# US 2018/0322873 A1 · Speech processing method and speech processing device

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2018/0322873 A1
- Document ID: US20180322873A1
- Status: Published application
- Kind: A1
- Application number: 15/971,347
- Filed: 2018-05-04
- Published: 2018-11-08
- Earliest claimed: 2017-05-08
- Assignees: Smartisan Digital Co., Ltd.
- Applicants: Smartisan Digital Co., Ltd.
- Inventors: Yonghao Luo; Xiaomu Zhu; He Huang
- Web page: https://patentgrep.com/patent/US20180322873A1

## CPC

- G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue
- G06F 3/04817: using icons (graphical or visual programming using iconic symbols G06F8/34)
- G06F 3/0482: Interaction with lists of selectable items, e.g. menus
- G06F 3/167: {Audio in a user interface, e.g. using voice commands for navigating, audio feedback}
- G06F 16/3344: {using natural language analysis}
- G06F 16/338: Presentation of query results
- G10L 15/26: Speech to text systems (G10L15/08 takes precedence)
- G10L 2015/223: {Execution procedure of a spoken command}
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A speech processing method and a speech processing device are provided. The method includes: collecting, in a case where it is detected that an operation on a designated key provided in the terminal meets a preset condition, a speech signal in an audio collecting region of the terminal, where the designated key is capable of being invoked at any interface of the terminal; converting the collected speech signal into a text; and displaying a text operating box on the display interface, and displaying the text in a text displaying region of the text operating box.

## Claims

### Claim 1

A speech processing method for a terminal having a display interface, the speech processing method comprising:
collecting, in a case where it is detected that an operation on a designated key provided in the terminal meets a preset condition, a speech signal in an audio collecting region of the terminal, wherein the designated key is capable of being invoked at any interface of the terminal;
converting the collected speech signal into a text; and
displaying a text operating box on the display interface, and displaying the text in a text displaying region of the text operating box.

### Claim 2 (depends on 1)

The speech processing method according to claim 1, wherein
before displaying the text operating box on the display interface, the method further comprises:
searching for content related to the text, and
while displaying the text operating box on the display interface and displaying the text in the text displaying region of the text operating box, the method further comprises:
displaying a search result for the text on the display interface.

### Claim 3 (depends on 2)

The speech processing method according to claim 2, wherein the searching for content related to the text comprises:
invoking at least one designated application in the terminal to search for the content related to the text.

### Claim 4 (depends on 3)

The speech processing method according to claim 3, wherein the invoking at least one designated application to search for the content related to the text comprises one or more of:
invoking a search engine in the terminal to search for the content related to the text; and
invoking a contact list application in the terminal to search a contact list for the content related to the text.

### Claim 5 (depends on 2)

The speech processing method according to claim 2, wherein
the searching for content related to the text comprises:
searching applications installed in the terminal for a target application with an application name matching with the text, and
the displaying a search result for the text on the display interface comprises:
displaying, in a case where the target application is found, an icon of the target application in the display interface.

### Claim 6 (depends on 5)

The speech processing method according to claim 5, wherein after displaying the icon of the target application in the display interface, the method further comprises:
activating the target application in a case where it is detected that the icon of the target application displayed in the display interface is clicked.

### Claim 7 (depends on 1)

The speech processing method according to claim 1, wherein
a sharing operation option for triggering sharing of the text is further displayed in the text operating box,
after displaying the text in the text displaying region of the text operating box, the method further comprises:
displaying a sharable list in a case where a triggering operation on the sharing operation option is detected, wherein the sharable list comprises a plurality of sharing manner options; and
determining, in a case where a selecting operation on an sharing manner option in the sharable list is detected, a target sharing manner selected by the selecting operation, and transmitting a sharing instruction containing the text to a target application associated with the target sharing manner, wherein the sharing instruction is configured to instruct the target application to paste, based on the target sharing manner, the text into a region designated by the target sharing manner.

### Claim 8 (depends on 1)

The speech processing method according to claim 1, wherein after displaying the text in the text displaying region of the text operating box, the method further comprises:
displaying, in a case where an operation instruction for activating a text editing application for editing a text is detected, a text editing interface of the text editing application, wherein the text editing interface comprises at least one text editing region; and
determining, in a case where a designated drag operation on the text operating box is detected, a target text editing region where an ending point of the designated drag operation is located from the at least one text editing region of the text editing interface, and copying the text in the text operating box into the target text editing region, wherein the designated drag operation is used to drag the text operating box or the text in the text operating box to the text editing region.

### Claim 9 (depends on 1)

The speech processing method according to claim 1, wherein
a contraction operation option for triggering contraction of the text operating box is further displayed in the text operating box, and
after displaying the text in the text displaying region of the text operating box, the method further comprises:
hiding the text operating box in a case where a trigger operation on the contraction operation option is detected; and
displaying, in a case where a trigger operation on an expanding operation option for triggering display of the text operating box is detected when the text operating box is in a hidden state, the text operating box in the display interface.

