JP2011039164A - Communication karaoke system for automatically creating customer-by-customer singing history based on singing voice characteristics - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To automatically record a singing history of a customer to a database without requiring the customer to perform troublesome operation for input of a customer ID every time the customer sings when the customer sings a Karaoke musical piece and to search the singing history stored in the database at high speed with little processing load when providing service for utilizing a recorded data of the database. <P>SOLUTION: A database server 200 receives an information set of a musical piece ID, signing time and voice characteristics data from a karaoke device 100, searches the voice characteristics data most similar to the received voice characteristics data from voice characteristics database 210, extracts a corresponding customer ID, and additionally records the received musical piece ID and the singing time, to a corresponding singing history in a customer database 220, based on the extracted customer ID. <P>COPYRIGHT: (C)2011,JPO&INPIT

Description

  The present invention relates to a communication karaoke system in which a plurality of karaoke apparatuses are connected to a database server via a communication network, and more particularly to a communication karaoke system that automatically creates a singing history for each customer based on the characteristics of singing voices.

  In the communication karaoke system, information related to the use of a large number of karaoke apparatuses distributed over a wide area can be collected and aggregated in a database server via a communication network. By using the information of this database server, various services can be provided to stores and users of karaoke devices connected via the communication network, for example, as shown below. . Furthermore, it is possible to create a new service that uses the information gathered in the database server.

  Examples listed below are related arts of a communication karaoke system equipped with a database server that aggregates and manages customer-specific usage information of karaoke devices.

<< Patent No. 3629450 (Patent Document 1) >>
Even if there are a large number of customers in a store that uses a karaoke device for customer service, the customer database that collects performance histories (music selection history or singing history) for each customer is provided in the database server. In addition to improving the quality of service by operating the karaoke device quickly in response to requests and requests, the karaoke device operation rate is improved by naturally guiding customers to karaoke.

<< Patent No. 3946662 (Patent Document 2) >>
This personal customer A listens to a song sung by another customer while a regular customer A enjoys karaoke, with respect to a personal karaoke song book system that creates and uses a favorite song list for each user in a karaoke device. It is automatically compiled as a list of songs (list of songs that have been listened to) that would have been listened to, and the songs that Customer A has listened to many times are introduced on the personal information screen of Customer A and registered in the favorite songs list Prompt.

<< Patent No. 3946669 (Patent Document 3) >>
Provided with a database that aggregates customer-specific records associated with customer IDs, updates corresponding customer-specific records based on customer-specific record update information received from a karaoke performance terminal, and requests customer-specific record requests that specify customer IDs When receiving from the karaoke performance terminal, the corresponding customer-specific record is transmitted to the karaoke performance terminal. The customer-specific record includes basic registration information related to the customer and customer music selection history information. For customers who enjoy karaoke singing in a karaoke box (private room without a store clerk), a customer service function that makes a familiar store clerk feel like a regular customer.

  Further, as exemplified below, voice feature data (voice print data) is extracted from user's input voice as identification data for identifying a customer (user individual), and customer-specific usage information is searched using this voice feature data. An online karaoke system has been developed.

<< JP-A-9-146563 (Patent Document 4) >>
The user's personal information is managed in a database using the voice print data as a key, the voice print data of the user who intends to use the service is extracted, and the user's personal information is searched using this voice print data. This eliminates the need for the user to input a personal ID or set an ID card, and does not require a device such as a personal remote control.

Japanese Patent No. 3629450 Japanese Patent No. 3946662 Japanese Patent No. 3946669 JP-A-9-146563

  In the online karaoke system, it is possible to provide various services to karaoke installation stores and users by collecting and aggregating customer-specific usage information of a large number of karaoke devices distributed over a wide area in a database server. In addition, the creation of a new service that uses the information gathered in the database server is also expected, but in order to do so, every time a karaoke use event occurs in one of a number of karaoke devices, It is necessary to transmit information, that is, the ID (music ID) of the karaoke music sung and sung by the customer and the singing date and time to the database server together with the ID (customer ID) for identifying the customer. The database server aggregates and manages music IDs and singing dates transmitted from the karaoke apparatus in association with customer IDs.

  Such customer-specific usage information management makes it possible to provide various services. For that purpose, for each event of karaoke use, the ID of the customer who has generated the event is acquired, and A process for associating the music ID and singing date and time as the breakdown of the event is required. However, in order to perform this association process, each time the customer sings karaoke music once, the customer has to input his own customer ID or some identification information for identifying himself / herself. You have to ask.

  As means for omitting or simplifying the input effort of the identification information, voice feature data such as voiceprint data is extracted from the user's input voice, and the user's karaoke usage information is searched for the extracted voice feature data. It is conceivable to use key data for this purpose. In other words, it is possible to omit or simplify the customer ID input by substituting the voice feature data for the customer ID, but the information retrieval using the voice feature data as the key data can be described by a simple character code string. Compared to information retrieval using the customer ID as key data, the processing load becomes extremely large.

