JPH11282477A - Music playing device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To share a generally used voice input means for voice recognition and for singing. SOLUTION: A control part 7 identifies the operation modes of plural stages such as the inter-song mode of not reproducing music data and an introduction mode relating to the time of reproduction, etc., and switches the output destination of voice signals inputted from a microphone to a microphone signal switching part 3 to one of a mixer part 6 and a voice recognition part 8 corresponding to the identified operation mode.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

The present invention relates to a karaoke apparatus,
The present invention relates to a music performance device such as a communication karaoke device.

[0002]

2. Description of the Related Art In recent years, as an input means of a computer which does not use an input device such as a keyboard or a mouse, it is general to use a voice recognition technique to input various operation instructions by voice. If an input means using voice recognition technology is adopted in a music performance device such as a karaoke device for reproducing music, a communication karaoke device, etc., operations such as selection of karaoke songs can be easily performed, and a user interface of a user can be improved. it can.

Therefore, a karaoke apparatus conventionally provided with a microphone for singing and a microphone for selecting music, and recognizing a requested music from voice input from the microphone for music selection (for example, see Japanese Patent Application Laid-Open No. Hei 6-161482). ) And a dedicated microphone provided with a switch for switching between the voice recognition function mode and the karaoke function mode, and recognizes the requested song or volume adjustment by the collected voice after switching to the voice recognition function mode. A karaoke apparatus (for example, see Japanese Patent Application Laid-Open No. 6-89096) has been proposed.

[0004]

However, the above-mentioned karaoke apparatus has a problem that the user needs to change the microphone between singing and selecting a tune, which is inconvenient. Also, in the latter karaoke apparatus, a dedicated microphone provided with a switch for switching between the voice recognition function mode and the karaoke function mode is required, and in many cases, a preferred one from among different sound qualities is used for each microphone. People could not use their favorite microphones. In particular, since a general wireless microphone cannot be used, it is inconvenient when singing karaoke.

[0005] Furthermore, the instruction content by voice input includes, in addition to music selection, command control instructions such as volume adjustment and tempo adjustment. There was also a problem of causing a decrease.

The present invention has been made in view of the above points, and has as its object to enable commonly used voice input means to be shared for voice recognition and singing. It is another object of the present invention to improve the accuracy of recognizing the contents of an instruction given by a voice from a user.

[0007]

In order to achieve the above object, the present invention provides a music reproducing means for reproducing a music signal based on music data, a voice input means for inputting an audio signal, and the music reproducing means. Music / speech output means for outputting the music of the reproduced music signal together with the sound of the sound signal input by the sound input means; and a sound instruction content based on the sound signal input by the sound input means. Speech recognition means for recognizing, means for executing processing corresponding to the instruction content recognized by the means, and operation mode identification means for identifying a plurality of stages of operation modes when the music data is not reproduced and when the music data is reproduced And the output destination of the audio signal input by the audio input means in accordance with the operation mode identified by the means. Providing music performance apparatus having a sound output destination switching means for switching to either the voice output unit and the voice recognition means.

Further, it is more preferable to provide a means for outputting information notifying the output destination of the audio signal by the audio output destination switching means.

Also, a music reproducing means for reproducing a music signal based on music data, a voice input means for inputting an audio signal, a music based on the music signal reproduced by the music reproducing means, and a music input by the voice input means. Music / speech output means for outputting the combined speech with the speech signal, speech recognition dictionary storage means for storing a plurality of types of speech recognition dictionaries, and the respective speech recognition dictionaries stored in the means. Voice recognition means for recognizing a voice instruction content based on a voice signal input by the voice input means,
Means for executing a process corresponding to the instruction content recognized by the means, operation mode identification means for identifying a plurality of stages of operation modes when the music data is not reproduced and when the music data is reproduced, and operation mode identification means for identifying the music data. The music performance device may include a voice recognition dictionary switching unit that switches the type of the voice recognition dictionary in the voice recognition dictionary storage unit referred to by the voice recognition unit according to the operation mode.

Further, it is more preferable to provide a means for outputting information notifying the type of the speech recognition dictionary switched by the speech recognition dictionary switching means.

