JP4269973B2 - Car audio system - Google Patents

Description

  The present invention relates to a car audio system that is mounted on a vehicle and reproduces music recorded on, for example, an HDD or a DVD.

For example, in a car navigation device, in order to improve user convenience and safety, a voice recognition device is incorporated to input a destination or a command such as switching the scale of a displayed map. There is something that can be done even by voice. This is equipped with a microphone that captures a voice signal, and is configured so that a user speaks a place name or the like as a destination, processes a voice input signal from the microphone, and performs voice recognition. At this time, generally, in order to confirm that speech recognition has been performed, talkback is performed using synthesized speech based on the speech recognition result (see, for example, Patent Document 1).
JP 2000-322098 A

  By the way, in recent years, it has been considered that a car audio device mounted on a car and reproducing music can enjoy music stored in large quantities on an HDD, a DVD, or the like. Even in such a car audio device, for the purpose of improving the convenience and safety of the user, it is considered to use voice recognition for designating song names, album names, artist names, etc., and for inputting commands. It is done.

  However, in the conventional apparatus, since the audio device cannot be heard from the speaker in the talkback section, as shown in the time chart of FIG. 9, the talkback is performed after the voice recognition, and then the music reproduction is started. For this reason, music playback starts after the time T has elapsed from the start of voice input (speech), and the music playback response is delayed. At this time, in the case of a long sentence, the talkback may take from several seconds to about 10 seconds, so that the user feels strongly waiting and feels frustrated.

  The present invention has been made in view of the above circumstances, and an object of the present invention is to enable a user to give an instruction using voice recognition, and to solve the user's inconvenience caused by talkback. To provide the system.

In order to achieve the above object, a car audio system according to the present invention includes an audio unit that reproduces an acoustic signal and outputs it from a speaker, an audio input unit for inputting an instruction to the audio unit by audio, and the audio input unit Voice recognition means for performing voice recognition of the voice signal input from the voice, response control means for controlling the utterance of talkback according to the recognition result of the voice recognition means, and the audio based on the recognition result of the voice recognition means an audio control means for controlling the parts, and an output control means for recognition result is determined based on output from simultaneously the speaker and an acoustic that will be reproduced by the audio part of the speech recognition means and talk-back voice by the response control means , The sound when the talkback sound and the reproduced sound are simultaneously output by the output control means. Characterized in place comprising an adjustment means for adjusting the timing of the output initiation (the invention of claim 1).

According to this, when the user inputs an instruction to the audio unit from the voice input means and the recognition by the voice recognition means is performed, a talkback utterance according to the recognition result is made under the control of the response control means, and The audio control means controls the audio unit based on the recognition result, reproduces the acoustic signal, and outputs it from the speaker. At this time, the output control means, and the talk-back voice due to the response control means, since the sound that will be reproduced by the audio section is determined based on the speech recognition is to be outputted from the speaker at the same time, the sound after the talkback Unlike the case where the output is performed, the start of the sound output can be advanced correspondingly, and the response can be quick. Therefore, even when the talkback takes several seconds to 10 seconds, it can be solved that the user feels frustrated. Moreover, by providing the adjusting means, the start of the output of the sound is delayed if necessary or at the user's preferred timing, in addition to the simultaneous start of the output of the talkback sound and the reproduced sound. It is possible to increase the usefulness.

  More specifically, the output control means can be composed of synthesis means for synthesizing the audio signal of the audio section and the talkback audio signal (invention of claim 2). Alternatively, the output control means may be configured to output talkback sound from at least one of the plurality of speakers of the audio unit and output sound reproduced by the audio unit from the remaining speakers. Invention of 3). In either case, the intended purpose can be achieved with a relatively simple configuration.

At this time, in the present invention, by the adjustment means, the timing of the output initiation of the sound reproduced, delayed from the start of the talkback, and can you to configure to be able to in talkback period (Invention of Claim 4) .