  For example, in order to be able to search for customer-specific singing history from the customer's voice feature data, the customer's singing history is recorded in a database in association with the customer's voice feature data, and the recorded singing history is stored in the customer's voice feature data. When presenting as requested, the customer's singing history is searched from the database using the voice feature data of the customer as key data.

  However, the number of users handled in the online karaoke system may be as large as several million, and processing requests for retrieving a customer's singing history from a database are also generated at a frequency corresponding to the number of users. In this case, if the customer's singing history is recorded in the database in association with the customer's voice feature data, the recorded data (singing history) is also searched with the voice feature data. It will be very big.

  For this reason, although the trouble of inputting the customer ID is simplified, the processing load of the system is greatly increased, and in particular, there is a problem that it becomes impossible to smoothly provide the service using the data recorded in the database.

  The present invention has been made in view of the technical background as described above, and the purpose of the present invention is when a customer sings karaoke music in a communication karaoke system in which a plurality of karaoke apparatuses are connected to a database server via a communication network. Can automatically update the customer's singing history recorded in the database based on the characteristics of the customer's singing voice, without the customer having to enter the customer ID every time they sing. On the other hand, when providing a service that utilizes the recorded data of the database, it is possible to search the singing history recorded in the database at a high speed with a small processing load, thereby providing the service. An object of the present invention is to provide a communication karaoke system that can be performed smoothly.

The karaoke apparatus according to the present invention is specified by the following items (1) to (12).
(1) A communication karaoke system in which a plurality of karaoke apparatuses are connected to a database server via a communication network. (2) The database server includes a voice feature database and a customer database. (3) The voice feature database is (4) The customer database includes the correspondence between the customer ID and the singing history (5) The singing history describes the association between the song ID and the singing date and time. (6) The database server receives the information set of the song ID, singing date / time, and voice feature data from the karaoke device, and performs customer identification processing and history update processing. (7) Customer identification processing is received. Search voice feature data that most closely matches the voice feature data from the voice feature database and extract the corresponding customer ID (8) The new process adds a record of the received song ID and singing date and time to the corresponding singing history in the customer database based on the customer ID extracted in the customer specifying process. (9) The karaoke apparatus is accompanied by a karaoke performance. Perform voice feature analysis processing and history creation processing (10) Voice feature analysis processing analyzes the singing voice signal from the microphone to generate voice feature data,
(11) In the history creation process, the song ID of the performance song, the performance date and time, and the generated voice feature data are recorded in association with each other. (12) The karaoke apparatus communicates with the database server and is recorded. Send information set of song ID, performance date and voice feature data

  In a communication karaoke system in which a plurality of karaoke apparatuses are connected to a database server via a communication network, when a customer sings karaoke music, the customer does not have to enter the customer ID every time he sings. Based on the characteristics of the customer's singing voice, the customer's singing history recorded in the database can be automatically updated. On the other hand, when providing a service utilizing the recorded data of the database, the database It is possible to search for the singing history recorded in a high-speed with a small processing load, and thereby to provide the service smoothly.

It is a block diagram which shows schematic structure of the communication karaoke system of this invention. It is a block diagram which shows schematic structure of the karaoke apparatus used with this invention system. It is a flowchart which shows one Example of the singing voice analysis process in this invention system.

=== Configuration of online karaoke system ===
A schematic configuration of a communication karaoke system constituting an embodiment of the present invention is shown in FIG.
As shown in the figure, in the communication karaoke system of the present invention, first, a plurality of karaoke apparatuses 100 are connected to a database server 200 via a communication network. The database server 200 includes a voice feature database 210 and a customer database 220.

  The voice feature database 210 aggregates and manages voice feature data in association with customer IDs. The customer database 220 aggregates and manages data including the correspondence between customer IDs and singing histories. In the singing history, the correspondence between the song ID and the singing date is described.

  The database server 200 receives information sets of music IDs, singing dates and voice feature data from a large number of karaoke apparatuses 100 distributed over a wide area, and performs customer identification processing and history update processing.

  The customer specifying process searches the voice feature database 210 for voice feature data that most closely matches the received voice feature data, and extracts the corresponding customer ID. In the history update process, based on the customer ID extracted in the customer specifying process, a record of the received song ID and singing date is added to the corresponding singing history in the customer database 220.

  The karaoke device performs a voice feature analysis process and a history creation process along with the karaoke performance, creates an information set of music ID, singing date / time, and voice feature data, and transmits it to the database server 200.

