Speech system and warning device

Abstract

To provide a technology capable of achieving a reutterance function such as re-outputting the already output voice information from a speaker for example, when a user cannot catch the voice information outputted from the speaker with an easy and inexpensive configuration, in an utterance system provided with a voice output processing part to which the voice information is made to output sequentially from the speaker.SOLUTION: An utterance system includes: an audio command output part 20 for outputting a reutterance command accompanying the input of sound satisfying a specific determination condition for reutterance; and a reutterance control part 12 which executes the reutterance target setting process in which an audio output processing part 23 sequentially sets the audio information during or after the output to the reutterance target and also executes the reutterance control for outputting the sound information of the reutterance target from the beginning to an audio output processing part 23 again when the reutterance command is outputted by the audio command output part 20.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a speech system including a speech output processing unit that sequentially outputs voice information from a speaker, and an alarm device including the same.

Background Art

[0002] There is known a speech system including a speech output processing unit that sequentially outputs voice information from a speaker (in the present application, outputting voice information from a speaker may be referred to as "speaking"). (See Patent Documents 1 and 2.) The speech system described in Patent Document 1 is a so-called smart speaker having a speech recognition function for identifying a user's speech in addition to a speech output processing unit, which identifies the speech from the user and collects desired content information from an external information source such as the web according to the command obtained by identifying the speech, and converts the collected content information into voice information and sequentially outputs it from the speaker. The speech system described in Patent Document 2 is a language education device that outputs, in voice, an output sentence generated for an input sentence input by a learner from a keyboard, and has a speech repetition function of outputting the latest output sentence again in voice when the learner inputs a repeat request code by operating the keyboard. The speech system described in Patent Document 3 is a system having a speech recognition function for identifying a user's speech in addition to a speech output processing unit, and capable of performing a dialogue with the user, which identifies the speech from the user and is configured to be able to suppress the output of voice information according to the command obtained by identifying the speech. Also known is an alarm device that monitors an abnormal state of a user's residence, including a speech system including a speech output processing unit that sequentially outputs notification information regarding the abnormal state as voice information from a speaker. (See Patent Document 4.)

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

[0004] In particular, in a configuration in which voice information is output from a speaker regardless of the user's request, such as an alarm device equipped with a speech system, when the user cannot hear the voice information output from the speaker, etc., it is desirable to adopt a re-speech function that causes the voice information already output to be output from the speaker again. In a speech system that accepts an input operation from a keyboard, such as the speech system described in Patent Document 2 above, if the user inputs a repeat request code by a key input operation, the voice information already output can be output from the speaker again. However, a key input device such as a keyboard is required, and there is a problem that the repeat request code cannot be input when it is installed in a place out of reach or when the user's hand is blocked.

[0005] Also, in a speech system having a voice recognition function, such as Patent Documents 1 and 3 above, the user's voice can be recognized and the voice information already output can be output from the speaker again according to the command for which the voice was recognized. However, since it is necessary to provide a relatively large-scale voice recognition function, there is a problem that the system becomes expensive and large-scale. In view of this situation, the main problem of the present invention is to provide a technique that can realize a re-speech function of outputting again the voice information already output from a speaker when the user cannot hear the voice information output from the speaker in a speech system provided with a voice output processing unit that sequentially outputs voice information from the speaker, with a simple and inexpensive configuration.

Means for Solving the Problem

[0006] A first characteristic configuration of the present invention is a speech system including a speech output processing unit that sequentially outputs voice information from a speaker, an acoustic command output unit that outputs a re-speech command in response to an input of sound that satisfies a specific re-speech determination condition, a re-speech control unit that executes a re-speech target setting process for sequentially setting the voice information being output or output after by the speech output processing unit as a re-speech target, and executes a re-speech control for causing the speech output processing unit to output the voice information of the re-speech target again from the beginning when the re-speech command is output by the acoustic command output unit.