  In addition, it is possible to configure so that at least one of the sound volumes can be set when the output control means outputs the talkback sound and the reproduced sound at the same time (invention of claim 5). According to this, it becomes possible to change the balance between the volume of the talkback sound and the reproduced sound according to the user's preference, and the convenience can be improved.

  By the way, a car navigation apparatus mounted on a vehicle is generally configured so that a voice recognition apparatus is incorporated so that a destination and various commands can be input by voice. Therefore, the car audio system of the present invention can be configured by being incorporated in a car navigation device (invention of claim 6). According to this, the voice input means, the voice recognition means, the response control means, and the like can be shared with the car navigation device, and the configuration can be simplified.

  Further, when configured to be incorporated in a car navigation device, the output control means may be configured to simultaneously output guidance voice of the car navigation device and sound reproduced by the audio unit from a speaker (claim). Item 7). According to this, the sound reproduced by the audio unit can be saved without interruption during the output of the guidance voice of the car navigation device.

  Hereinafter, an embodiment of the present invention will be described with reference to FIGS. In this embodiment, the car audio system mounted on the vehicle (automobile) is configured as an integrated system incorporated in the car navigation device. A specific example is a case where music (music) stored in a large-capacity storage medium (music file) such as HDD or DVD is played and enjoyed by the audio unit.

  FIG. 1 schematically shows the overall configuration of a car audio system 1 according to the present embodiment. The car audio system 1 includes a main body 2, a plurality of, for example, four (or six) speakers 3 (only two are shown for convenience), a microphone (microphone) 4 connected to the main body 2, and an audio unit. 5, a mixer unit 6, a display 7, and the like. Among them, the microphone 4 is used by the user to input various instructions by voice, and functions as a voice input unit. Although not shown, an operation switch unit is also provided for the user to manually operate the car audio system 1 (various settings, etc.).

  The speaker 3 is adapted to output music such as music reproduced by the audio unit 5 and synthesized speech, which will be described later. The audio unit 5 outputs reproduced music data from a main body unit 2 (music operation control unit), which will be described later, to the mixer unit 6 as an analog sound signal for each speaker 3. The mixer unit 6 amplifies the acoustic signal from the audio unit 5 and outputs the amplified signal to each speaker 3 and, as will be described later, synthesizes the acoustic signal and the synthesized voice signal, and outputs control means ( Functioning as a synthesis means). The display 7 is for displaying necessary information to the user.

  The main unit 2 includes a microcomputer, and has a voice recognition unit 8, a recognition dictionary unit 9, a dialogue control unit 10, a dialogue data storage unit 11, and a music search unit 12 depending on the hardware and software configuration. , A music database 13, a display control unit 14, a voice synthesis control unit 15, a music operation control unit 16, a music file 17, and the like. Among them, the music file 17 is composed of a large-capacity storage medium such as an HDD or a DVD, and the user can store a large amount of music from a music CD (album) or the like in advance. In this case, the album edited by the user can be stored with an arbitrary title name (for example, “My Best”).

  The voice recognition unit 8 recognizes a voice input signal input from the microphone 4 and outputs the recognition result to the dialogue control unit 10. At this time, the recognition dictionary unit 9 stores data such as recognition dictionary data, an acoustic model, and a language model, and the recognition processing by the speech recognition unit 8 is performed using these data. It is configured. The user can input a voice name, an album name, an artist name, etc., and input various commands through the microphone 4, and the voice recognition unit 8 recognizes the voice signal.

  The dialogue control unit 10 outputs music designation (search) data to the music search unit 12 from the voice recognition data recognized by the voice recognition unit 8, and outputs a reproduction command to the music operation control unit 16. It has become. At the same time, the dialogue control unit 10 sends the voice synthesis control unit 15 to the speech synthesis control unit 15 based on data such as a dialogue scenario group, dialogue dictionary, and utterance text stored in the dialogue data storage unit 11 as necessary. On the other hand, a response voice (talkback) utterance instruction (output of synthesized text) is performed. The speech synthesis control unit 15 functions as a response control unit and outputs a synthesized sound (talkback speech signal) to the mixer unit 6 based on the synthesized text. Details of the talkback will be described later.

