JP2023122012A - karaoke device - Google Patents

Abstract

To provide a Karaoke device capable of presenting appropriate breathing timing to a singer.SOLUTION: A Karaoke device includes: an extraction unit for extracting timing in which a singer can breathe in music on the basis of reference data of the music; a detection unit for detecting breathing information including timing in which the singer breathed on the basis of a voice signal corresponding to singing voice of the singer and/or a video signal obtained by imaging the singer; a specification unit for specifying timing in which the singer can breathe next on the basis of timing in which the singer can breathe in extracted music and the detected breathing information; and a presentation unit which presents timing to perform specified next breathing to the singer.SELECTED DRAWING: Figure 2

Description

The present invention relates to a karaoke machine.

As a singing support function provided by a karaoke device, there is one that presents the timing of breathing to the singer.

For example, Patent Literature 1 discloses a technique that makes it possible to intuitively grasp the timing of breathing by discretely displaying the sounds before and after the timing of breathing based on information indicating the timing of breathing included in reference data. disclosed.

JP 2016-031394 A

However, according to the technique disclosed in Patent Literature 1, only predetermined breath timings can be presented for one piece of music.

SUMMARY OF THE INVENTION It is an object of the present invention to provide a karaoke machine capable of presenting a singer with appropriate timing for taking a breath.

One invention for achieving the above object is an extracting unit that extracts the timing at which it is possible to take a breath in the song based on the reference data of the song, and corresponds to the singing voice of the singer who sings karaoke of the song. Based on the audio signal and/or the video signal obtained by photographing the singer, a detection unit that detects breath information including the timing of the breath performed by the singer, and the extracted breath in the song. and the timing at which the singer can take the next breath based on the timing and the detected breath information, and the specified timing at which the next breath can be taken. and a presentation unit that presents to the singer.
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 present an appropriate timing for taking a breath to the singer.

It is a figure which shows the karaoke apparatus which concerns on embodiment. It is a figure which shows the karaoke main body which concerns on embodiment. FIG. 10 is a diagram showing an example of presenting the timing of the next breath by the presenting unit according to the embodiment; It is a flow chart which shows processing of a karaoke device concerning an embodiment.

<Embodiment>
A karaoke apparatus according to an embodiment will be described with reference to FIGS. 1 to 4. FIG.

==Karaoke Device==
The karaoke device K is a device for performing karaoke performances of musical pieces and singing karaoke by singers. 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, a remote control device 50, and a photographing means 60.

The karaoke main body 10 performs various controls related to karaoke performance and karaoke singing, such as karaoke 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 karaoke performance sounds and singing voices based on signals 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 singing voice accompanying the karaoke singing of the singer 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 . The photographing means 60 is a camera for photographing the singer.

As shown in FIG. 2, the karaoke main body 10 according to this embodiment includes storage means 10a, communication means 10b, input means 10c, performance means 10d, and control means 10e. Each configuration is connected to bus B via an interface (not shown).

[Storage means]
The storage unit 10a is a large-capacity storage device that stores various data. The storage means 10a stores music data.

The music data is provided with music identification information for specifying individual music. The song identification information is information unique to each song, such as a song ID for identifying the song. The music data includes accompaniment data, reference data, and the like.

Accompaniment data is data that is the source of karaoke performance sounds. The reference data is data indicating the main melody to be sung of the karaoke-performed song. Each piece of music (reference data for each piece of music) is composed of a plurality of notes. Each note is set with a predetermined pitch, utterance start timing, utterance end timing, and the like. The utterance start timing is the timing at which utterance of a character corresponding to a certain note should be started, and the utterance end timing is the timing at which the utterance of a character corresponding to a certain note should be finished. The utterance start timing and the utterance end timing can be indicated by the elapsed time based on the timing at which the performance of the music is started.

The storage means 10a also stores lyrics data for displaying the lyrics corresponding to the music on the display device 30 or the like in time with the karaoke performance of the music. The lyric data includes information on characters that form the lyrics of the music. One character is associated with one note. The lyric data also includes timing information indicating the timing of displaying each character. The timing for displaying one character can be indicated by the elapsed time based on the timing at which the performance of the music is started.