[0011] Also, a music reproducing means for reproducing a music signal based on music data, a voice input means for inputting an audio signal, a music based on the music signal reproduced by the music reproducing means, and a music input by the voice input means Music / speech output means for outputting the combined speech with the speech signal, speech recognition dictionary storage means for storing a plurality of types of speech recognition dictionaries, and the respective speech recognition dictionaries stored in the means. Voice recognition means for recognizing a voice instruction content based on a voice signal input by the voice input means,
Means for executing a process corresponding to the instruction content recognized by the means, operation mode identification means for identifying a plurality of stages of operation modes involved when the music data is not reproduced and when the music data is reproduced, and operation mode identification means for identifying the music data. Voice output destination switching means for switching an output destination of a voice signal input by the voice input means to one of the music / voice output means and voice recognition means in accordance with the operation mode, and the operation mode identification means. The music performance device may include a voice recognition dictionary switching unit that switches the type of the voice recognition dictionary in the voice recognition dictionary storage unit referred to by the voice recognition unit according to the operation mode.

Further, a means for outputting information notifying the output destination of the voice signal by the voice output destination switching means and information notifying the type of the voice recognition dictionary switched by the voice recognition dictionary switching means is provided. Good.

According to a first aspect of the present invention, there is provided a music performance device for identifying various operation modes such as inter-music, prelude, mid-music, middle and last, and voice input means according to the operation mode. The output destination of the audio signal input from the device is switched to either the voice recognition means or the music / voice output means, so that when music such as karaoke is not being reproduced, and when the prelude, middle, and subsequent performances are selected, the volume and volume are selected. , A tempo, etc., and a singing voice can be input during a music song.

Therefore, a general microphone can be used as a voice input means for voice recognition and singing, and the user can select a tune, sing and adjust the volume and tempo during singing by complicated procedures such as changing microphones. It can be performed without performing work, and a comfortable singing environment can be obtained.

Further, the music performance device according to the second aspect of the present invention displays information indicating whether the output destination of the audio signal is the music / speech output means or the speech recognition means. It is possible to easily determine when a voice input for an instruction to adjust a tune, a volume, a tempo, etc. is possible from the input means and when a singing voice is input. Therefore, the user can adjust the volume and tempo between the song selection, the singing, and the singing with good timing, and can enjoy the singing more.

Further, the music performance apparatus according to a third aspect of the present invention distinguishes between various operation modes such as inter-music, prelude, mid-course, middle, and subsequent, and outputs sound according to the operation mode. Since the type of voice recognition dictionary to be referred to by the recognition means is switched, it is necessary to recognize the song name and song number for song selection in order to recognize between songs that are likely to be requested and voice input during the subsequent performance It is necessary to recognize the control commands for adjusting the volume and tempo for recognizing voices input during preludes and middle plays that are likely to be adjusted in volume and tempo by referring to a dictionary for song title recognition It is possible to refer to a dictionary for recognizing various control commands. Therefore, the recognition accuracy can be improved by narrowing down to the recognition of the instruction content that is most likely to be performed for each operation mode.

Further, the music performance apparatus according to the fourth aspect of the present invention displays information as to which type of dictionary is used for voice recognition. It is possible to determine which of the instructions is appropriate. For example, the user can be caused to select a music when the music is not being reproduced and at the time of the subsequent performance during the reproduction, and to adjust the volume and the tempo at the time of the middle performance from the start to the end of the reproduction. Therefore, the instruction operation intended by the user can be reliably performed, and a more comfortable singing environment can be provided for the user.

Further, the music performance apparatus according to a fifth aspect of the present invention identifies various operation modes such as inter-music, prelude, mid-music, middle and last, and outputs sound according to the operation mode. Since the output destination of the voice signal input from the input means is switched to either the voice recognition means or the music / voice output means, and the type of the voice recognition dictionary referred to by the voice recognition means is switched according to the operation mode, Recognition of the selected song, etc., from the voice input during karaoke or other music not played and during the subsequent performance, and instructions for adjusting the volume, tempo, etc. based on the voice input during the prelude and the middle during playback. , And the voice input during the song can be output as singing voice along with the music.

Therefore, the user can easily give an instruction such as selection of a song by singing and voice, adjustment of a volume and a tempo by one voice input means, and the content of the instruction by the voice can be surely executed.