  The music search unit 12 searches for a specified music from the music database 13 based on input data (music search data) from the dialogue control unit 10. At this time, the song database 13 stores a list of song names, album names, artist names, title names arbitrarily given by the user, and the like of the music (songs) stored in the song file 17. The unit 12 searches for music from this database. The music search unit 12 is provided with a search result storage memory 12a.

  When the search is completed (the music to be played is determined), the music search unit 12 outputs the search result to the music operation control unit 16, the display control unit 14, and the dialogue control unit 10. It has become. Note that the music search unit 12 is used when there is no corresponding music, or when the search instruction is ambiguous and the music cannot be determined (for example, when there are a plurality of albums with the specified artist name). This is output to the dialogue control unit 10. At this time, the dialogue control unit 10 instructs the voice synthesis control unit 15 to speak so as to respond to the user.

  The music operation control unit 16 functions as an audio control unit, reads music data in the music file 17 based on a search result from the music search unit 12 and a playback command from the dialog control unit 10, and performs predetermined processing. It is output to the audio unit 5 at timing. Further, the display control unit 14 is instructed to change the display or to give a necessary message. The display control unit 14 controls the display on the display 7 based on the search result from the music search unit 12 and the instruction from the music operation control unit 16.

  Although not shown, the main body 2, the speaker 3, the microphone 4, the display 7, and the like are shared with a car navigation device mounted on the vehicle. At this time, the speaker 3 is disposed on both the left and right sides of the front and rear portions of the passenger compartment, and the microphone 4 picks up the voice of the driver such as the upper portion of the steering column cover and the sun visor on the driver's seat side. It is arranged at an easy position. Moreover, the display 7 is provided in the upper center part etc. of an instrument panel, and the main-body part 2 is unitized and provided in the center console (instrument panel) part.

  Here, the car navigation apparatus will be briefly described. As well known, the car navigation device includes a position detector that detects the position of the vehicle using a GPS system, a map database that stores map data, and a microcomputer, in addition to the common part with the car audio system 1 described above. And a control circuit that performs processing and control related to navigation, an operation switch unit including a remote control device, and the like.

  Thus, the car navigation apparatus realizes a location function for displaying the position of the vehicle on the road map on the screen of the display 7, and searches for and guides an appropriate route to the destination designated by the user. The route guidance function is realized. At this time, the voice recognition function in the main body 2 allows the user to input a command such as designation of the destination and switching the scale of the map displayed on the display 7 by voice input from the microphone 4. Be able to. In addition, the speech synthesis function in the main body 2 allows the speaker 3 to output, for example, talkback when inputting a destination, guidance voice during route guidance, and the like.

  Now, the speech synthesis control unit 15 and the mixer unit 6 will be described with reference to FIG. As shown in FIG. 2, the mixer unit 6 has a function of amplifying an acoustic signal for each speaker 3 input from the audio unit 5 and outputting the amplified signal to each speaker 3. In this case, in one speaker 3, It is configured to have a function of electrically synthesizing the acoustic signal of the audio unit 5 and the talkback audio signal input from the audio synthesis control unit 15. Then, the voice synthesis control unit 15 outputs a talkback voice signal when a voice name such as a song name, album name, or artist name is input to the mixer unit 6 and outputs control information to the mixer unit 6. Thus, the synthesis of the acoustic signal and the talkback audio signal is controlled.

  At this time, as will be described later in the description of the operation, the voice synthesis control unit 15 performs control so that talkback voice and sound (reproduced music) are simultaneously output from the speaker 3 during music reproduction. It has become. In this embodiment, the volume of each speaker 3 is also controlled. During talkback, the volume on the music playback side can be reduced relative to the volume of the talkback sound, or the volume on the music playback side can be reduced. It is possible to control such that the volume starts to decrease and gradually increases. Furthermore, it is also possible to slightly shift the output start timing between talkback sound and music playback (slightly delay the start of music playback with respect to the talkback sound). These can be set by an initial setting by a user, for example.