Further, the storage means 10a stores background image data such as a background image displayed on the display device 30 or the like during a karaoke performance, and attribute information of music. The attribute information includes, for example, the name of the singer, music genre information of the song, tempo information of the song, and the like.

[Communication means, input means, performance means]
The communication means 10b provides an interface for communicating with the remote controller 50. FIG. The input means 10c is a structure for the singer to input various instructions. The input means 10c is a button or the like provided on the karaoke main body 10 . Alternatively, the remote control device 50 may function as the input means 10c. The performance means 10d performs karaoke performance of music and processes signals based on singing voices input through the microphone 40 under the control of the control means 10e.

[Control means]
The control means 10e performs various controls in the karaoke apparatus K. FIG. The control means 10e includes a CPU and memory (both not shown). The CPU implements various functions by executing programs stored in the memory.

In the present embodiment, the control means 10e functions as an extraction unit 100, a detection unit 200, an identification unit 300, and a presentation unit 400 by the CPU executing programs stored in the memory.

(Extraction part)
The extracting unit 100 extracts the timing at which the user can take a breath in the music based on the reference data of the music.

The timing at which it is possible to take a breather is the timing at which the singer can take a breather without straining (with a margin). For example, non-singing sections (sections such as prelude, interlude, and postlude where lyrics to be sung in a certain song are not set) and singing sections (lyrics to be sung in a certain song, such as A melody and chorus) is set), if there is a certain amount of time between the end of vocalization of one character and the start of vocalization of the next character, the singer can take a reasonable breather. The timing at which it is possible to take a breath can be indicated by the elapsed time based on the timing at which the performance of the music is started.

Specifically, the extracting unit 100 extracts the utterance end timing TE _n of one note N _n and the utterance start timing TS n _{+1 of the next note N n+ 1} in the reference data for the song selected by the singer. Find the time difference (TS _n+1 -TE _n ). The extraction unit 100 checks whether the obtained time difference satisfies a first predetermined condition. When the first predetermined condition is satisfied, the extraction unit 100 extracts the utterance end timing TE _n of the note N _n as the timing at which the breath can be taken. The extraction unit 100 performs the above-described processing for each note included in the song selected by the singer (excluding the last note of the song) in the order of the notes, so that there are multiple timings at which you can take a breath in the song. Extract. The first predetermined condition is a condition that is set in advance assuming a period of time during which a reasonable breath can be taken, such as 250 msec or more and longer than 300 msec.

(Detection unit)
The detection unit 200 detects the timing of the breath performed by the singer based on the audio signal corresponding to the singing voice of the singer who sings karaoke of the song and / or the video signal obtained by shooting the singer. Detect breath information including: The timing of the breath performed by the singer is the timing of the breath actually performed during karaoke singing of the song. The timing of the breath performed by the singer can be indicated by the elapsed time based on the timing when the performance of the music is started.

Specifically, the detection unit 200 analyzes the frequency characteristics of the audio signal corresponding to the singing voice of the singer input through the microphone 40 using a known technique. If the detection unit 200 determines, based on the analysis result, that an audio signal due to exhalation (audio signal corresponding to overtone components) is not included and an audio signal corresponding to inhalation noise peculiar to breathing is included, The time when the singing voice corresponding to the voice signal is input is detected as the timing of the singer's breathing.

In addition, the detection unit 200 applies the technology described in Japanese Patent Application Laid-Open No. 2007-271977, and based on the power of the singer's voice signal (corresponding to the frequency characteristics described above) and the musical score sound data (corresponding to the reference data described above), It is possible to detect the timing of breathing performed by a person.

