JPH1028068A - Radio device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To select only required information and to easily provide the information by voice synthesizing stored text data corresponding to external input and outputting voice synthesized voice signals. SOLUTION: A voice recognition part 30 recognizes radio broadcast and converts it to the text data. Then, since a key word retrieval part 32 retrieves a key word determined beforehand, the broadcast contents of specified contents such as traffic information or the like are stored as the text data. Further, the voice synthesizing part 34 synthesizes the text data and outputs them to a speaker when the external input is present. Thus, a user obtains the information of the contents specified by the key word as needed, and since not the voice signals but data made into texts are stored in a memory 14, more information is stored. Thus, only the required information of the contents of the broadcast is obtained.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a radio device, and more particularly to a radio device mounted on a vehicle. In addition, it can be used not only for in-vehicle use but also for home-use radios (components and radio-cassettes).

[0002]

2. Description of the Related Art Conventionally, a radio receives only one broadcast station per main body, and a user can obtain information of only one broadcast station. For this reason, it was not possible to listen to the two broadcasting stations at the same time.

[0003] In addition, since a traffic information station on a highway has a receivable range, the tuning frequency must be changed each time, and the broadcast contents that the user wants to listen to must be temporarily interrupted.

[0004]

However, in the above-mentioned conventional example, if there are two broadcasts that one really wants to hear, it cannot be heard. Furthermore, since the receivable range of traffic information and the like is fixed, there is a disadvantage that when listening to traffic information, the broadcast station that has been heard during that time cannot be heard.

[0005] Furthermore, in a sports program or the like, it is desired to listen only when a score is obtained, but such a thing cannot be performed. That is, in the conventional example, there is an inconvenience that only necessary information cannot be selected and heard.

Since the traffic information broadcast area is small and there are few signs, the traffic information may be missed. In addition, there is a disadvantage that the driver who sees the sign must operate the radio device to receive the traffic information, and after hearing the traffic information, operate the radio device again.

[0007]

SUMMARY OF THE INVENTION It is an object of the present invention to improve the disadvantages of the prior art and, in particular, to provide a radio apparatus capable of selecting only necessary information and providing the information easily. I do.

[0008]

Therefore, according to the present invention, there is provided a tuner for receiving a radio broadcast, and a speaker for externally outputting an audio signal output from the tuner. Moreover, a voice recognition means for recognizing a voice signal received by the tuner, a search means for searching for a predetermined keyword from text data output from the voice recognition means, and a part where the keyword is searched by the search means Storage means for storing the text data of the above, wherein the storage means performs voice synthesis of the text data stored in the storage means in response to an external input and outputs a voice signal obtained by voice synthesis to a speaker Is adopted. This aims to achieve the above-mentioned object.

In the present invention, the speech recognition means recognizes the voice of the radio broadcast and converts it into text data,
In order to search for a predetermined keyword, broadcast contents of specific contents such as traffic information can be stored as text data, and the voice synthesizing means synthesizes the text data by voice when there is an external input. Output to the speaker.

[0010]

Embodiments of the present invention will be described below with reference to the drawings.

FIG. 1 is a block diagram showing a configuration of a radio apparatus according to the present invention. The radio apparatus includes first and second tuners 10 and 11, a voice synthesis recording / reproducing circuit 12 for recognizing the content of a radio broadcast received by the first tuner and voice-synthesizing text data, and a voice synthesis recording / playback circuit. A memory (storage means) 14 for storing text data generated by the reproducing circuit 12, a voice switching circuit 18 for switching the output of a voice signal output from the second tuner or the voice synthesis recording / reproducing circuit 12, and a voice switching circuit An amplifier 20 amplifies an audio signal output from the circuit, and a speaker 22 that converts the output of the amplifier 20 into an acoustic signal (sound wave).

The operations of these units are controlled by the CPU 16. In addition, the display unit 24 includes a display unit 24 that edits and displays the text data recognized by voice.