According to a sixth aspect of the present invention, there is provided a music performance apparatus, wherein the type of dictionary used for voice recognition is determined along with information indicating whether the output destination of the voice signal is music / voice output means or voice recognition means. Since it displays information about which one is
It is possible to make the user determine whether it is appropriate to perform a singing, a song selection, or an instruction to adjust the volume or the tempo. Therefore, the user can enjoy singing without having to spend time singing, selecting songs, adjusting volume and tempo.

[0021]

Embodiments of the present invention will be specifically described below with reference to the drawings. FIG. 1 is a block diagram showing a configuration of a karaoke apparatus according to an embodiment of the present invention.

This karaoke apparatus is realized by a microcomputer including a CPU, a ROM, a RAM, and the like, and includes a microphone 1, a microphone amplifier 2, a microphone signal switching unit 3, a karaoke reproducing unit 4, a karaoke music data storage unit 5, a mixer. It comprises a unit 6, a control unit 7, a voice recognition unit 8, a speaker 9, and a display unit 10.

The microphone 1 is a voice input device for inputting a singing voice and voices for selecting songs, adjusting volume, tempo, and the like. The microphone amplifier unit 2 amplifies the audio signal input from the microphone 1 and outputs the amplified audio signal to the microphone signal switching unit 3.

The microphone signal switching unit 3 performs a switching process for outputting an audio signal input from the microphone 1 to one of the mixer unit 6 and the audio recognition unit 8 based on an output destination switching signal from the control unit 7. Do. The karaoke playback unit 4 refers to music data (also referred to as “song data”) of the song requested from the karaoke song data storage unit 5 and outputs a music signal reproduced from the music data to the mixer unit 6. And the like.

The karaoke song data storage unit 5 is a storage device such as a hard disk which stores music data (for example, MIDI data) of various types of karaoke songs. Information for identifying the mode is added. The mixer unit 6
The music signal received from the karaoke reproducing unit 4 and the audio signal received from the microphone signal switching unit 3 are combined and output to the speaker 9.

The control unit 7 controls the entire karaoke apparatus. The operation mode when the karaoke music is not reproduced and the karaoke music data storage unit 5 reproduced by the karaoke reproduction unit 4 when the karaoke music is reproduced. The music data is referred to, the operation mode of each stage is identified based on information for identifying each operation mode in the music data, and the microphone input signal is output to the microphone signal switching unit 3 according to each operation mode. A process of outputting a destination switching signal, a command control process of a music selection corresponding to the recognition result received from the voice recognition unit 8 and a process of adjusting a volume and a tempo, and an output destination of the voice input from the microphone 1 is the speaker 9 or the voice. A process of displaying a message notifying the recognition unit 8 is also executed.

The voice recognizing unit 8 recognizes the content of the command of the music name, volume and tempo selected based on the dictionary registered in advance, based on the voice signal received from the microphone signal switching unit 3. And outputs the recognition result to the control unit 7. The speaker 9 outputs the singing voice together with the karaoke music so as to be audible. The display unit 10
LC that displays various information such as various operation guidance when using karaoke and a message indicating that the output destination of the voice input from the microphone 1 is the speaker 9 or the voice recognition unit 8
A display device such as a D or CRT.

That is, the karaoke reproducing section 4 functions as a music reproducing means for reproducing a music signal based on music data, the microphone 1 functions as a sound input means for inputting a sound signal, and the mixer section 6 And speaker 9
Functions as a music / speech output unit that outputs the music based on the music signal reproduced by the karaoke reproducing unit 4 and the sound based on the audio signal input by the microphone 1 together.

The voice recognition section 8 functions as voice recognition means for recognizing voice instructions based on a voice signal input by the microphone 1, and the control section 7 controls the voice content recognized by the voice recognition section 8. And a function of an operation mode identifying means for identifying a plurality of stages of operation modes involved when the music data is not reproduced and when the music data is reproduced.

Further, the microphone signal switching unit 3 determines whether the output destination of the audio signal input by the microphone 1 according to the operation mode identified by the control unit 7 is any one of the mixer unit 6, the speaker 9, and the voice recognition unit 8. The function of the audio output destination switching means for switching between the crab and the crab is performed. Then, the display unit 1
0 functions as a means for outputting information notifying the output destination of the audio signal by the microphone signal switching unit 3.