On the other hand, the detection unit 200 analyzes the video signal obtained by photographing the singer by the photographing means 60 by a known technique. If the detection unit 200 determines, based on the analysis result, that a movement peculiar to breathing (for example, vertical movement of the shoulder or head, opening and closing of the mouth) is included, the time when the movement was captured is recorded by the singer. It is detected as the timing of breathing performed by

Alternatively, the detection unit 200 compares the timing of the breath performed by the singer detected based on the audio signal and the timing of the breath performed by the singer detected based on the video signal, and detects only the matching or similar timing. may be detected as the timing of the breath performed by the singer. In addition, the detection unit 200 compares the timing of the breath performed by the singer detected based on the audio signal and the timing of the breath performed by the singer detected based on the video signal, and compares the timing of the breath performed by the singer detected based on the video signal. The shortest elapsed time based on the timing at which the performance starts) may be detected as the timing of the breath performed by the singer.

(specific part)
The specifying unit 300 specifies the timing at which the singer can take a next breath based on the extracted timing at which the song can take a breath and the detected breath information. The timing at which the next breath can be taken can be indicated by the elapsed time based on the timing at which the performance of the music is started.

Specifically, the specifying unit 300 determines the timing BT of the breath performed by the singer included in the detected breath information, and the timing TE _m after the timing BT among the timings at which the breath can be taken in the extracted music. to find the time difference (TE _m - BT). The identifying unit 300 determines whether the obtained time difference satisfies a second predetermined condition. If the second predetermined condition is satisfied, the identifying unit 300 identifies the timing TE _m as the timing at which the next breath can be taken. The second predetermined condition is a condition that is set in advance assuming a period of time during which there is a high possibility that you will not be able to hold your breath, such as 10 seconds or less, or less than 15 seconds (a period during which you can sing karaoke without taking a breath).

After taking a breather, karaoke can be sung without taking a breather for a certain period of time. That is, the timing at which the next breath can be taken includes timings that do not need to be specified as the timing at which the next breath can be taken. Therefore, the second predetermined condition is not only the time when there is a high possibility that the breath will not last, such as 10 seconds or more and 15 seconds or less, longer than 9 seconds and less than 13 seconds (time during which karaoke can be sung without breathing), It may be set assuming a time when there is a high possibility that a breather is unnecessary.

(presentation part)
The presentation unit 400 presents the timing at which the specified next breath can be taken to the singer.

Specifically, the presentation unit 400 can display the specified timing at which the next breath can be taken in correspondence with the display of the lyrics of the music.

The presentation unit 400 refers to the timing information included in the lyric data of the song, and extracts the character for which the timing that matches the specified timing at which the next breath can be taken is set. When the extracted characters are displayed on the display screen of the display device 30, the presentation unit 400 displays such that the singer can understand the timing at which the next breath can be taken. For example, as shown in FIG. 3, the presentation unit 400 can present the timing of the next breath to the singer by displaying the character "breathing" after the extracted character "ga". It should be noted that presentation unit 400 may display an icon (for example, a breath symbol) prompting to take a breath instead of the characters “breathe”.

On the other hand, the presentation unit 400 measures the elapsed time from the start of the performance of the music, displays a countdown according to the specified timing at which the next breath can be taken, and performs the specified next breath. It is also possible to display the characters "breathing" when the timing at which it is possible to

Alternatively, the presentation unit 400 emits a sound corresponding to the countdown from the speaker 20 instead of displaying the countdown, thereby presenting the singer with the specified timing at which the next breath can be taken. is also possible.

==Operation of karaoke machine K==
Next, a specific example of the operation of the karaoke machine K in this embodiment will be described with reference to FIG. FIG. 4 is a flow chart showing an operation example of the karaoke machine K. As shown in FIG.

The singer S operates the remote control device 50 to select a song X. The karaoke apparatus K reserves the karaoke performance of the music piece X by registering the music ID of the music piece X in the reservation queue (reservation of the karaoke performance of the music piece X, step 10).

The extraction unit 100 extracts the timing at which the user can take a breath in the music X based on the reference data of the music X read from the storage unit 10a (extract the timing at which the user can take a breath in the music X; step 11).