### Claim 10 (depends on 1)

The speech processing method according to claim 1, wherein the displaying the text operating box on the display interface comprises:
displaying the text operating box on a top layer of the display interface.

### Claim 11 (depends on 1)

The speech processing method according to claim 1, wherein the designated key is a designated physical key, before collecting the speech signal in the audio collecting region of the terminal, the method further comprises:
determining a current state of the terminal; wherein
in a case where the terminal is in an operating state, the operation for collecting the speech signal in the audio collecting region of the terminal is performed; and
in a case where the terminal is in a lock screen state or a standby state, the terminal is unlocked or awaked, and the operation for collecting the speech signal in the audio collecting region of the terminal is performed.

### Claim 12

A speech processing device, comprising:
a speech collecting unit configured to collect, in a case where it is detected that an operation on a designated key provided in a terminal meets a preset condition, a speech signal in an audio collecting region of the terminal, wherein the designated key is capable of being invoked at any interface of the terminal;
a text converting unit configured to convert the collected speech signal into a text; and
a text displaying unit configured to display a text operating box on a display interface and display the text in a text displaying region of the text operating box.

### Claim 13 (depends on 12)

The speech processing device according to claim 12, further comprising:
a text searching unit configured to search for content related to the text before the text operating box is displayed on the display interface by the text displaying unit; and
a search result displaying unit configured to display a search result for the text on the display interface while the text operating box is displayed on the display interface by the text displaying unit.

### Claim 14 (depends on 13)

The speech processing device according to claim 13, wherein the text searching unit comprises:
a first text searching unit configured to invoke at least one designated application in the terminal to search for the content related to the text.

### Claim 15 (depends on 13)

The speech processing device according to claim 13, wherein the text searching unit comprises:
a second text searching unit configured to search applications installed in the terminal for a target application with an application name matching with the text, wherein
the search result displaying unit is configured to display, in a case where the target application is found, an icon of the target application in the display interface while the text operating box is displayed on the display interface by the text displaying unit.

### Claim 16 (depends on 12)

The speech processing device according to claim 12, wherein a sharing operation option for triggering sharing of the text is further displayed in the text operating box displayed by the text displaying unit,
the speech processing device further comprises:
a list displaying unit configured to display a sharable list in a case where a triggering operation on the sharing operation option is detected after the text is displayed in the text displaying region of the text operating box by the text displaying unit, wherein the sharable list comprises a plurality of sharing manner options; and
a text sharing unit configured to determine, in a case where a selecting operation on an sharing manner option in the sharable list is detected, a target sharing manner selected by the selecting operation, and transmit a sharing instruction containing the text to a target application associated with the target sharing manner, wherein the sharing instruction is configured to instruct the target application to paste, based on the target sharing manner, the text into a region designated by the target sharing manner.

### Claim 17 (depends on 12)

The speech processing device according to claim 12, further comprising:
an editing interface displaying unit configured to display, in a case where an operation instruction for activating a text editing application for editing a text is detected after the text is displayed in the text displaying region of the text operating box by the text displaying unit, a text editing interface of the text editing application, wherein the text editing interface comprises at least one text editing region; and
a text pasting unit configured to determine, in a case where a designated drag operation on the text operating box is detected, a target text editing region where an ending point of the designated drag operation is located from the at least one text editing region of the text editing interface, and copy the text in the text operating box into the target text editing region, wherein the designated drag operation is used to drag the text operating box or the text in the text operating box to the text editing region.

### Claim 18 (depends on 12)

The speech processing device according to claim 12, wherein
a contraction operation option for triggering contraction of the text operating box is further displayed in the text operating box, and
the speech processing device further comprises:
a text hiding unit configured to hide the text operating box in a case where a trigger operation on the contraction operation option is detected after the text is displayed in the text displaying region of the text operating box by the text displaying unit; and
a text restoring unit configured to display the text operating box in the display interface in a case where a trigger operation on an expanding operation option for triggering display of the text operating box is detected when the text operating box is in a hidden state.

### Claim 19 (depends on 12)

The speech processing device according to claim 12, wherein the text displaying unit is configured to display the text operating box on a top layer of the display interface.

### Claim 20 (depends on 12)

The speech processing device according to claim 12, wherein
the designated key is a designated physical key, and
the speech processing device further comprises a state determining unit configured to determine a current state of the terminal before the speech signal in the audio collecting region of the terminal is collected by the speech collecting unit, wherein
in a case where the terminal is in an operating state, the operation for collecting the speech signal in the audio collecting region of the terminal is performed, and
in a case where the terminal is in a lock screen state or a standby state, the terminal is unlocked or awaked, and the operation for collecting the speech signal in the audio collecting region of the terminal is performed.