Next, processing in the karaoke apparatus will be described. First, at the time of reproducing the karaoke music, there are a plurality of stages of operation modes such as inter-song, prelude, mid-song, middle, and after. The inter-song mode is when karaoke music is not being played. Prelude mode prepares for playback of karaoke music, starts playback, and starts singing the first lyrics (intro)
Up to. In song mode, the karaoke singing part (for example,
No. 1 and No. 2). The middle performance mode is a portion of the music that is not sung (for example, between No. 1 and No. 2). In the after-play mode, the singing of lyrics ends and the playback of karaoke music is input.

In the karaoke apparatus, music data (karaoke music data) stored in the karaoke music data storage unit 5 in advance.
The timing data for identifying each of the above operation modes is added to each of the sections. The locations to which the timing data is added are, for example, the first song singing location, the first song ending location, the second song singing start location, the second song ending location, and the like.

When the karaoke music data is not being reproduced, the control section 7 judges that the music mode is the music mode. When the karaoke music data is reproduced, the control section 7 performs the prelude mode, the music mode, and the music reproduction mode based on the timing data in the karaoke music data. Middle mode,
And the trailing mode can be identified.

In the karaoke apparatus, when the audio signal input from the microphone 1 is amplified by the microphone amplifier unit 2, the amplified audio signal is transmitted to the microphone signal switching unit 3. The microphone signal switching unit 3 sends an output destination from the control unit 7 to the mixer unit 6.
When the output destination switching signal for switching to the audio amplifier is received, the audio signal received from the microphone amplifier unit 2 is output to the mixer unit 6 via the signal line a, and the output destination switching signal for switching the output destination to the audio recognition unit 8 is received. The voice signal received from the microphone amplifier unit 2 is output to the voice recognition unit 8 via the signal line b.

On the other hand, the karaoke reproducing section 4 refers to the karaoke music data stored in the karaoke music data storage section 5 selected by the control section 7, reproduces the music signal of the karaoke music based on the karaoke music data, and sends it to the mixer section 6. The mixer unit 6 combines (mixes) the music signal received from the karaoke reproducing unit 4 and the audio signal received from the microphone signal switching unit 3 and outputs the combined signal to the speaker 9.

The voice recognition unit 8 recognizes a song name or number selected from a voice signal received from the microphone signal switching unit 3 or a command control for adjusting volume, tempo, etc., based on a dictionary registered in advance. The recognition result is sent to the control unit 7
The control unit 7 adjusts the music selection, volume, tempo, and the like based on the recognition result received from the voice recognition unit 8, and displays a message on the display unit 10 informing the output destination of the voice signal.

Further description will be given. In the inter-song mode, the control unit 7 switches the output destination of the microphone signal switching unit 3 to the voice recognition unit 8 and outputs the voice signal from the microphone 1 to the voice recognition unit 8. When the voice recognition section 8 recognizes the song title of the request from the voice signal, it outputs the song title to the control section 7, and the control section 7 causes the karaoke playback section 4 to play the corresponding karaoke song data in the karaoke song data storage section 5. .

When the karaoke reproducing section 4 reproduces the karaoke music, the control section 7 recognizes the timing of the end of the prelude mode based on the timing data of the karaoke music data, and changes the output destination of the microphone signal switching section 3 to the mixer section. 6 and the audio signal from the microphone 1 is
Output to Accordingly, the music signal of the karaoke music and the audio signal of the singing voice are mixed by the mixer section 6 and output from the speaker 9.

When the control unit 7 recognizes the timing at which the karaoke music is finished and the karaoke music is in the middle mode, the control unit 7 switches the output destination of the microphone signal switching unit 3 to the voice recognition unit 8 again, and The voice signal is output to the voice recognition unit 8. When the voice recognition unit 8 recognizes the command control for the adjustment such as “volume up” or “tempo down” from the voice signal, the command control is output to the control unit 7, and the control unit 7 outputs the karaoke playback unit 4 and the mixer unit. 6 is executed for various adjustment commands.

Further, when the control unit 7 recognizes the start timing of the second after the middle mode ends, the control unit 7 switches the output destination of the microphone signal switching unit 3 to the mixer unit 6 again, and
Is output to the mixer unit 6. Accordingly, the music signal of the karaoke music and the audio signal of the singing voice are mixed by the mixer section 6 and output from the speaker 9.