Specifically, the extraction unit 100 obtains the time difference (TS ₂ −TE ₁ ) between the utterance end timing TE ₁ of the first note N ₁ and the utterance start timing TS ₂ of the next note N ₂ for the song X. The extraction unit 100 checks whether the obtained time difference satisfies a first predetermined condition. In this example, it is assumed that the first predetermined condition is 250 msec or longer. In other words, it is assumed that if the interval between the end timing of uttering a certain note and the start timing of uttering the next note is 250 msec or more, it is possible to take a reasonable breather.

The extracting unit 100 extracts a plurality of timings in music X at which it is possible to take a breath by repeatedly performing the above processing in the order of the notes included in music X. FIG. In this example, as timings at which breath can be taken, utterance end timing TE ₄ (3,000 msec) for _note N ₄ , utterance end timing TE ₈ (7,500 msec) for note N ₈ , . Vocalization end timing TE _n (38,000 msec), utterance end timing TE _o (42,000 msec) for note N _o , utterance end timing TE _p (46,500 msec) for note N _p , utterance end timing TE _q for note N _q (49,000 msec), utterance end timing TE _r of note N _r (52,500 msec), utterance end timing TE _s of note N _s (55,500 msec), utterance end timing TE _t of note N _t (61,500 msec) , are extracted. The numerical value of the timing is based on the timing (0 msec) at which the performance of the music piece X is started.

After that, the karaoke machine K starts karaoke performance of the music piece X (starts karaoke performance of the music piece X, step 12). Singer S sings karaoke song X using microphone 40 .

The detection unit 200 detects breath information including the timing of the breath performed by the singer S based on the audio signal corresponding to the singing voice of the singer S who sings karaoke of the song X (detects breath information. Step 13).

Specifically, the detection unit 200 analyzes the frequency characteristics of the audio signal corresponding to the singing voice of the singer S input through the microphone 40 using a known technique. If the detection unit 200 determines based on the analysis result that the sound signal due to exhalation is not included and the sound signal corresponding to the inhalation noise peculiar to breathing is included, the singing voice corresponding to the sound signal is detected. The input time is detected as the breath timing BT performed by the singer S. In this example, it is assumed that the player takes a breath after 40 seconds from the timing (0 msec) at which the musical composition X starts playing. In this case, the detection unit 200 detects 40,000 msec as the timing BT.

The specifying unit 300 specifies the timing at which the singer S can take the next breath based on the timing at which the song extracted in step 11 can take a breath and the breath information detected in step 13. (Specify the timing at which the next breath can be taken. Step 14).

Specifically, the specifying unit 300 determines the timing BT (40,000 msec) of the breath performed by the singer S included in the detected breath-taking information and the timing at which the breath in the song X extracted in step 11 is possible. , the time difference from the timing after the timing BT. The identifying unit 300 determines whether the obtained time difference satisfies a second predetermined condition. In this example, it is assumed that the second predetermined condition is 10 seconds or more and 15 seconds or less. That is, it is assumed that karaoke can be sung without taking a breath for 10 seconds after the actually taken breath, and there is a high possibility that the breath will not last for more than 15 seconds.

Here, among the timings at which breath can be taken in the piece of music X extracted in step 11, the timing before the utterance end timing TE _n (38,000 msec) of the note N _n is the timing before the timing BT. Therefore, the specifying unit 300 sequentially obtains the time difference from the timing BT (40,000 msec) of the breath performed by the singer _S , starting from the utterance end timing TE _o (42,000 msec) of the note No. determine whether it satisfies

The time difference between the timing BT (40,000 msec) and the utterance end timing TE _n (42,000 msec) of note _No is 2,000 msec. Therefore, the identifying unit 300 determines that the second predetermined condition is not satisfied. Similarly, the time difference between the timing BT (40,000 msec) and the utterance end timing TE _p (46,500 _msec ) of note N _p is 6,500 msec. The time difference from the utterance end timing TE _q (49,000 msec) is 9,000 msec. Therefore, the identifying unit 300 determines that the second predetermined condition is not satisfied.

