JP7240271B2 - Karaoke input device - Google Patents

Description

The present invention relates to an input device for karaoke.

2. Description of the Related Art Techniques for inputting commands and search words by voice using a remote controller attached to a karaoke machine to change the tempo and key of a karaoke performance and to search for music are known.

For example, Patent Literature 1 discloses a music search system capable of automatically extracting each search term from a series of audio data containing a plurality of search terms and performing a highly accurate music search.

JP-A-2002-189483

Here, assume that while one user is singing karaoke, another user uses the remote controller to search for music by voice input. In this case, the remote control device may extract the search word from the singing voice of a certain user accompanying karaoke singing, instead of the voice of another user. As a result, the remote control device may erroneously recognize the search word and present a search result different from the user's desired result.

On the other hand, there is a possibility that the lyrics of the song that the user sings in karaoke and the command executed by voice input match. For example, suppose that the user utters the word "stop" which is the lyrics of a certain song. In this case, the remote controller may erroneously recognize the lyrics "stop" as the command "stop karaoke performance" and stop the karaoke performance.

SUMMARY OF THE INVENTION It is an object of the present invention to provide a karaoke input device capable of reducing erroneous recognition when using voice input in karaoke singing.

One invention for achieving the above object is a karaoke input device used when singing karaoke, comprising a plurality of commands corresponding to processes executable when singing karaoke, and execution or execution of the commands. A data storage unit that stores trigger words for instructing music searches in association with different text data, and a voice that performs voice recognition processing on the user's voice signal output from the sound collecting means and outputs it as text data. a processing unit, a search unit that searches for music based on a search word, a notification unit that notifies the user of search results, an execution unit that executes a command, and a text output by the voice processing unit A control unit that acquires the trigger word based on data, and when the voice processing unit outputs certain text data within a first predetermined time after acquiring the trigger word, the certain text a first process of instructing the search unit to search for a song using the data as the search word; when the trigger word is acquired and the command is stored in the storage means, the stored command is deleted after instructing the execution unit to execute the stored command. On the other hand, the karaoke input device has a control section that performs a second process of deleting the stored command when a second predetermined time has elapsed since the latest command was stored.
Other features of the present invention will be clarified by the description of the specification and drawings described later.

According to the present invention, it is possible to reduce erroneous recognition when using voice input in karaoke singing.

It is a figure which shows the karaoke apparatus which concerns on embodiment. It is a figure which shows the remote control device which concerns on embodiment. It is a figure which shows the table which the data storage part which concerns on embodiment memorize|stores. 4 is a flowchart showing first processing by a control unit of the remote control device according to the embodiment; 9 is a flowchart showing second processing by the control unit of the remote control device according to the embodiment;

A karaoke input device according to an embodiment will be described with reference to FIGS. 1 to 4B.

==Karaoke Device==
The karaoke device K is a device for performing karaoke music and for users to sing karaoke songs. As shown in FIG. 1, the karaoke machine K includes a karaoke main body 10, a speaker 20, a display device 30, a microphone 40, and a remote control device 50. As shown in FIG.

The karaoke main body 10 performs various controls related to karaoke performance and karaoke singing, such as performance control of selected music, display control of lyrics, background images, etc., and processing of audio signals input through the microphone 40 . The speaker 20 is configured to emit sound based on the sound emission signal from the karaoke main body 10 . The display device 30 is configured to display video and images on the screen based on the signal from the karaoke main body 10 . The microphone 40 is configured to convert the user's singing voice into an analog voice signal and input it to the karaoke main body 10 . The remote control device 50 is a device for performing various operations on the karaoke main body 10 when performing karaoke singing. The remote control device 50 in this embodiment corresponds to a "karaoke input device".

== remote control device ==
As shown in FIG. 2, the remote control device 50 according to this embodiment includes storage means 50a, communication means 50b, display means 50c, input means 50d, sound collecting means 50e, and control means 50f. Each configuration is connected to bus B via an interface (not shown).

[Storage means]
The storage unit 50a is a large-capacity storage device that stores various data, such as a hard disk drive. In this embodiment, part of the area of the storage means 50a functions as the data storage section 100. FIG.

(data storage unit)
The data storage unit 100 stores a plurality of commands and trigger words in association with different text data.

A command is an instruction corresponding to a process that can be executed during karaoke singing. Commands are, for example, "Increase the tempo of karaoke performance", "Lower the key of karaoke performance", "Pause karaoke performance", "Increase the volume of the microphone", "Lower the volume from the speaker", " This is a command for executing a process such as “turn off display of lyrics”.

