second operation according to the second voice control instruction, further comprising: monitoring an execution process of the second operation, to determine completion of the second operation; judging whether the second operation is to terminate execution of the first operation; and continuing to execute the first operation from a switching time corresponding to switching to the second operation if the second operation is not to terminate the execution of the first operation. A voice interaction apparatus, comprising: a first execution module, configured to acquire a first voice control instruction, and execute a first operation corresponding to the first voice control instruction; a gathering module, configured to gather mixed audio data, comprising: audio data played when the first operation is executed and a second voice control instruction; an identification module, configured to filter out the played audio data from the mixed audio data, and identify the second voice control instruction; and a switching module, configured to switch from the first operation to a second operation corresponding to the second voice control instruction according to the second voice control instruction. The apparatus according to claim 6, wherein, the first execution module comprises: a first processing unit, configured to receive the first voice control instruction, and perform an analog-digital conversion process to the first voice control instruction; and an execution unit, configured to identify data subjected to the analog-digital conversion process, and execute the first operation according to an identification result. The apparatus according to claim 6, further comprising: a backup module, configured to back up the played audio data, wherein backup data are used for identifying the second voice control instruction from the mixed audio data. The apparatus according to claim 8, wherein, the identification module comprises: a second processing unit, configured to perform an analog-digital conversion process to the mixed audio data; a third processing unit, configured to compare data subjected to the analog-digital conversion process with the backup data, and filter out the backup data from the data subjected to the analog-digital conversion process; and an identification unit, configured to identify the second voice control instruction based on a remaining part of data after filtering out the backup data. The apparatus according to claim 6, further comprising: a monitoring module, configured to monitor an execution process of the second operation, to determine completion of the second operation; a judgment module, configured to judge whether the second operation is to terminate execution of the first operation; and a second execution module, configured to continue to execute the first operation from a switching time corresponding to switching to the second operation when an output of the judgment module is that the second operation is not to terminate the execution of the first operation. |
| CPC Classification | SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS;SPEECH RECOGNITION;SPEECH OR VOICE PROCESSING TECHNIQUES;SPEECH OR AUDIO CODING OR DECODING ELECTRIC DIGITAL DATA PROCESSING |
| Extended Family | 198-150-435-558-383 011-794-804-560-983 170-044-600-017-279 182-267-934-814-116 014-677-058-442-673 |
| Patent ID | 3151087 |
| Inventor/Author | He Zhibin Jiang Zhifeng |
| IPC | G06F3/01 G10L15/26 |
| Status | Discontinued |
| Simple Family | 014-677-058-442-673 011-794-804-560-983 170-044-600-017-279 182-267-934-814-116 198-150-435-558-383 |
| CPC (with Group) | G10L15/222 G06F3/167 G10L21/0208 G10L25/84 G10L2015/223 G10L2021/02087 |
| Issuing Authority | United States Patent and Trademark Office (USPTO) |
| Kind | Patent Application Publication |