On the other hand, the time difference between the timing BT (40,000 msec) and the utterance end timing TE _r (52,500 msec) of note N _r is 12,500 msec. Therefore, the identifying unit 300 determines that the second predetermined condition is satisfied.

Note that the time difference between the timing BT (40,000 msec) and the utterance end timing TE _s (55,500 msec) of the note N _s is 15,500 msec. Therefore, the identifying unit 300 determines that the second predetermined condition is not satisfied. Since it is clear that the second predetermined condition is not satisfied at the utterance end timing after this, the specifying unit 300 ends the processing.

The specifying unit 300 specifies the utterance end timing TE _r (52,500 msec) of the note N _r determined to satisfy the second predetermined condition as the timing at which the next breath can be taken. The identifying unit 300 outputs to the presenting unit 400 the identified timing at which the next breath can be taken.

The presentation unit 400 presents to the singer S the timing at which the next breath specified in step 14 can be performed (the timing at which the next breath can be performed is presented, step 15).

Specifically, the presentation unit 400 refers to the timing information included in the lyric data of the song X, and selects a character whose timing matches the utterance end timing TE _r (52,500 msec) of the note N _r (that is, character corresponding to note N _r ). When the character corresponding to the extracted note N _r is displayed on the display screen of the display device 30, the presentation unit 400 determines the timing at which the singer S can take a next breath (timing TE _r at which the vocalization of the note N _r ends). display in such a way that

The karaoke machine K repeats the processing from step 13 to step 15 until the karaoke performance of the piece of music X is completed (in the case of Y in step 16). Note that when a plurality of timings at which the next breath can be taken are identified, they are displayed in correspondence with the display of the lyrics.

As is clear from the above, the karaoke device K according to the present embodiment includes an extraction unit 100 that extracts the timing at which the song can be breathed based on the reference data of the song, and the singer who sings karaoke of the song. Based on the audio signal corresponding to the singing voice and / or the video signal obtained by photographing the singer, the breath information including the timing of the breath performed by the singer is detected. A specifying unit 300 that specifies the timing at which the singer can take the next breath based on the timing at which the breath can be taken in the song and the detected breath information, and the specified next breath. and a presentation unit 400 that presents possible timings to the singer.

According to such a karaoke device K, according to the timing of the breath actually performed by the singer who is singing karaoke of a certain song, the next breath is selected from the timing at which the breath in the song can be taken. Timing can be specified and presented to the singer. Therefore, the singer can grasp the appropriate timing as the timing of the next breath. That is, according to the karaoke apparatus K according to this embodiment, it is possible to present the singer with an appropriate timing for taking a breath.

In addition, in the karaoke machine K according to the present embodiment, the presentation unit 400 can display the specified timing at which the next breath can be taken in correspondence with the display of the lyrics of the music. According to such a karaoke machine K, it is possible to visually present the timing of breathing to the singer.

In the above example, only the utterance end timing TE _r of note N _r is identified as the timing at which the next breath can be taken. On the other hand, the second predetermined condition is not set for each singer. Therefore, depending on the singing ability and manner of singing of the singer, there is a possibility that the breath will stop before the next breath timing specified based on the second predetermined condition.

Therefore, the specifying unit 300 selects the timing at which the next breath can be taken from among the timings at which the breath can be taken in the extracted music, together with the timing that satisfies the second predetermined condition, and the timing earlier than the second predetermined condition as the timing at which the next breath can be taken. may be specified.

For example, in the above example, the specifying unit 300 determines the range of the second predetermined condition (10 seconds to 15 seconds) together with the utterance end timing TE _r (52,500 msec) of the note N _r determined to satisfy the second predetermined condition. second) is identified as the _timing at which the next _breath can be taken.

According to such a configuration, it is possible to present an appropriate timing for taking a breath, assuming that there is a difference due to the singing ability of the singer.

<Modification 1>
The extracting unit 100 may extract the timing at which a breath can be taken in the music based on the reference data of the music and the lyric data of the music.