[0007] According to this configuration, when the user cannot hear the voice information output from the speaker, etc., the user only needs to make a sound that satisfies a specific re-speech determination condition without operating a key input device or the like, and the acoustic command output unit can output a re-speech command in response to the input of the sound. On the other hand, since the re-speech control unit executes the re-speech target setting process, the voice information being output or output after by the speech output processing unit is sequentially set as the re-speech target. Therefore, when the re-speech command is output by the acoustic command output unit, the re-speech control is executed by the re-speech control unit, so that the voice information that has already been output from the speaker and set as the re-speech target at that time can be output to the speaker again from the beginning (in the present application, outputting the already output voice information again in this way may be referred to as "re-speech"). And, by simply adopting a simple and reasonable configuration that discriminates in response to the input of sound that satisfies a specific condition like the acoustic command output unit without requiring an expensive and large-scale speech recognition function, a re-speech function for performing the above-described re-speech can be realized. Therefore, according to the present invention, in a speech system including a voice output processing unit that sequentially outputs voice information from a speaker, when the user cannot hear the voice information output from the speaker, etc., it is possible to provide a technology that can realize a re-speech function of re-outputting the already output voice information from the speaker with a simple and inexpensive configuration.

[0008] A second characteristic configuration of the present invention lies in that the acoustic command output unit identifies an input of an acoustic having a sound pressure level equal to or higher than a predetermined re-speech setting sound pressure level as an input of an acoustic satisfying the re-speech determination condition.

[0009] According to this configuration, in the acoustic command output unit, by simply adopting a simple and reasonable configuration of recognizing only the sound pressure level of the input acoustic, when the sound pressure level of the input acoustic becomes equal to or higher than a predetermined re-speech setting sound pressure level, a re-speech command can be output. By this, the user can cause the voice information already output from the speaker at that time to be re-spoken by simply performing a simple action such as speaking loudly or clapping hands, that is, generating an acoustic having a sound pressure level equal to or higher than the re-speech setting sound pressure level.

[0010] A third characteristic configuration of the present invention lies in that the acoustic command output unit identifies a continuous input of an acoustic having a sound pressure level equal to or higher than a predetermined re-speech setting sound pressure level for a predetermined number of re-speech settings as an input of an acoustic satisfying the re-speech determination condition.

[0011] According to this configuration, in the above-described acoustic command output unit, by adopting a simple and reasonable configuration of recognizing the sound pressure level of the input acoustic and counting the continuous input times of the acoustic having a sound pressure level equal to or higher than a predetermined replay setting sound pressure level, when the sound pressure level of the input acoustic continuously reaches a predetermined replay setting sound pressure level or higher for a predetermined number of replay setting times, a replay command can be output. In this way, the user can replay the voice information already output from the speaker at that time by performing a simple action such as continuously uttering a loud voice or continuously clapping hands, etc., that is, continuously generating an acoustic having a sound pressure level equal to or higher than the replay setting sound pressure level. In addition, when a large acoustic is input single-shot without continuous occurrence contrary to the user's intention, it is possible to prevent the output of an incorrect replay command and prevent the unnecessary execution of the replay control.

[0012] A fourth characteristic configuration of the present invention lies in that the acoustic command output unit corrects the replay setting sound pressure level based on the output sound pressure level from the speaker or the input sound pressure level from the surrounding environment.

[0013] According to this configuration, the replay setting sound pressure level, which is a criterion for determining whether the input acoustic satisfies the replay determination condition, is not fixed to a certain value, but is corrected based on the output sound pressure level indicating the volume of the acoustic output from the speaker or the input sound pressure level indicating the volume of the acoustic input from the surrounding environment. For example, the replay setting sound pressure level is changed proportionally to the output sound pressure level or the input sound pressure level. In this way, when an acoustic output from the speaker or an acoustic in the surrounding environment is input regardless of the user's intention, it is possible to surely avoid an incorrect determination that the input of the acoustic is erroneously determined as an input of an acoustic that satisfies the replay determination condition.

[0014] A fifth characteristic configuration of the present invention lies in that, in the replay target setting process, the replay control unit sets the voice information being output by the voice output processing unit as the replay target and prohibits the update of the replay target until a predetermined time has elapsed from the end point of the output of the voice information.

[0015] According to this configuration, when the voice output processing unit continuously outputs a plurality of voice information, etc., the voice information being output is set as the re-speaking target, and further, the re-speaking target is maintained until a predetermined time has elapsed from the end point of the output of the voice information. In this way, even when the output of a certain voice information ends, if a re-speaking command is output immediately after the end, instead of the next voice information being output at that time, the voice information before the end of the output can be output again. Therefore, the user can issue a sound for outputting a re-speaking command with a margin and re-speak the voice information whose output has already ended.