A trigger word is a word or short sentence for instructing execution of a command or search for music. The trigger word is preferably a coined word that does not appear in the lyrics of a song or conversation between users. One trigger word is set in advance for each remote control device.

Text data is data for identifying commands and trigger words. A plurality of commands and trigger words are each associated with a single different piece of text data.

FIG. 3 is an example of a table stored in the data storage unit 100. As shown in FIG. For example, the command C01 (increase the tempo of karaoke performance by 5%) is associated with the text data of "tempo agete". Also, in this example, the text data "Karaoke" is linked as the trigger word. Note that text data not stored in the table is treated as having no corresponding command. In the following description, it is assumed that the data storage unit 100 stores the table shown in FIG.

[Communication means, display means, input means, sound collection means]
The communication means 50b provides an interface for communicating with the karaoke main body 10. FIG. The display means 50c is a structure for displaying various information. The input means 50d is a structure for the user to input various instructions. The input means 50d is a button or the like provided on the remote control device 50 . Alternatively, if the display means 50c is configured in a touch panel format, the display means 50c also functions as the input means 50d. The sound collecting means 50e is a microphone for collecting the voice uttered by the user and outputting it as a voice signal.

[Control means]
The control means 50 f performs various controls in the remote control device 50 . The control means 50f includes a CPU and memory (both not shown). The CPU implements various functions by executing programs stored in the memory.

Here, it is assumed that the user who uses the karaoke machine K wants to input commands and search words by voice. In this case, the user selects the "voice input" icon displayed on the display unit 50c, for example, via the input unit 50d. Based on the selection, the CPU of the control means 50f executes the program stored in the memory and shifts to the voice input mode. In this case, the control unit 50f functions as the voice processing unit 200, the search unit 300, the notification unit 400, the execution unit 500, and the control unit 600.

(sound processing unit)
The voice processing unit 200 performs voice recognition processing on the user's voice signal output from the sound collecting means 50e, and outputs it as text data. A known method can be used for the speech recognition processing.

For example, assume that the user U utters "Karaoke" to the sound collecting means 50e. The sound collecting means 50e collects sound and outputs it to the sound processing section 200 as a sound signal. The audio processing unit 200 processes the audio signal and outputs "Karaoke" indicated by the audio signal as text data.

(search part)
The search unit 300 searches for music based on search words. Search words are used when searching for songs to be sung in karaoke. Specifically, search words are singer names, song titles, part of lyrics, and the like. The search unit 300 extracts songs containing a search word from among a plurality of songs. Note that a known method can be used to search for songs based on search words. In this embodiment, search words are input by voice. The search unit 300 searches for music according to instructions from the control unit 600 (details will be described later).

(Notification part)
The notification unit 400 notifies the user of the search result. For example, assume that the search unit 300 has extracted songs X1, X2, and X3 as search results. In this case, the notification unit 400 notifies the result of the search by displaying the song titles and song IDs of the song X1, song X2, and song X3 on the display unit 50c. It should be noted that the search result may be notified by voice via a speaker (not shown) provided in the remote control device 50 .

(execution part)
The execution unit 500 executes commands. The execution unit 500 executes commands stored in the storage unit 50a based on instructions from the control unit 600 (details will be described later).

(control part)
The control unit 600 acquires trigger words based on the text data output by the speech processing unit 200 .

For example, it is assumed that text data "Karaoke" is output from voice processing unit 200 . Control unit 600 checks whether data corresponding to the output text data is stored in data storage unit 100 . According to the example of FIG. 3, the text data "Karaoke" is associated with the trigger word. In this case, the control section 600 acquires the trigger word.

For example, it is assumed that text data "Harahetta" is output from speech processing unit 200 . Control unit 600 checks whether data corresponding to the output text data is stored in data storage unit 100 . According to the example of FIG. 3, there is no trigger word or command associated with the text data "harahetta". In this case, the control unit 600 does not perform the following processing.

Here, the control unit 600 according to the present embodiment performs first processing and second processing. Each process will be described in detail below.

In the first process, when certain text data is output from the speech processing unit 200 within a first predetermined period of time after the acquisition of the trigger word, music is searched using the certain text data as a search word. This is a process for instructing the unit 300 . A value such as "3 seconds" is set in advance for the first predetermined time.

Specifically, the control unit 600 starts timing when the trigger word is acquired. The control unit 600 confirms whether or not the speech processing unit 200 will output the text data within the first predetermined time after the acquisition of the trigger word. Here, it is assumed that the user U utters "Iruma chair" before the first predetermined time elapses, and based on the utterance, the voice processing unit 200 outputs the text data "Illmais". In this case, the control unit 600 determines the text data "Illmais" as the search word. The control unit 600 instructs the search unit 300 to search for music using the search word “Illmais”. Based on the instruction, the search unit 300 searches for music using the search word “Illmais”.