Further, when the control unit 7 recognizes the timing at which the karaoke music enters the after-play mode, it switches the output destination of the microphone signal switching unit 3 to the voice recognition unit 8 again, and recognizes the voice signal from the microphone 1 by voice recognition. Output to the unit 8. When the voice recognition unit 8 recognizes the song title of the request from the audio signal, it outputs the song title to the control unit 7, and the control unit 7 causes the karaoke playback unit 4 to play the corresponding karaoke song data in the karaoke song data storage unit 5. .

When the control unit 7 switches the output destination of the audio signal to the audio recognition unit 8, the display unit 10 displays a message such as "You can select music with a microphone", "You can adjust the volume and tempo with a microphone". Is displayed, and when the output destination is switched to the mixer section 6, a message such as "You can sing with a microphone" is displayed on the display section 10.

In this way, singing of karaoke and selection of karaoke and adjustment of volume, tempo, keys, etc. can be easily performed without complicated switching operation with a general microphone, thereby improving the singing environment of the user. Can be done.

Next, another embodiment of the present invention will be described. Generally, in speech recognition, the smaller the number of recognition targets, the higher the recognition accuracy. When the karaoke apparatus is controlled, it can be roughly divided into music selection and command operation. In the case of song selection, the recognition target by voice is a song name or a song number, and in the case of command control, the recognition target by voice is control of volume adjustment, tempo control, and key control.

In general, song selection is often performed in the inter-song mode, and command operation is often performed in the prelude mode after the song selection. Therefore, in the karaoke apparatus, the dictionary used for voice recognition in the inter-song mode is designated by the song name (or song name). number)
If the dictionary used for voice recognition in the prelude mode is switched to the command control dictionary, recognition targets can be narrowed and recognition accuracy can be improved. Therefore, a karaoke apparatus for switching a dictionary used for voice recognition according to an operation mode is provided.

FIG. 2 is a diagram showing a configuration of a karaoke apparatus for switching a dictionary used for speech recognition according to an operation mode according to another embodiment of the present invention. And description thereof is omitted.

This karaoke apparatus is provided with a dictionary switching section 11 and a dictionary storage section 12 in addition to the functional sections of the karaoke apparatus shown in FIG. The dictionary switching unit 11 includes the control unit 7
The speech recognition unit 8 performs a process of switching the dictionary of the dictionary storage unit 12 to be referred to at the time of speech recognition, based on the dictionary switching signal from. The dictionary storage unit 12 includes a song name dictionary 13 for recognizing the requested song referenced by the voice recognition unit 8 and a command dictionary 14 for recognizing the contents of the command control for adjusting the volume, tempo, key and the like.

That is, the dictionary storage unit 12 corresponds to a voice recognition dictionary storage unit storing a plurality of types of voice recognition dictionaries, and the voice recognition unit 8 corresponds to each of the voice recognition dictionaries stored in the dictionary storage unit 12. And performs the function of voice recognition means for recognizing the content of a voice instruction based on the voice signal input by the microphone 1 with reference to FIG. Further, the dictionary switching unit 11 functions as a voice recognition dictionary switching unit that switches the type of the voice recognition dictionary in the dictionary storage unit 12 referred to by the voice recognition unit 8 according to the operation mode identified by the control unit 7. .

Further, the control section 7 and the display section 10 function as a means for outputting information notifying the type of the speech recognition dictionary switched by the dictionary switching section 11. Furthermore, the control unit 7 and the display unit 10 output information for notifying the output destination of the audio signal by the microphone signal switching unit 3 and information for notifying the type of the voice recognition dictionary switched by the dictionary switching unit 11. Also performs the function of

Next, processing in the karaoke apparatus will be described. In this karaoke device, the control unit 7
As described above, the output destination of the voice signal is switched, and a dictionary switching signal is output to the dictionary switching unit 11 via the signal line d according to each operation mode, and the dictionary which the voice recognition unit 8 refers to at the time of voice recognition. The song dictionary 13 and the command dictionary 14 in the storage unit 12 are switched.