[0016] The sixth characteristic configuration of the present invention is that when the re-speaking control unit executes the re-speaking control and outputs the voice information of the re-speaking target to the voice output processing unit again, the voice information is output in a high recognition state with high recognition by the user.

[0017] According to this configuration, when executing re-speaking control to re-speak the voice information of the re-speaking target, the voice information is output in a high recognition state such as a large volume or a low speed with higher recognition by the user than in the normal state. Therefore, the user can surely recognize the re-spoken voice information.

[0018] The seventh characteristic configuration of the present invention is that the acoustic command output unit uses the speaker as a microphone to receive acoustic input from the speaker.

[0019] According to this configuration, since the acoustic command output unit determines the reception of the command only based on the characteristics of the sound, without using a high-performance microphone that enables voice recognition, a speaker that can receive sound input recognizable for simple acoustic characteristics is used as a microphone, and the cost reduction and simplification of the system can be achieved.

[0020] The eighth characteristic configuration of the present invention is an alarm device for monitoring an abnormal state of a user's residence, A speech system having any one of the above-described first to seventh characteristic configurations is provided. The voice output processing unit sequentially outputs the notification information regarding the abnormal state as the voice information from the speaker.

[0021] According to this configuration, in an alarm device in which the voice output processing unit sequentially outputs the notification information regarding the abnormal state of the user's residence as voice information from the speaker, since the speech system according to the present invention described above is provided, the same operational effects as those of the speech system can be achieved.

Brief Description of the Drawings

[0022]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Modes for Carrying Out the Invention

[0023] 〔First Embodiment〕 The first embodiment of the present invention will be described with reference to FIG. 1 and the like. The voice system of this embodiment (hereinafter referred to as "this voice system") 1 is a system provided in an alarm device 50 installed in a user's residence, such as a gas alarm, a residential fire alarm, or a fire notification device, for monitoring an abnormal state of the residence. In addition to the notification information regarding the abnormal state detected by the alarm device 50, content information such as a weather forecast collected by the voice information distribution system 30 from the web 32, which is an external information source, is converted into voice data, and the converted voice information is sequentially output from the speaker 24. In this embodiment, an example in which the voice system 1 is provided in the alarm device 50 is described, but the voice system 1 may be provided alone or in another device.

[0024] This voice system 1 includes a voice output processing unit 23 that sequentially outputs (speaks) voice information from the speaker 24. Specifically, in this voice system 1, there are a speaker 24 that converts an input voice signal into voice and outputs it externally (for example, to the user side), a voice output processing unit 23 that converts the input voice information into a voice signal and outputs it to the speaker 24, a control unit 10 that controls their operations, and a voice information storage unit 26 that can appropriately store the voice information output from the speaker 24. Further, the control unit 10 functions as a speech control unit 11. In the speech control unit 11, speech control is executed in which the voice information collected by the voice information distribution system 30 according to the user's request or other conditions is sequentially output to the voice output processing unit 23, and the voice information is sequentially output to the speaker 24 for speaking. The voice information distribution system 30 can be configured as a server system installed on the administrator side separate from the user's residence, and the voice system 1 and the voice information distribution system 30 are configured to be communicable through a communication line such as the Internet.

[0025] Furthermore, this voice system 1 is provided with an acoustic command output unit 20 that outputs a specific command in accordance with the input of an acoustic sound that satisfies a specific determination condition (in this application, such an input of an acoustic sound may be expressed as "input of a specific acoustic sound"). The acoustic sound to be determined by the acoustic command output unit 20 is the acoustic sound excluding the one output as the voice information during speaking from the speaker 24. In addition, this acoustic command output unit 20 is configured to receive an input of an acoustic signal from the speaker 24 by using the speaker 24 as a microphone 21. Incidentally, when using the speaker 24 as a microphone, a known microphone-speaker dual-use element can be used as the speaker 24. Further, it can also be configured to switch between a state in which the speaker 24 functions as a normal speaker and a state in which it functions as the microphone 21 by using a switching element. Incidentally, as shown in FIG. 10, instead of using the speaker 24 as the microphone 21, a separate microphone 21 may be provided and configured to receive an input of an acoustic signal from the microphone 21.