  Next, the operation of the above configuration will be described with reference to FIGS. As described above, a user (driver) who uses the car audio system 1 can input instructions for selecting music (music) to be reproduced by inputting (speaking) music titles and album names from the microphone 4. It is said that. As a result, the convenience and safety of the user can be improved. The time charts of FIGS. 3 to 7 show the state of the voice input signal from the microphone 4 and the output of the speaker 3 at that time. FIG. 3 is a basic one, and FIGS. Four types are shown.

  That is, as shown in FIG. 3, when the user inputs a voice (speech) such as a song name or album name, voice recognition by the voice recognition unit 8 is performed. Then, after a time T1 from the start of the utterance, a talkback voice (music name or artist name) for confirmation of voice recognition generated by the dialogue control unit 10 and the voice synthesis control unit 15 is sent via the mixer 6 to the speaker 3. Is output from. At this time, the mixer section 6 synthesizes the acoustic signal from the audio section 5 and the talkback sound. In this embodiment, the reproduction of the music starts simultaneously with the talkback after time T1 and is output from the speaker 3.

  This makes it possible to improve the music playback response, unlike the conventional one in which music playback is started after talkback (after the time T has elapsed) as shown in FIG. When the ending time T has elapsed, the music has already been played. As a result, even if the talkback takes about several seconds to 10 seconds, the user can be relieved of the feeling that the user is waiting, and the feeling that the user feels frustrated can be eliminated.

  In this case, as shown in FIG. 4, it is possible to reduce the volume of the music playback during the talkback period and to a normal volume after the talkback ends, as shown in FIG. Further, as shown in FIG. 5, it is also possible to slightly delay the start point of music playback from the start of talkback. Furthermore, as shown in FIG. 6, it is possible to gradually increase the volume of music playback during the talkback period so that the normal volume is reached at the end of talkback. Alternatively, as shown in FIG. 7, as shown in FIG. 5 and FIG. 6, it is possible to slightly delay the start point of music playback and gradually increase the volume.

  Although detailed explanation is omitted, even when the user (driver) uses the car navigation device, it is possible to input commands and destinations by voice, and the safety and convenience are improved. Can do. Further, during route guidance, the dialogue control unit 10 and the voice synthesis control unit 15 allow synthesized voice related to voice guidance (for example, guidance voice such as “100m ahead is left”) through the mixer unit 6 at a necessary timing. The sound is output from the speaker 3. Even when it is necessary to perform such voice guidance during music playback, for example, the mixer unit 6 can synthesize the guidance voice and the playback music and simultaneously output them from the speaker 3. At that time, it is possible to perform control such that the volume on the playback music side is slightly reduced by the initial setting of the user.

  As described above, according to the car audio system 1 of the present embodiment, the user can give an instruction using the voice recognition, and the excellent effect that the user's frustration caused by the talkback can be solved. Play. In particular, in this embodiment, it is possible to adjust the output start timing of the talkback sound and the playback music and to adjust the balance of the volume of the talkback sound and the playback music. Can be set according to the user's preference, and the usefulness and convenience can be enhanced. Furthermore, in particular, in this embodiment, the car audio system 1 is built in the car navigation device, so that the configuration can be completed easily and the reproduced music can be saved without interruption during the output of the guidance voice. The merit that can be done can also be obtained.

  FIG. 8 shows another embodiment of the present invention. This embodiment is different from the above embodiment in the configuration of the mixer section 21 as output control means. The mixer section 21 amplifies the acoustic signal for each speaker 3 input from the audio section 5 to In addition to having a function of outputting to the speaker 3, in this case, in one of the four speakers 3, a function of a changeover switch that switches between the acoustic signal of the audio unit 5 and the talkback audio signal input from the speech synthesis control unit 15 Have.