First, the extraction unit 100 extracts the utterance end timing of the note that satisfies the first predetermined condition by executing the processing described in the embodiment. Next, the extracting unit 100 narrows down the timings at which the user can take a breath in the music based on the lyric data from among the extracted utterance end timings of the notes.

Specifically, the extracting unit 100 analyzes the lyrics corresponding to the lyrics data using a known technique (for example, JP-A-2004-070634) and identifies clauses into which commas can be inserted. The extraction unit 100 extracts, from among the utterance end timings of the notes that satisfy the first predetermined condition, the timing that matches the timing at which the last character of the specified phrase is displayed as the timing at which the user can take a breath in the music.

Even in general conversational sentences, there is a break between the end of the utterance of the last character contained in a phrase in which commas can be inserted and the beginning of the utterance of the first character contained in the next phrase, so you can catch your breath. many. In other words, the period from the end of the utterance timing of the note corresponding to the last character included in the phrase in which the comma can be inserted to the utterance start timing of the note corresponding to the first character included in the next phrase is naturally audible breathing. is possible. Therefore, the timing extracted based on the lyric data together with the reference data of the music is the timing at which it is easier for the singer to take a breath and the breath can be heard naturally.

In the above example, the lyrics corresponding to the lyrics data are analyzed to specify the phrases in which the commas can be inserted. In this case, the extracting unit 100 narrows down the timings at which a breath can be taken in the music based on the timing of the reading points included in the lyrics data.

As is clear from the above, in the karaoke machine K according to this modified example, the extracting unit 100 extracts the timing at which it is possible to take a breath in a piece of music, based on the lyric data of the piece of music. According to such a karaoke machine K, it is possible to present the singer with a more suitable timing for taking a breath.

<Modification 2>
The breath information detected by the detection unit 200 may include the timing of the singer's breath and the length of the breath performed by the singer.

For example, the detection unit 200 analyzes the frequency characteristics of the audio signal corresponding to the singing voice of the singer input through the microphone 40 using a known technique. If the detection unit 200 determines, based on the analysis result, that an audio signal due to exhalation (audio signal corresponding to overtone components) is not included and an audio signal corresponding to inhalation noise peculiar to breathing is included, The time when the singing voice corresponding to the voice signal is input is detected as the timing of the singer's breathing. At this time, the detection unit 200 obtains the duration in which the sound signal corresponding to the inhalation noise peculiar to breathing is included, and detects the duration as the length of the breath performed by the singer.

In addition, the detection unit 200 analyzes the video signal obtained by photographing the singer by the photographing means 60 by a known method. If the detection unit 200 determines, based on the analysis result, that a movement peculiar to breathing (for example, vertical movement of the shoulder or head, opening and closing of the mouth) is included, the time when the movement was captured is recorded by the singer. It is detected as the timing of breathing performed by At this time, the detection unit 200 obtains the duration of the movement peculiar to breathing, and detects the duration as the length of the breath performed by the singer.

Alternatively, the detection unit 200 compares the length of the breath performed by the singer detected based on the audio signal and the length of the breath performed by the singer detected based on the video signal, and compares the length of the breath performed by the singer detected based on the video signal. may be detected as the length of the breath taken by the singer. In addition, the detection unit 200 compares the length of the breath taken by the singer detected based on the audio signal and the length of the breath taken by the singer detected based on the video signal, and compares the length of the breath taken by the singer detected based on the video signal. may be detected as the length of the breath taken by

Here, in this modified example, a plurality of second predetermined conditions referred to by the specifying unit 300 are set according to the length of the breath performed by the singer. If the length of the breath performed by the singer is short, it is assumed that the time during which there is a high possibility that the breath will not continue (the time during which karaoke can be sung without taking a breath) will also be shortened. On the other hand, if the length of the breath performed by the singer is long, it is assumed that the time during which there is a high possibility that the breath will not be continued (the time during which karaoke can be sung without taking a breath) will also increase. Therefore, it is preferable that the second predetermined condition includes a plurality of patterns corresponding to the length of breath.