[0026] Referring to FIG. 1, the acoustic command output unit 20 can identify an input of an acoustic having a sound pressure level equal to or higher than a predetermined set sound pressure level or a continuous input of an acoustic having a sound pressure level equal to or higher than a predetermined set sound pressure level for a predetermined set number of times as an input of the specific acoustic. For example, when an acoustic having a sound pressure level equal to or higher than the set sound pressure level is input to the microphone 21 when the user shouts or claps, or when an acoustic having a sound pressure level equal to or higher than the set sound pressure level is continuously input to the microphone 21 when the user continuously shouts or continuously claps, the acoustic command output unit 20 identifies the input of the acoustic as an input of the specific acoustic, and outputs a specific command.

[0027] In order to accurately determine whether or not to output the specific command, the maximum sound pressure level of the user's voice or the ambient environmental sound input during normal times is learned, or the sound pressure level of the actually input acoustic in a predetermined set mode is recorded, and the set sound pressure level can be appropriately set as a sound pressure level exceeding the learned or recorded sound pressure level of the acoustic. Furthermore, the acoustic command output unit 20 can automatically correct the set sound pressure level based on the output sound pressure level of the voice information output from the speaker 24 or the input sound pressure level of the sound in the surrounding environment input to the microphone 21. That is, the set sound pressure level serving as the criterion for determining whether to issue the specific command is not fixed at a certain value, but is changed proportionally to the output sound pressure level or the input sound pressure level. This can surely avoid misjudgment that, regardless of the user's intention, when the sound output from the speaker or the sound in the surrounding environment is input, the input of the sound is erroneously determined as the input of the sound that satisfies the re-speaking determination condition. Also, in this embodiment, it is determined whether to output the specific command based on the sound pressure level of the input sound. However, for example, the determination may be made based on another acoustic characteristic such as the frequency of the sound. Furthermore, when identifying the input of a predetermined number of consecutive inputs of the sound that satisfy a specific determination condition as the input of the specific sound, the determination conditions set for each input of the sound may be made different from each other. For example, consecutive inputs of a loud or high-pitched sound and a soft or low-pitched sound can be recognized as the input of the specific sound.

[0028] The acoustic command output unit 20 can output a re-speaking command, which is a trigger for the re-speaking control unit 12 described later to execute re-speaking control, as the specific command. That is, the acoustic command output unit 20 recognizes the input of a sound having a sound pressure level equal to or higher than a predetermined set sound pressure level for re-speaking, or the input of a sound having a sound pressure level equal to or higher than a predetermined set sound pressure level for re-speaking for a predetermined number of consecutive times as the input of the specific sound, and can output a re-speaking command in accordance with the input of the sound.

[0029] The control unit 10 functions as a re-speech control unit 12 that executes predetermined re-speech control. In this re-speech control, a re-speech target setting process is executed in which the voice output processing unit 23 sequentially sets the voice information during or after output as the re-speech target, and when a re-speech command is output by the acoustic command output unit 20, the voice information of the re-speech target is output (re-spoken) again from the beginning by the voice output processing unit 23. That is, by executing the above re-speech target setting process, the voice information A during or after output by the voice output processing unit 23 is sequentially set as the re-speech target and stored in the voice information storage unit 26. And, for example, when the user cannot hear the voice information output from the speaker 24 regardless of the user's request, if there is an input of the specific sound from the user during the output of the voice information A, the acoustic command output unit 20 outputs a re-speech command in accordance with the input of the sound. Then, the re-speech control unit 12 executes re-speech control, and the voice information that has already been output from the speaker 24 and set as the re-speech target at that time is extracted from the voice information storage unit 26, and the extracted voice information A is re-spoken again from the beginning from the speaker 24.

[0030] In such re-speech control, when re-speaking the voice information of the re-speech target, the voice information can be output in a high-recognition state with high recognition by the user. Specifically, in this embodiment, in the high-recognition state, the voice information is re-spoken with a re-speech message for recognizing that it is a re-speech added at the beginning. Note that as the high-recognition state, the voice information can be re-spoken in a state where it is easier for the user to hear, such as increasing the volume of the speaker 24 or slowing down the playback (speaking) speed.