  Then, the voice synthesis control unit 15 outputs the synthesized voice (talkback voice signal) to the mixer unit 21 and also controls the changeover switch of the mixer unit 21 and the volume of each speaker 3. At this time, by controlling the changeover switch of the mixer unit 21, the talkback sound is output from one of the plurality of speakers 3, and the sound reproduced by the audio unit 5 is output from the remaining speakers 3. At the time of reproduction, talkback sound and sound (reproduced music) are simultaneously output from each speaker 3.

  Therefore, also in this embodiment, since the talkback sound and the music can be simultaneously output from the speaker 3 in the mixer section 21 as in the above embodiment, the music playback response can be improved. It is possible to provide a user with instructions using voice recognition, and it is possible to obtain an excellent effect such as being able to eliminate the user's frustration due to talkback.

  In the above-described embodiment, the talkback sound is output from one speaker 3. However, the talkback sound and the reproduced music may be synthesized and output from a plurality or all of the speakers. In addition, the present invention is not limited to each of the above-described embodiments. For example, the talkback sound is not limited to the one that just talks back the song title, and the talkback is made with a sentence including the artist name and song title. In that case, it is possible to make a DJ-like sentence or intonation. Further, the car audio system of the present invention is not limited to the reproduction of music stored in an HDD, a DVD, or the like, but can be similarly implemented when reproducing a DVD video or enjoying a radio or TV. The present invention can be implemented with appropriate modifications within a range not departing from the above.

The block diagram which shows one Example of this invention and shows the whole structure of a car audio system roughly Block diagram showing the configuration of the mixer section Time chart showing the state of audio input signals and speaker output Time chart showing variation (part 1) of FIG. Time chart showing variation (2) of Fig. 3 Time chart showing variations (part 3) of FIG. Time chart showing variation (part 4) of FIG. FIG. 2 equivalent view showing another embodiment of the present invention. FIG. 3 equivalent view showing a conventional example

Explanation of symbols

In the drawings, 1 is a car audio system, 2 is a main body, 3 is a speaker, 4 is a microphone (voice input means), 5 is an audio section, 6 and 21 are mixer sections (output control means), and 8 is a voice recognition section (voice). (Recognition means), 10 is a dialogue control unit, 15 is a synthesized voice control unit (response control unit), and 16 is a music operation control unit (audio control unit).

Claims (7)

An audio unit that reproduces an acoustic signal and outputs it from a speaker;
Voice input means for inputting voice instructions to the audio unit;
Voice recognition means for performing voice recognition of the voice signal input from the voice input means;
Response control means for controlling the utterance of the talkback according to the recognition result of the voice recognition means;
Audio control means for controlling the audio unit based on a recognition result of the voice recognition means;
A talk-back voice by the response control means, and an output control means for outputting a sound that will be played simultaneously from the speaker by the audio unit is determined based on the recognition result of the speech recognition means,
A car audio system comprising adjusting means for adjusting the timing of starting sound output when the output control means simultaneously outputs talkback sound and reproduced sound .   2. The car audio system according to claim 1, wherein the output control means is composed of synthesis means for synthesizing an audio signal of the audio section and a talkback audio signal.   The output control means is configured to output talkback sound from at least one of the plurality of speakers of the audio unit, and output sound reproduced by the audio unit from the remaining speakers. The car audio system according to claim 1. 4. The output start timing of the reproduced sound can be delayed from the start of the talkback by the adjusting means and can be set during the talkback period . 5. Car audio system.   4. The volume of at least one of the settings can be set when the talkback sound and the reproduced sound are simultaneously output by the output control means. Car audio system.   6. The car audio system according to claim 1, wherein the car audio system is incorporated in a car navigation device.   The car audio system according to claim 6, wherein the output control unit is configured to simultaneously output the guidance voice of the car navigation device and the sound reproduced by the audio unit from the speaker.

Images