For example, the second predetermined condition is 10 seconds or more and less than 15 seconds when the length of breath is less than 500 msec, 11 seconds or more and less than 16 seconds when the length of breath is 500 msec or more and less than 750 msec, and the length of breath is If it is 750 msec or more and less than 1,000 msec, it is 12 seconds or more and less than 17 seconds, and if the breath length is 1,000 msec or more, it is 13 seconds or more and less than 18 seconds.

In addition, as described in the first embodiment, the specifying unit 300, in order from the vocalization end timing TE _o (42,000 msec) of the note _No , the breath timing BT (40,000 msec) performed by the singer S, and to determine whether the second predetermined condition is satisfied.

The time difference between the timing BT (40,000 msec) and the utterance end timing _{TE o (} 42,000 msec) of note No is 2,000 msec. Therefore, the identifying unit 300 determines that the second predetermined condition is not satisfied regardless of the length of the breath. Similarly, the time difference between the timing BT (40,000 msec) and the utterance end timing TE _p (46,500 _msec ) of note N _p is 6,500 msec. The time difference from the utterance end timing TE _q (49,000 msec) is 9,000 msec. Therefore, the identifying unit 300 determines that the second predetermined condition is not satisfied regardless of the length of the breath.

On the other hand, the time difference between the timing BT (40,000 msec) and the utterance end timing TE _r (52,500 msec) of note N _r is 12,500 msec. Therefore, the specifying unit 300 sets the second predetermined condition when the length of breath is less than 500 msec, when the length of breath is 500 msec or more and less than 750 msec, and when the length of breath is 750 msec or more and less than 1,000 msec. It is determined that the condition is satisfied, and if the breath length is 1,000 msec or more, it is determined that the second condition is not satisfied.

Also, the time difference between the timing BT (40,000 msec) and the utterance end timing TE _s (55,500 msec) of the note N _s is 15,500 msec. Therefore, the identification unit 300 determines that the second predetermined condition is not satisfied when the length of the breath is less than 500 msec, and determines that the length of the breath is 750 msec or more1, when the length of the breath is 500 msec or more and less than 750 msec. If it is less than 000 msec and if the breath length is 1,000 msec or more, it is determined that the second condition is satisfied.

Furthermore, the time difference between the timing BT (40,000 msec) and the utterance end timing TE _t (61,500 msec) of the note N _t is 21,500 msec. Therefore, the identifying unit 300 determines that the second predetermined condition is not satisfied regardless of the length of the breath. Since it is clear that the second predetermined condition is not satisfied at the utterance end timing after this regardless of the length of the breath, the specifying unit 300 ends the processing.

In this way, the detection unit 200 according to this modification can detect breath information including the length of the breath performed by the singer. By considering the length of the breath taken by the singer when specifying the timing at which the next breath can be taken, it is possible to present the singer with a more suitable timing for taking a breath.

<Others>
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 scope and spirit of the invention, as well as the scope of the invention described in the claims and equivalents thereof.

100 extraction unit 200 detection unit 300 identification unit 400 presentation unit K karaoke device

Claims (4)

an extraction unit that extracts a timing at which a breath can be taken in the song based on the reference data of the song;
Based on the audio signal corresponding to the singing voice of the singer who sings karaoke of the song and / or the video signal obtained by shooting the singer, breath information including the timing of the breath performed by the singer a detection unit that detects
a specifying unit that specifies the timing at which the singer can take a next breath based on the extracted timing at which the song can take a breath and the detected breath information;
a presentation unit that presents the specified timing at which the next breath can be taken to the singer;
A karaoke device having 2. The karaoke apparatus according to claim 1, wherein the presentation unit displays the identified timing at which the next breath can be taken in correspondence with the display of the lyrics of the music piece. 3. The karaoke apparatus according to claim 1, wherein the extraction unit extracts a timing at which the user can take a breath in the music based on lyric data of the music. 4. The karaoke apparatus according to any one of claims 1 to 3, wherein the detection unit detects the breath information including the length of the breath performed by the singer.

Images