[0031] In the above re-speech target setting process, the voice information being output by the voice output processing unit 23 is set as the re-speech target, and the update of the re-speech target is prohibited until a predetermined time has elapsed from the end point of the output of the voice information. That is, when the voice output processing unit 23 continuously outputs a plurality of voice information, for example, when the voice information being output is sequentially set as the re-speaking target, the set voice information of the re-speaking target will be maintained as the re-speaking target until a predetermined time has elapsed since the end of the output of that voice information. In this way, even when the output of a certain voice information has ended, if a re-speaking command is output immediately after the end, instead of the next voice information being output at that time being re-spoken, the voice information before the end of the output will be re-spoken. Therefore, the user can issue a sound for outputting a re-speaking command with a margin and re-speak the voice information whose output has already ended. In addition, it may be configured to prohibit the update of the re-speaking target from the end point of the output of the voice information to the start point of the output of the next voice information. In this case, even when the output of a certain voice information has ended, if a re-speaking command is output before the next voice information is output, the voice information before the end of the output will be re-spoken. Also, it can be configured to set the voice information being output as the re-speaking target and reset the re-speaking target at the end point of the output of that voice information. In this case, the voice information will be re-spoken only when a re-speaking command is output during the output of a certain voice information. Hereinafter, specific embodiments will be described based on the drawings.

[0032] (First Embodiment) As shown in FIG. 2, the first embodiment is an example in which the above specific sound is input during the speaking of voice information A. In this case, a re-speaking command is output in accordance with the input of the above specific sound during the speaking of voice information A, and re-speaking control is executed. Also, during the speaking of voice information A, the voice information A being spoken is set as the re-speaking target. Therefore, at the time of input of the specific sound, the voice information A being spoken, which is set as the re-speaking target, will be re-spoken from the beginning with an appropriate re-speaking message attached.

[0033] (Second Embodiment) The second embodiment is an example in which the specific sound is input between the end point of the utterance of the voice information A and the elapse of a predetermined time Tr. In this case, a re-utterance command is output in accordance with the input of the specific sound between the end point of the utterance of the voice information A and the elapse of the predetermined time Tr, and re-utterance control is executed. Also, since the update of the re-utterance target is prohibited between the end point of the utterance of the voice information A and the elapse of the predetermined time Tr, the voice information A whose utterance has ended is maintained as the re-utterance target. Therefore, at the time of the input of the specific sound, the voice information A that has already ended its utterance and is set as the re-utterance target is re-uttered from the beginning with an appropriate re-utterance message attached thereto.

[0034] (Third Embodiment) The third embodiment is an example in which, as shown in FIG. 4, when the voice information A and the voice information B are continuously uttered in order, the specific sound is input between the end point of the utterance of the voice information A and the elapse of a predetermined time Tr. In this case, a re-utterance command is output in accordance with the input of the specific sound between the end point of the utterance of the voice information A and the elapse of the predetermined time Tr, and re-utterance control is executed. Also, since the update of the re-utterance target is prohibited between the end point of the utterance of the voice information A and the elapse of the predetermined time Tr, the voice information A whose utterance has ended is maintained as the re-utterance target. Therefore, at the time of the input of the specific sound, the voice information A that has already ended its utterance and is set as the re-utterance target is re-uttered from the beginning with an appropriate re-utterance message attached thereto, and the voice information B is re-uttered following the re-utterance of the voice information A.

[0035] (Fourth Embodiment) The fourth embodiment is an example in which, as shown in FIG. 5, when the voice information A and the voice information B are continuously uttered in order, the specific sound is input during the utterance of the voice information B after the elapse of a predetermined time Tr from the end point of the utterance of the voice information A. In this case, after a predetermined time Tr has elapsed since the end of the utterance of the voice information A, a re-utterance command is output in response to the input of the specific sound during the utterance of the voice information B, and re-utterance control is executed. Also, after a predetermined time Tr has elapsed since the end of the utterance of the voice information A, the prohibition of updating the re-utterance target is released, and the re-utterance target is updated to the voice information B. Therefore, at the time of the input of the specific sound, the voice information B being uttered, which is set as the re-utterance target, will be re-uttered from the beginning with an appropriate re-utterance message attached thereto.

[0036] 〔Second Embodiment〕 The second embodiment of the present invention will be described with reference to FIG. 6 and the like. Note that, in this embodiment, compared with the aforementioned first embodiment, the acoustic command output unit 20 outputs a voice suppression command as the specific command, in addition to the re-utterance command, and the control unit 10 functions as a voice suppression control unit 13 separately from the voice control unit 11. Therefore, in the following description, for the same configurations as those in the aforementioned first embodiment, the same reference numerals will be given in the drawings, and detailed descriptions thereof will be omitted.