On the other hand, if the speech processing unit 200 does not output certain text data before the first predetermined time elapses, the control unit 600 does not instruct the search unit 300 to search for music.

If the text data is output before the first predetermined time elapses, or if the text data is not output until the first predetermined time elapses, the control unit 600 terminates the time measurement and the timer reset.

In the second process, when the text data linked to the command is output, the command linked to the text data is stored in the storage means 50a, the trigger word is acquired, and the command is stored in the storage means 50a. If so, after instructing the execution unit 500 to execute the stored command, the stored command is deleted. This is the process of deleting commands that are The second predetermined time is set to a value such as "3 seconds" in advance. Note that the first predetermined time and the second predetermined time may be the same time or may be different.

For example, assume that the user U who listened to the introductory part of the music piece X1 feels that the key and the tempo of the music piece X1 are too high to sing in karaoke. In this case, the user U sequentially utters "lower the key" and "lower the tempo" to the sound collecting means 50e. The speech processing unit 200 performs speech recognition processing on the speech signal based on the speech, and outputs "Kisagete" and "Tempo Sagete" as text data.

Control unit 600 checks whether data corresponding to the output text data is stored in data storage unit 100 . According to the example in FIG. 3, the text data "keysagete" is associated with the command C05 (lower the karaoke performance key by 1 semitone), and the text data "tempo sagete" is associated with the command C02 (lower the karaoke performance tempo by 5%). ) are linked. Therefore, the control unit 600 stores the commands C05 and C02 linked to the text data "Kisagete" and "Tempo Sagete" in the order of utterance in the storage unit 50a.

When the command is stored, the control unit 600 resets the timer and starts timing. When storing a plurality of commands as in the above example, the control unit 600 resets the timer each time a command is stored and starts timing anew.

Assume that the user U utters "Karaoke" and the control unit 600 acquires a trigger word. In this case, the control section 600 instructs the execution section 500 to execute the commands C05 and C02 stored in the storage means 50a. After issuing the instruction, the control unit 600 deletes the stored command C05 and command C02 from the storage unit 50a. Note that when the command is deleted, the control unit 600 ends the timekeeping.

On the other hand, when the second predetermined time has passed since command C02 was stored, control unit 600 deletes command C05 and command C02 from storage unit 50a. It should be noted that when the command is deleted, the control unit 600 ends the timing. That is, control unit 600 deletes the stored command when the second predetermined time has passed since the latest command was stored.

Here, when a plurality of commands are stored, the control section 600 can instruct the execution section 500 to execute all the commands.

For example, control unit 600 can instruct execution unit 500 to execute all commands in the order in which they are stored. In the above example, when the trigger word is acquired and the command C05 and the command C02 are stored, the control section 600 instructs the execution section 500 to execute the command C05 and the command C02 in this order. After issuing the instruction, the control unit 600 deletes all stored commands from the storage unit 50a.

Based on the instruction, the execution unit 500 first executes a process of lowering the karaoke performance key of the song X1 by one semitone, and then executes a process of lowering the tempo by 5%.

Alternatively, when a plurality of commands are stored, the control section 600 may instruct the execution section 500 to execute only some of the commands.

For example, the control unit 600 may delete all stored commands after instructing the execution unit 500 to execute only the latest commands.

In the case of the above example, the command C05 and the command C02 are stored in the order of the storage means 50a. Here, when the trigger word is acquired, the control unit 600 instructs the execution unit 500 to execute only the latest command C02. Even when instructing execution of some of the stored commands in this way, the control unit 600 deletes all the stored commands from the storage unit 50a after the instruction.

Based on the instruction, the execution unit 500 only executes the process of lowering the tempo of the karaoke performance of the song X1 by 5%.

==About the processing in the remote controller==
Next, processing in the control unit 600 of the remote control device 50 according to this embodiment will be described with reference to FIGS. 4A and 4B. FIG. 4A is a flowchart showing processing (first processing) in the control unit 600 when searching for music based on voice input. FIG. 4B is a flowchart showing processing (second processing) in the control unit 600 when executing a command based on voice input. In this example, it is assumed that the voice input mode is being executed. It is also assumed that the data storage unit 100 stores a plurality of commands and one trigger word in association with different text data.

(First processing)
The speech processing unit 200 performs speech recognition processing on the user's speech signal output from the sound collecting means 50e and outputs it as text data (output of text data, step 10).