The user normally receives a broadcast from a certain broadcasting station on the second tuner 11 side. In the present embodiment, there is no problem even if the user listens to a tape, a CD, or the like without using the radio. The first tuner 10 receives a broadcast station (sports program, traffic information) for performing an extraction process using a predetermined keyword. The voice signal input from the first tuner 10 is input to the voice synthesis recording / reproducing circuit 12 and is compared with a preset keyword.

In the case of traffic information, keywords such as "traffic information", "accident", "Japan Highway Public Corporation", and "traffic jam" are used. In the case of a sports program, for example, in the case of baseball, words such as "baseball", "home run", "home in", "timely" and the like are used.

If there is a keyword that matches the voice recognition result, the contents of the voice result are stored in the memory 14.

The stored contents are stored in an audio output switching circuit 18.
, And prioritizes the broadcast content of the second tuner for audio output, or turns on the indicator on the display unit,
The user is notified by a display such as a chime. For this reason, the user, for example, while listening to music,
When the word "congestion" is searched for in the traffic information, the contents of the traffic information can be known.

FIG. 2 is a functional block diagram of a voice synthesis recording / reproducing circuit and its peripheral configuration. Voice synthesis recording / reproduction circuit 12
A voice recognition unit (voice recognition unit) 30 for voice recognition of a voice signal output from the first tuner according to a voice recognition algorithm; a voice synthesis unit (voice synthesis unit) 34 for voice-synthesizing text data; And a keyword search unit (search means) 32 for searching for a predetermined keyword from the result. Then, the display unit 24
An editing unit 38 for editing text data for display, and a display 36 using an LCD for displaying display data edited by the editing unit 38 are provided.

The voice recognition unit 30 converts the input voice signal into text data. This data is input to the keyword detection unit 32 and searches for the same word as the keyword. If there is the same word as the keyword, a memory start signal is output to the storage unit 14. Thereby, the storage unit 14 stores the broadcast content. When outputting the stored contents as audio, the text data is converted into an audio signal and output. At this time, it is also possible to use a display such as an LCD to display the score of a sports program, traffic information of traffic information, and the like.

The speech recognition unit 30 makes a hypothesis of a sentence for each given keyword, predicts a word based on the hypothesis, sequentially predicts a phoneme, and collates a phoneme having a high possibility of input with an input voice signal. Perform top-down processing. Since the purpose of speech recognition is to extract keywords, it is necessary to recognize these keywords first. According to this top-down process, even if recognition of speech that has nothing to do with keywords is somewhat failed, Sentences including are surely recognized.

This speech recognition is performed by using a DSP with the tuner output as a direct source, so that the influence of noise is relatively small. Further, since the announcement is performed with a general sound, a well-known technique relating to the speech recognition is effectively used. can do. In the case of stereo broadcasting, voice recognition processing is performed on one sound source. In addition to DSP, DSP
It is also used to control other equipment for vehicles.

The speech recognition unit 30 uses the result of speech recognition as text data. In order to perform speech synthesis more accurately,
In addition to the text data, an accent position or the like, a break in reading aloud, or the like may be generated as additional information.
In addition, since traffic information broadcast in a specific area repeatedly broadcasts the same content with a silent portion interposed therebetween, it may be possible to recognize from the audio signal after the silent portion to the next silent portion.

FIG. 3 is an explanatory view showing an example of the display unit 36 for displaying the display data edited by the editing unit 38. FIG. 3A shows an example in which traffic information is edited and displayed. When the traffic information is broadcasted on a radio broadcast saying "There is a traffic jam of 10 km near the Hamamatsu Interchange" and the speech recognition is successful, the editing unit 38 uses the keyword "traffic jam" to extract "place" information and "distance" information. Is extracted. Further, "Hamamatsu-ten-jun" is edited for display as "Hamamatsu IC". The editor 38 also writes “accident”,
For keywords such as “construction”, “time” information is extracted when “location” information is present. As described above, the editing unit 38 determines the “place” determined in advance by the keyword.
The text data is converted into display data in accordance with syntax information that is a combination such as “distance”.