Further description will be given. In the inter-song mode, the control unit 7 switches the output destination of the microphone signal switching unit 3 to the voice recognition unit 8, outputs the voice signal from the microphone 1 to the voice recognition unit 8, and causes the dictionary switching unit 11 to output the voice recognition unit. 8 is switched so as to refer to the song name dictionary 13. When the voice recognition unit 8 recognizes the requested song name from the audio signal with reference to the song name dictionary 13, it outputs the song name to the control unit 7, and the control unit 7 sends the karaoke song data storage unit 5 to the karaoke playback unit 4.
The karaoke song data corresponding to is reproduced. Thus,
In the inter-song mode in which voice input is frequently performed for song selection, a dictionary for recognizing song titles can be used to improve song title recognition accuracy.

When the karaoke reproducing section 4 reproduces the karaoke music, the control section 7 recognizes the prelude mode based on the timing data of the karaoke tune data, and the voice recognition section 8 refers to the command dictionary 14 to the dictionary switching section 11. When the voice recognition unit 8 recognizes the command control content for adjusting the volume, tempo, key and the like from the voice signal with reference to the command dictionary 14, the voice recognition unit 8 outputs the command control content to the control unit 7, The control unit 7 executes a command control for the karaoke reproducing unit 4 and the mixer unit 6 at the time of reproducing the karaoke music data.

Thus, in the prelude mode in which voice input for command control is frequently performed, the recognition accuracy of command control can be improved by using a dictionary for recognizing the contents of command control.

When the karaoke reproducing section 4 reproduces the karaoke music, the control section 7 recognizes the timing of the end of the prelude mode based on the timing data of the karaoke music data, and changes the output destination of the microphone signal switching section 3 to the mixer section. 6 and the audio signal from the microphone 1 is
Output to Accordingly, the music signal of the karaoke music and the audio signal of the singing voice are mixed by the mixer section 6 and output from the speaker 9.

When the control unit 7 recognizes the timing at which the karaoke music number 1 ends and the mode changes to the middle mode, the control unit 7 switches the output destination of the microphone signal switching unit 3 to the voice recognition unit 8 again, and The voice signal is output to the voice recognition unit 8. When the voice recognition unit 8 recognizes the command control for the adjustment such as “volume up” or “tempo down” from the voice signal with reference to the command dictionary 14, the command recognition is performed by the control unit 7.
The control unit 7 executes command control for various adjustments to the karaoke reproducing unit 4 and the mixer unit 6.

As described above, even in the intermediate mode where the voice for command control is frequently input together with the prelude mode, the recognition accuracy of the command control can be improved by using the dictionary for recognizing the contents of the command control. it can.

Further, when the control section 7 recognizes the timing of the start of the second after the end of the middle mode, the control section 7 switches the output destination of the microphone signal switching section 3 to the mixer section 6 again, and
Is output to the mixer unit 6. Accordingly, the music signal of the karaoke music and the audio signal of the singing voice are mixed by the mixer section 6 and output from the speaker 9.

Further, when the control unit 7 recognizes the timing at which the karaoke music enters the after-play mode, the output destination of the microphone signal switching unit 3 is switched to the voice recognition unit 8 again, and the voice signal from the microphone 1 is recognized by voice. In addition to the output to the section 8, the dictionary switching section 11 switches the voice recognition section 8 to refer to the song name dictionary 13. When the voice recognizing unit 8 recognizes the song title of the request from the audio signal using the song title dictionary 13, it outputs the song title to the control unit 7, and the control unit 7 corresponds to the karaoke song data storage unit 5 to the karaoke playback unit 4. Play karaoke song data.

Thus, in the after-play mode in which voice input for command control is frequently performed together with the inter-song mode, a dictionary for recognizing the title of the requested song can be used to improve the recognition accuracy of the song selection. When the dictionary is switched in this manner, a microphone for voice recognition different from a microphone for singing can be used.

When the dictionary used for voice signal recognition is switched to the song name dictionary 13, the control unit 7 displays “You can select a song with a microphone” on the display unit 10, and when it switches to the command dictionary 14, A message such as “You can adjust the volume and tempo with a microphone” is displayed on the display unit 10.

In this manner, the music selection and the sound volume by voice,
Since the accuracy of recognizing the adjustment of the tempo, the key, and the like can be improved, the content instructed by the user by voice can be reliably executed, and the operation instructed by the erroneous recognition is not performed, or the user is not performed. It is possible to prevent a singing environment in which an operation different from the intended operation is performed from being deteriorated, and to provide a more comfortable singing environment.