The control unit 600 acquires trigger words based on the text data output by the speech processing unit 200 . Further, the control unit 600 starts time measurement when the trigger word is acquired (acquisition of the trigger word and start of time measurement; step 11).

If the speech processing unit 200 outputs certain text data before the first predetermined time has elapsed after acquisition of the trigger word (Y in step 12), the control unit 600 treats the certain text data as a search word. The search unit 300 is instructed to search for the music to be played. In addition, the control unit 600 ends the time measurement and resets the timer (instruction to search and end of time measurement; step 13).

The search unit 300 searches for music based on the instruction in step 13 (search for music; step 14).

The notification unit 400 notifies the user of the search result obtained in step 14 (notification of search result; step 15).

On the other hand, if the speech processing unit 200 does not output certain text data within the first predetermined time after the trigger word is acquired (N in step 12), the control unit 600 terminates timing. to reset the timer, and the subsequent processing is not performed (end of timing, step 16).

(Second processing)
The speech processing unit 200 performs speech recognition processing on the user's speech signal output from the sound collecting means 50e and outputs it as text data (output of text data, step 20).

When the text data associated with the command is output, the control unit 600 stores the command associated with the text data in the storage unit 50a. In addition, when the command is stored, the control unit 600 resets the timer and starts timing (storing the command, resetting the timer, and starting timing; step 21).

When the trigger word is acquired and the command is stored (Y in step 22), the control unit 600 instructs the execution unit 500 to execute the stored command (instruct execution of the command; step 23). ). Note that the execution unit 500 executes the command based on the instruction of step 23 .

Thereafter, control unit 600 deletes the stored command. In addition, the control unit 600 ends the timing (deletion of command and termination of timing; step 24). On the other hand, if the second predetermined time has passed since the start of time measurement (Y in step 25), the control unit 600 deletes the stored command and ends the time measurement (command deletion and time measurement). end of step 24).

As is clear from the above, the remote control device 50 according to the present embodiment is used when performing karaoke singing. The remote control device 50 has a data storage unit that stores a plurality of commands corresponding to processes that can be executed during karaoke singing, and trigger words for instructing the execution of the commands or the search for music, in association with different text data. 100, a speech processing unit 200 that performs speech recognition processing on the user's speech signal output from the sound collecting means 50e and outputs it as text data, a search unit 300 that searches for music based on search words, and the user , a notification unit 400 that notifies the result of the search, an execution unit 500 that executes the command, and a control unit 600 that acquires the trigger word based on the text data output by the voice processing unit 200, and the trigger word is A first process of instructing the search unit 300 to search for a song using the given text data as a search word when the voice processing unit 200 outputs certain text data before a first predetermined time elapses after the acquisition. , and when the text data linked to the command is output, the command linked to the text data is stored in the storage means 50a, the trigger word is acquired, and the command is stored in the storage means 50a , after instructing the execution unit 500 to execute the stored command, delete the stored command, and delete the stored command when the second predetermined time has elapsed since the latest command was stored. and a control unit 600 that performs a second process for performing the processing.

According to the remote control device 50 as described above, it is possible to search for music by voice input, triggered by the acquisition of the trigger word. Therefore, the possibility of erroneously recognizing a search word is reduced. Further, according to the remote control device 50 as described above, when a command is input by voice, the command is executed upon acquisition of the trigger word. Therefore, the possibility of executing an unintended command due to erroneous command recognition is reduced. That is, according to the remote control device according to the present embodiment, it is possible to reduce erroneous recognition when using voice input in karaoke singing.

Also, when a plurality of commands are stored, the control unit 600 instructs the execution unit 500 to execute all the commands in the order in which they are stored, and then deletes all the stored commands. With such a configuration, all commands can be executed in the order desired by the user. Further, since all the stored commands are deleted after command execution is instructed, the next voice input becomes possible.

On the other hand, when a plurality of commands are stored, the control unit 600 may delete all stored commands after instructing the execution unit 500 to execute only the latest command. According to such a configuration, it is possible to execute only part of the command desired by the user. Further, since all the stored commands are deleted after command execution is instructed, the next voice input becomes possible.

<Others>
In the above embodiment, the remote control device 50 has been described as an example of the input device for karaoke. On the other hand, the karaoke apparatus K itself may function as a karaoke remote controller. In this case, the karaoke main body 10 includes at least storage means 50a (data storage section 100), communication means 50b, input means 50d, control means 50f (voice processing section 200, search section 300, notification section 400, execution section 500, control section 600). ). The display device 30 functions as the display means 50c, the remote control device 50 functions as the input means 50d, and the microphone 40 functions as the sound collecting means 50e.