=== Configuration of Karaoke Device ===
FIG. 2 shows a schematic configuration of the hardware main body of the karaoke apparatus used in the system of the present invention.
This karaoke apparatus is a computer application device equivalent to a well-known personal computer, and the central processing unit 11 that forms the core of the karaoke apparatus forms a computer main body including a CPU, a RAM, and a ROM.

  Under the control and management of the central processing unit 11, a karaoke host device via a hard disk device 12 as a large-capacity external storage, an optical disk playback device 13 such as a CD-ROM or DVD-ROM, and a public communication line such as an optical communication line A communication control device 14 that communicates with a database server or the like, a user interface device 15 that exchanges input from the user and responses to the user, and generates an acoustic signal of accompaniment music based on MIDI music performance data Music generating device 16, accompaniment music, an acoustic device 17 that amplifies an acoustic signal from a microphone 171, etc., and produces a sound from a speaker 172, a display (display device) 18 using an LCD or PDP, and the like to be displayed on this display 18 A video processing device 19 for processing video data is installed.

  More specifically, the hard disk device 12 stores karaoke data including accompaniment music data mainly composed of MIDI data and lyric character data that is the origin of generation of lyrics subtitles for a large number of karaoke songs. In addition, for the long-format video data in a predetermined format, script data that defines the video data processing sequence (storage location and processing order of video data to be processed, etc.) Table of contents information such as the release year and the singing part of the lyrics is also stored.

  The music generation device 16 generates accompaniment music from the accompaniment music data in the karaoke data. With respect to the lyric character data, a lyric subtitle image in which a portion to be sung is changed in color in synchronization with the accompaniment music is sequentially generated, and a bitmap is developed in the video RAM. Also, predetermined moving image data is sequentially transferred to the video processing device 19 in a predetermined order based on the script data, and the background moving image of the lyrics subtitle is decoded.

  The acoustic device 17 mixes and amplifies the accompaniment music generated by the music generation device 16 and the singing voice input to the microphone 171 and outputs the sound from the speaker 172. The video processing device 19 superimposes the lyrics subtitles on the decoded moving image and displays and outputs them on the display 18. Lyric subtitles are sequentially created from time-series lyrics character data synchronized with the progress of the accompaniment music.

  The user interface device 15 includes an operation panel 151 of the karaoke device main body and a karaoke remote control device 152. In order to exchange operation information with the karaoke remote control device 152, short distance wireless communication means (IrDA transceiver, infrared LED, infrared light receiving element) capable of bidirectional communication is provided.

  The central processing unit 11 identifies karaoke data, script data, table of contents information and the like of each music piece by the music piece ID, and manages this as a karaoke database. The central processing unit 11 receives a reservation command (request) from the user interface device 15. The reservation command includes a music ID (music identification code). When this reservation command is received, the music IDs included in the command are registered at the end of the processing reservation queue in the order of reception. And music ID is taken out sequentially from the head of a queue. When the music ID is extracted from the queue, the karaoke data for the corresponding music is extracted from the karaoke database and used for performance processing.

=== Characteristic Functions of the Invention Constructed by the Hardware ===
In addition to the basic functions described above, the karaoke apparatus 100 is configured with a function that performs voice feature analysis processing and history creation processing in conjunction with karaoke performance.

  The voice feature analysis process analyzes the singing voice signal from the microphone 171 and generates voice feature data. In the history creation process, the song ID of the performance song, the performance date and time, and the generated voice feature data are recorded in association with each other. This recorded data, that is, an information set of music ID, performance date / time, and voice feature data is transmitted to the data server 200 via the communication network.

=== Operation of the online karaoke system according to the present invention ===
On the karaoke device 100 side, when a user who has registered a customer ID in advance sings a karaoke piece arbitrarily selected according to the accompaniment performance, the characteristics of the voice uttered by the singing are analyzed.

  The voice feature data generated by this analysis process is recorded in association with the song ID and performance date of the performance song. This recorded data, that is, an information set of music ID, performance date / time, and voice feature data is transmitted to the data server 200 via the communication network.

  On the database server 200 side, when an information set of music ID, performance date / time, and voice feature data is received from the karaoke apparatus 100, a customer identification process and a history update process are performed.

  The customer specifying process searches the voice feature database 210 for voice feature data that most closely matches the received voice feature data, and extracts the corresponding customer ID. In the history update process, based on the customer ID extracted in the customer specifying process, a record of the received song ID and singing date is added to the corresponding singing history in the customer database 220. That is, the record of the music ID and the singing date and time recorded in association with the customer ID extracted in the customer specifying process is updated.

  With the above processing, when a customer sings, the customer recorded in the customer database 220 based on the characteristics of the customer's singing voice, even if the customer does not bother to input the customer ID every time he sings. The singing history can be automatically updated.

  On the other hand, when providing a service utilizing the recorded data of the customer database 220, the customer database 220 is recorded based on the customer ID, not the voice feature data. Singing history can be performed at a high speed with a small processing load. Thereby, the service can be smoothly provided.