[0037] The acoustic command output unit 20 can output a voice suppression command that serves as a trigger for the voice suppression control unit 13, which will be described later, to execute voice suppression control, as the specific command. That is, the acoustic command output unit 20 recognizes the input of a sound having a sound pressure level equal to or higher than a predetermined voice suppression setting sound pressure level, or the continuous input of a sound having a sound pressure level equal to or higher than a predetermined voice suppression setting sound pressure level for a predetermined number of times for voice suppression, as the input of the specific sound, and can output a voice suppression command in response to the input of that sound.

[0038] The control unit 10 functions as a voice suppression control unit 13 that executes predetermined voice suppression control. In that voice suppression control, the output (utterance) of voice information by the voice output processing unit 23 is suppressed when a voice suppression command is output by the acoustic command output unit 20. That is, when the voice information output from the speaker 24 is annoying to the user regardless of the user's intention or situation, for example, if there is an input of the specific sound from the user during the output of the voice information, the sound command output unit 20 outputs a voice suppression command in accordance with the input of the sound. Then, the voice suppression control unit 13 executes voice suppression control, and the output of the voice information at that time is suppressed. Furthermore, as a specific method for suppressing the output of voice information, a method of temporarily stopping the output of voice information is adopted. Specifically, the output of voice information from the speaker 24 is stopped, and the voice information is output from the beginning at the time when a predetermined voice stop time has elapsed since the stop time. In addition, in this embodiment, the voice information is configured to be output from the beginning again after the temporary stop. However, when outputting again, it is possible to adopt a method of skipping the already output part and outputting the voice information from the continuation, or reducing the volume of the speaker 24 for the voice information to be output again and the voice information to be output thereafter. Also, as another method for suppressing the output of voice information, it is possible to adopt a method of reducing the volume of the speaker 24 while continuing without stopping the output of the voice information. Furthermore, when voice suppression is performed by a method such as stopping the output of specific voice information or reducing the volume by voice suppression control, the same voice suppression may be performed for all voice information output thereafter. However, for example, it is also possible to configure to perform voice suppression only for the output of voice information of the same genre or in the same output time zone as the voice information for which voice suppression has been performed. Also, when performing voice suppression for the output of voice information of the same genre, voice guidance for notifying the user to that effect can be performed. Also, the stop of the output of voice information of the same genre can be performed on the side of the speech system 1 or on the side of the voice information distribution system 30.

[0039] The voice information output by the voice output processing unit 23 is configured as information capable of identifying the speech priority. That is, for voice information that needs to be surely recognized by the user, such as the notification information transmitted from the warning device 50, the speech priority is set high. On the other hand, for voice information regarding general content information, the speech priority is set low. And the speech suppression control unit 13 prohibits the execution of the above-described speech suppression control when the voice output processing unit 23 outputs voice information with a high speech priority. By this, for voice information with a high speech priority, it is output so that the user can clearly hear it without being suppressed.

[0040] The acoustic command output unit 20 can determine and output a re-speech command and a speech suppression command in accordance with the input of the specific sound. For example, a re-speech determination condition including a re-speech setting sound pressure level and a re-speech setting number of times, and a speech suppression determination condition including a speech suppression setting sound pressure level and a speech suppression setting number of times can be set as different conditions respectively. However, in this embodiment, the re-speech determination condition and the speech suppression determination condition are set as the same condition, and the re-speech command and the speech suppression command are determined and output at the timing when the sound satisfying the condition is input. Specifically, when the input time point of the specific sound is within the re-speech command reception time zone until a predetermined time has elapsed from the output time point of the speech suppression command, the acoustic command output unit 20 outputs a re-speech command in accordance with the input of the specific sound. When it is in a time zone other than the re-speech command reception time zone, the acoustic command output unit 20 outputs a speech suppression command in accordance with the input of the specific sound. With this configuration, when the user wants to re-check the voice information for which speech suppression has been performed, a re-speech command is output in accordance with the input of the specific sound in the re-speech command reception time zone, and the voice information set as the re-speech target can be re-spoken. Hereinafter, specific embodiments will be described based on the drawings.