Although the karaoke apparatus has been described in the above embodiment, a communication karaoke apparatus that can receive karaoke music data and various services from a center apparatus via a public line, and a personal computer that can reproduce karaoke music data And the like can be implemented in the same manner as described above.

[0063]

As described above, according to the music performance apparatus of the present invention, the commonly used voice input means can be shared for voice recognition and singing. Further, it is possible to improve the accuracy of recognizing the instruction content by voice from the user.

[Brief description of the drawings]

FIG. 1 is a block diagram showing a configuration of a karaoke apparatus according to an embodiment of the present invention.

FIG. 2 is a block diagram showing a configuration of a karaoke apparatus according to another embodiment of the present invention.

[Explanation of symbols]

 1: microphone 2: microphone amplifier section 3: microphone signal switching section 4: karaoke playback section 5: karaoke song data storage section 6: mixer section 7: control section 8: voice recognition section 9: speaker 10: display section 11: dictionary switching Part 12: Dictionary storage part 13: Song name dictionary 14: Command dictionary

Claims (6)

[Claims] 1. A music reproducing means for reproducing a music signal based on music data, a voice input means for inputting an audio signal, a music based on the music signal reproduced by the music reproducing means, and a music input by the voice input means. Music / speech output means for outputting the combined speech with the speech signal, speech recognition means for recognizing the speech instruction content based on the speech signal input by the speech input means, and the instruction content recognized by the means Means for executing processing corresponding to the above, operation mode identification means for identifying a plurality of stages of operation modes involved when the music data is not being reproduced and when the music data is being reproduced, and the sound corresponding to the operation mode identified by the means. Voice output for switching the output destination of the voice signal input by the input means to one of the music / voice output means and voice recognition means A music performance device comprising: a first switching means. 2. The music performance apparatus according to claim 1, further comprising means for outputting information indicating an output destination of the audio signal by said audio output destination switching means. 3. A music reproducing means for reproducing a music signal based on music data, a voice input means for inputting an audio signal, and music input by the music signal reproduced by the music reproducing means and input by the voice input means. Music / speech output means for outputting the combined speech with the speech signal, speech recognition dictionary storage means for storing a plurality of types of speech recognition dictionaries, and speech recognition dictionaries stored in the means. Voice recognition means for recognizing a voice instruction content based on a voice signal input by the voice input means, means for executing processing corresponding to the content of the instruction recognized by the voice input means, and reproducing the music data. Operation mode identification means for identifying a plurality of stages of operation modes involved in the absence and reproduction, and the voice recognition means according to the operation mode identified by the means. A voice recognition dictionary switching means for switching a type of a voice recognition dictionary in the voice recognition dictionary storage means referred to by a row. 4. The music performance apparatus according to claim 3, further comprising means for outputting information for notifying the type of the voice recognition dictionary switched by said voice recognition dictionary switching means. 5. A music reproducing means for reproducing a music signal based on music data, a voice input means for inputting an audio signal, and music input by the music signal reproduced by the music reproducing means and input by the voice input means. Music / speech output means for outputting the combined speech with the speech signal, speech recognition dictionary storage means for storing a plurality of types of speech recognition dictionaries, and speech recognition dictionaries stored in the means. Voice recognition means for recognizing a voice instruction content based on a voice signal input by the voice input means, means for executing processing corresponding to the content of the instruction recognized by the voice input means, and reproducing the music data. Operation mode identification means for identifying a plurality of stages of operation modes involved in the absence and reproduction of the voice input means; and the voice input means according to the operation mode identified by the means. Voice output destination switching means for switching the output destination of a voice signal input by a stage to one of the music / voice output means and voice recognition means; and the voice recognition in accordance with the operation mode identified by the operation mode identification means. And a voice recognition dictionary switching means for switching a type of the voice recognition dictionary in the voice recognition dictionary storage means referred to by the means. 6. The music performance device according to claim 5, wherein information for notifying an output destination of the audio signal by the audio output destination switching means and a type of the voice recognition dictionary switched by the voice recognition dictionary switching means are notified. A music performance device comprising means for outputting information.