=== Preferred Embodiment of Voice Feature Analysis Processing ===
The voice feature analysis process performed on the karaoke device 100 side analyzes the singing voice, but the voice feature data sufficient to identify a specific customer in the customer specifying process in the database server 200 is the singing that is the voice source. It cannot be generated until it has progressed to some extent.

  On the other hand, in the karaoke apparatus 100 that is often used by a group, members in the group repeat selection and singing for each. In other words, the same karaoke device is used in the same time zone only by the members of the group using the karaoke device in that time zone.

  In this case, each member of the use group sings a plurality of karaoke pieces, but generating the voice feature data each time the singing is problematic in securing the information processing capability of the karaoke apparatus 100. It doesn't have to be.

  Although the number of users handled in the online karaoke system may be on the scale of millions, generation of voice feature data sufficient to identify a specific user from such a large number of users In order to do this, there is a certain information processing burden. In order to reduce this processing burden, in the present invention, as shown in a flowchart in FIG. 3, there are two types of singing voice analysis processing (processing route of S1, S2-S5 and processing route of S1, S2, S6, S7). Divided into two.

  That is, voice feature data generated for a plurality of songs sung during the latest predetermined period is temporarily recorded. The most recent predetermined period is set based on the time during which the karaoke apparatus is exclusively used in the same group, but may be, for example, the nearest half day (daytime and nighttime) or a time unit of one day.

  In FIG. 3, when analyzing the singing voice during singing, the voice feature data generated and recorded for a plurality of songs sung in the most recent predetermined period is referred to. It is checked whether or not the voice feature data of the voice feature that can be regarded as the same as the voice feature of the singing voice being analyzed is in the voice feature data set generated and recorded during the most recent predetermined period (S1).

  Here, when there is no voice feature data that can be regarded as the same in the recorded voice feature data set, the singing voice analysis process is continued to generate voice feature data (S2 to S5).

  On the other hand, if the voice feature data that can be regarded as the same is in the recorded voice feature data set, the singing voice analysis process is stopped, and the voice feature data that can be regarded as the same in the recorded voice feature data set is analyzed. It is set as voice feature data about the singing voice (S2, S6, S7).

  What should be noted in this voice feature analysis process is that the number of voice feature data generated and recorded for a plurality of songs sung during the most recent predetermined period is equivalent to the number of people using the same karaoke device during the predetermined time. However, compared to the number of voice feature data on the scale of millions that may be handled by the online karaoke system, it is so small that it cannot be compared.

  Therefore, the collation of whether or not the voice feature data whose analysis has been started is in the recorded voice feature data set can be accurately performed with an overwhelmingly small processing amount compared to the case where the database server 200 performs the same collation. Can be done.

  Thereby, the burden of the voice feature analysis process in the karaoke apparatus 100 can be reduced, and the information processing capability of the karaoke apparatus 100 can be secured high.

DESCRIPTION OF SYMBOLS 11 Central processing unit 12 Hard disk device 13 Optical disk reproducing device 14 Communication control device 15 User interface device 151 Operation panel 152 Karaoke remote control device 16 Music generating device 171 Microphone 172 Speaker 17 Sound device 18 Display (display device)
19 Video processing device 100 Karaoke device 200 Database server 210 Voice feature database 220 Customer database

Claims (2)

A communication karaoke system in which a plurality of karaoke apparatuses are connected to a database server via a communication network,
The database server has a voice feature database and a customer database,
The voice feature database aggregates voice feature data in association with customer IDs,
The customer database includes a correspondence between a customer ID and a singing history,
Singing history describes the correspondence between song ID and singing date and time,
The database server receives the information set of the song ID, singing date / time, and voice feature data from the karaoke device, performs customer identification processing and history update processing,
The customer identification process searches the voice feature database for voice feature data that most closely matches the received voice feature data, extracts the corresponding customer ID,
The history update process adds a record of the received song ID and singing date and time to the corresponding singing history in the customer database based on the customer ID extracted in the customer specifying process,
The karaoke device performs voice feature analysis processing and history creation processing along with karaoke performance,
The voice feature analysis process analyzes the singing voice signal from the microphone to generate voice feature data,
In the history creation process, the song ID of the performance song, the performance date and time, and the generated voice feature data are recorded in association with each other,
The karaoke device is a communication karaoke system that communicates with a database server and transmits an information set of recorded music ID, performance date and voice feature data. The voice feature analysis process refers to the voice feature data generated and recorded for a plurality of songs sung during the most recent predetermined period in the process of analyzing the singing voice, and the characteristics of the singing voice being analyzed are A communication karaoke apparatus that employs the recorded voice feature data as the feature data of the singing voice being analyzed when it is determined that the voice feature data can be regarded as the same.

Images