[0041] (Embodiment 5) Example 5 is an example where, as shown in FIG. 7, there is an input of the specific sound during the utterance of the voice information A, and further there is an input of the specific sound during the re-utterance command reception time period Tz starting from that point in time. In this case, a voice suppression command is output in accordance with the input of the specific sound during the utterance of the voice information A, and voice suppression control is executed. Therefore, at the time of input of the specific sound, the utterance of the voice information A is temporarily stopped. For example, if there is no input of the second specific sound, the voice information A whose utterance has been temporarily stopped is re-uttered from the beginning at the time when a predetermined voice stop time Tx has elapsed from the stop time point. However, as shown in the figure, since the specific sound is input during the re-utterance command reception time period Tz until a predetermined time has elapsed from the output time point of the voice suppression command, a re-utterance suppression command is output in accordance with the input of the specific sound, and re-utterance suppression control is executed. Also, during the re-utterance command reception time period Tz, the voice information A during which the utterance has stopped is set as the re-utterance target. Therefore, at the time of input of the specific sound, the voice information A during which the utterance has stopped and which is set as the re-utterance target is re-uttered from the beginning with an appropriate re-utterance message attached thereto. In addition, in this embodiment, the re-utterance command reception time period Tz is set to the same time period as the voice stop time Tx, but the re-utterance command reception time period Tz may be set to a time period shorter than the voice stop time Tx.

[0042] (Example 6) Example 6 is an example where, as shown in FIG. 8, when uttering voice information A consisting of an introduction part and the main text following it, there is an input of the specific sound during the utterance of the introduction part of the voice information A. In the voice information A, the introduction part is information that is not particularly important to the user and has a low utterance priority, and the main text is more important to the user than the introduction part and has a high utterance priority. And the acoustic command output unit 20 is configured to output a voice suppression command in accordance with the input of the specific sound during the utterance of the introduction part of the voice information A, while outputting a re-utterance command in accordance with the input of the specific sound during the utterance of the main text of the voice information A. For example, as shown in the figure, when the specific sound is input during the speech of the introduction part of the voice information A, a speech suppression command is output along with the input of the specific sound, and speech suppression control is executed. Therefore, at the time when the specific sound is input, the speech of the voice information A is temporarily stopped, and at the time when a predetermined speech stop time Tx has elapsed from the stop time, the voice information A whose speech has been temporarily stopped is re-spoken from the beginning introduction part. Furthermore, when the specific sound is input again during the re-speech command reception time zone Tz starting from the output of the speech suppression command, although the illustration is omitted, similar to the above-described Embodiment 5, a re-speech suppression command is output along with the input of the specific sound in the re-speech command reception time zone Tz, re-speech suppression control is executed, and the voice information A that is set as the re-speech target and whose speech is stopped is re-spoken from the beginning introduction part with an appropriate re-speech message attached. In addition, in the present embodiment, the re-speech command reception time zone Tz is set to the same time zone as the speech stop time Tx, but the re-speech command reception time zone Tz may be set to a time zone shorter than the speech stop time Tx.

[0043] (Embodiment 7) Embodiment 7 is an example in the case where, as shown in FIG. 9, when speaking voice information A consisting of an introduction part and the main text following it, the specific sound is input during the speech of the main text of the voice information A. In the voice information A, the introduction part is information that is not particularly important to the user and has a low speech priority, and the main text is more important to the user than the introduction part and has a high speech priority. And the acoustic command output unit 20 outputs a speech suppression command along with the input of the specific sound when the specific sound is input during the speech of the introduction part of the voice information A, while on the other hand, when the specific sound is input during the speech of the main text of the voice information A, it is configured to output a re-speech command along with the input of the specific sound. In addition, the acoustic command output unit 20 is configured to output a re-speech command only during the speech of the main text, which has a higher speech priority than the introduction part, when speaking voice information A consisting of the introduction part and the main text following it. For example, as shown in the figure, when the specific sound is input during the speech of the text of the voice information A, a re-speech command is output along with the input of the specific sound, and re-speech control is executed. Also, during the speech of the voice information A, the voice information A during the speech is set as the re-speech target. Therefore, at the time of the input of the specific sound, the voice information A during the speech set as the re-speech target will be re-spoken from the introductory part at the beginning with an appropriate re-speech message attached thereto.

[0044] Also, as shown in FIG. 6, a human presence sensor 25 for detecting a nearby user is provided, and when the specific sound is input during the speech of the voice information and the human presence sensor 25 detects a user, the acoustic command output unit 20 determines that the user desires re-speech and outputs a re-speech command, and when the human presence sensor 25 does not detect a user, it determines that the user desires speech suppression and outputs a speech suppression command.