In the example of the embodiment described above, a plurality of commands stored in the data storage unit 100 may have priorities set. In this case, the data storage unit 100 stores, for each command, priority information indicating the priority when executing a plurality of commands. Further, when a plurality of commands are stored, the control unit 600 deletes all the stored commands after instructing the execution unit 500 to execute the commands based on the priority information. For example, in the example of the embodiment, it is assumed that the priority of command C05 stored in storage means 50a is set to "high" and the priority of command C02 is set to "medium". In this case, the control unit 600 can instruct the execution unit 500 to execute only the high priority command C05 or to execute the high priority command C05 first.

Also, some users may wish to cancel a command that has been voice-inputted once. Therefore, the data storage unit 100 may store a cancel word for canceling command input in association with the text data. In this case, the control unit 600 can acquire the cancel word based on the text data output by the speech processing unit 200. FIG. Further, when the cancel word is acquired, the control unit 600 deletes all the stored commands without instructing the execution unit 500 to execute the stored commands.

For example, in the example of the embodiment, it is assumed that command C05 and command C02 are stored in storage means 50a. It is also assumed that the text data "Motoi" is associated with the cancel word.

The user utters the cancel word "motoi" in order to cancel the voice-inputted command. The speech processing unit 200 outputs text data "Motoi". Control unit 600 checks whether data corresponding to the output text data is stored in data storage unit 100 . As described above, the text data "Motoi" is associated with the cancel word. Therefore, the control unit 600 acquires the cancel word. The control unit 600 deletes the commands C05 and C02 stored in the storage unit 50a from the storage unit 50a without instructing the execution unit 500 to execute them.

Also, the first process and the second process in the above embodiment may be performed continuously. That is, after the control unit 600 instructs the execution unit 500 to execute the command stored in the storage unit 50a, when the voice processing unit 200 outputs the text data before the first predetermined time elapses , the search unit 300 may be instructed to search for music using the text data as a search word.

Conversely, after the control unit 600 instructs the execution unit 500 to execute the command stored in the storage unit 50a, it is assumed that the first predetermined time elapses until a new trigger word is input by voice. Even if the audio processing unit 200 outputs the text data by then, the search unit 300 may not be instructed to search for music using the text data as a search word.

The above embodiments are presented as examples and are not intended to limit the scope of the invention. The above configurations can be implemented in combination as appropriate, and various omissions, replacements, and modifications can be made without departing from the scope of the invention. The above-described embodiments and modifications thereof are included in the invention described in the claims and their equivalents, as well as being included in the scope and gist of the invention.

50 remote control device 100 data storage unit 200 audio processing unit 300 search unit 400 notification unit 500 execution unit 600 control unit

Claims (5)

A karaoke input device used when performing karaoke singing,
a data storage unit that stores a plurality of commands corresponding to processes that can be executed during karaoke singing, and trigger words for instructing the execution of the commands or the search for music, respectively, in association with different text data;
a speech processing unit that performs speech recognition processing on a user's speech signal output from the sound collecting means and outputs it as text data;
a search unit that searches for songs based on search words;
a notification unit that notifies the user of search results;
an execution unit that executes a command;
A control unit that acquires the trigger word based on the text data output by the voice processing unit, the text data having the voice processing unit before a first predetermined time elapses after acquiring the trigger word. is output, a first process of instructing the search unit to search for songs using the certain text data as the search word, and when text data linked to the command is output, the text data When the linked command is stored in the storage means, the trigger word is acquired, and the command is stored in the storage means, after instructing the execution unit to execute the stored command, a control unit that deletes the stored command and performs a second process of deleting the stored command when a second predetermined time has elapsed since the latest command was stored;
Karaoke input device having wherein, when a plurality of the commands are stored, the control unit instructs the execution unit to execute all the commands in the order in which they are stored, and then deletes all the stored commands. Item 1. An input device for karaoke according to item 1. 2. The control unit, when storing a plurality of the commands, deletes all the stored commands after instructing the execution unit to execute only the latest command. An input device for karaoke as described. The data storage unit stores priority information indicating a priority when executing a plurality of commands for each command,
3. The control unit, when storing a plurality of commands, deletes all the stored commands after instructing the execution unit to execute the commands based on the priority information. 1. The input device for karaoke according to 1. the data storage unit stores a cancel word for canceling the input of the command in association with text data;
The control unit
When a cancel word is acquired based on the text data output by the speech processing unit, all stored commands are deleted without instructing the execution unit to execute the stored commands. The input device for karaoke according to any one of claims 1 to 4.

Images