Explanation of Reference Numerals

[0045] 1 Speech system 10 Control unit 11 Speech control unit 12 Re-speech control unit 20 Acoustic command output unit 21 Microphone 23 Voice output processing unit 24 Speaker A Voice information B Voice information Tr Predetermined time

Claims

1. A speech system including a voice output processing unit that sequentially outputs voice information from a speaker, an acoustic command output unit that outputs a re-speech command in response to the input of an acoustic sound that satisfies a specific re-speech determination condition including the condition that an acoustic sound having a sound pressure level equal to or higher than a predetermined re-speech setting sound pressure level is input, and a re-speech control unit that executes a re-speech target setting process for sequentially setting the voice information being output or output after by the voice output processing unit as a re-speech target, and executes a re-speech control for causing the voice information of the re-speech target to be output again from the beginning to the voice output processing unit when the re-speech command is output by the acoustic command output unit, wherein the re-speech control unit sets the voice information being output by the voice output processing unit as the re-speech target in the re-speech target setting process, and prohibits updating of the re-speech target until a predetermined time has elapsed from the end point of the output of the voice information.

2. The acoustic command output unit outputs a voice suppression command in response to the input of an acoustic sound that satisfies a specific voice suppression determination condition, and includes a voice suppression control unit that executes a voice suppression control for suppressing the output of voice information by the voice output processing unit when the voice suppression command is output by the acoustic command output unit, The speech system according to claim 1, wherein the acoustic command output unit outputs the re-speech command only during a re-speech command reception time period until a predetermined time has elapsed from the output time point of the voice suppression command.

3. A speech system including a voice output processing unit that sequentially outputs voice information from a speaker, an acoustic command output unit that outputs a re-speech command in response to the input of an acoustic sound that satisfies a specific re-speech determination condition including the condition that an acoustic sound having a sound pressure level equal to or higher than a predetermined re-speech setting sound pressure level is input, and a re-speech control unit that executes a re-speech target setting process for sequentially setting the voice information being output or output after by the voice output processing unit as a re-speech target, and executes a re-speech control for causing the voice information of the re-speech target to be output again from the beginning to the voice output processing unit when the re-speech command is output by the acoustic command output unit, wherein the re-speech control unit sets the voice information being output by the voice output processing unit as the re-speech target in the re-speech target setting process, and prohibits updating of the re-speech target from the end point of the output of the voice information to the start point of the output of the next voice information. The acoustic command output unit outputs a voice suppression command in response to the input of acoustic sound that satisfies a specific voice suppression determination condition, A voice suppression control unit that executes voice suppression control for suppressing the output of voice information by the voice output processing unit when the voice suppression command is output by the acoustic command output unit is provided, A voice system in which the acoustic command output unit outputs the re-utterance command only in a re-utterance command reception time zone until a predetermined time has elapsed from the output time of the voice suppression command.

4. The voice information output by the voice output processing unit consists of an introduction part and a main text following it, The voice system according to claim 2 or 3, wherein the acoustic command output unit outputs the voice suppression command during the output of the introduction part and outputs the re-utterance command during the output of the main text.

5. The voice system according to any one of claims 1 to 4, wherein the acoustic command output unit identifies an input of acoustic sound having a sound pressure level equal to or higher than a predetermined re-utterance setting sound pressure level as an input of acoustic sound that satisfies the re-utterance determination condition.

6. The voice system according to any one of claims 1 to 5, wherein the acoustic command output unit identifies consecutive inputs of acoustic sound having a sound pressure level equal to or higher than a predetermined re-utterance setting sound pressure level a predetermined number of times as an input of acoustic sound that satisfies the re-utterance determination condition.

7. The voice system according to claim 5 or 6, wherein the acoustic command output unit corrects the re-utterance setting sound pressure level based on the output sound pressure level from the speaker or the input sound pressure level from the surrounding environment.

8. When the re-utterance control unit executes the re-utterance control to output the voice information to be re-uttered to the voice output processing unit again, the voice system according to any one of claims 1 to 7 outputs the voice information in a high recognition state with high recognition by the user.

9. The voice system according to any one of claims 1 to 8, wherein the acoustic command output unit receives an input of acoustic sound from the speaker by using the speaker as a microphone.

10. An alarm device for monitoring an abnormal state of a user's residence, Comprising the voice system according to any one of claims 1 to 9, An alarm device in which the voice output processing unit sequentially outputs notification information regarding the abnormal state as the voice information from the speaker.

Images