FIG. 3B is an explanatory diagram showing an example of displaying a baseball result. When the first tuner 10 receives a broadcast saying “the giant is leading Yakult in 5 to 3 after finishing 5 times”, the editing unit 38 performs grammatical analysis and performs editing using syntax information.

FIG. 4 is a flow chart showing an operation example according to the configuration shown in FIGS. First, an audio source is selected by the user. When the first tuner is selected, the broadcast frequency of the radio broadcast received in the background is selected (step S2). afterwards,
The process of the user proceeds to step S6.

When the frequency of the first tuner is selected,
When the electric field strength is equal to or higher than a certain level, the voice synthesis recording / reproducing circuit 12 performs voice recognition and compares it with a keyword (step S4). This is repeated until the same word as the keyword is searched or the radio device is turned off (step S4). When the same word as the keyword is searched,
The text data is stored in the memory 14, and a display indicating that the search has been performed is performed (step S11).

After selecting the frequency of the first tuner or turning on the radio device, when various audio sources other than the first tuner are selected,
The broadcast, CD, MD, cassette tape, and the like received by the second tuner 11 are reproduced (step S6). And
If necessary, the content stored in the memory is selected and listened (step S7). The content may be displayed on the display 36 (step S10), or may be synthesized (step S8), and output from the speaker 22.

As described above, according to the present embodiment, it is possible to obtain necessary information, such as when the user wants to listen to traffic information later or to know only the score of a sports program. For this reason, if the information is set in traffic information or the like, necessary information can be known without switching the reception frequency of the radio device when the operation of the radio on a highway is troublesome. Further, according to the present embodiment, the broadcasting station can be realized by changing only the radio apparatus without changing the existing equipment, and since the data is stored after being converted into text data, the audio data is not stored as it is. The storage capacity can be reduced.

[0028]

The present invention is constructed and functions as described above. According to this, according to this, the voice recognition means recognizes the radio broadcast by voice and converts it into text data, and the search means converts the predetermined keyword to the predetermined keyword. For searching, the broadcast contents of specific contents such as traffic information can be stored as text data, and furthermore, the voice synthesizing means synthesizes the text data when there is an external input and outputs it to the speaker. The user can obtain the information specified by the keyword when necessary, and the storage means stores text information instead of voice signals, so that more information can be stored. I can put it. Furthermore, in a configuration in which a normal tuner is separately provided, it is possible to perform keyword extraction processing on other broadcasts such as traffic information broadcasts in the background while listening to radio broadcasts normally. An excellent radio device, which has not been available in the past, that can obtain only the information necessary for the radio device can be provided.

[Brief description of the drawings]

FIG. 1 is a block diagram showing a configuration of an embodiment of the present invention.

FIG. 2 is a functional block diagram illustrating a detailed configuration of a voice synthesis recording / reproducing circuit and the like illustrated in FIG. 1;

FIG. 3 is an explanatory diagram showing a display example according to the configuration shown in FIG. 2; FIG. 3A is a diagram showing a display example of traffic information;
(B) is a figure showing a display example of sports information.

FIG. 4 is a flowchart showing an operation in the configuration shown in FIG. 1;

[Explanation of symbols]

 Reference Signs List 10 first tuner 11 second tuner 12 voice synthesis recording / reproducing circuit 14 memory (storage means) 16 CPU 18 voice switching circuit 30 voice recognition unit (voice recognition unit) 32 keyword search unit (search unit) 34 voice synthesis unit ( Voice synthesis means) 36 Display 38 Editing unit

Claims (3)

[Claims] 1. A radio apparatus comprising: a tuner for receiving a radio broadcast; and a speaker for externally outputting an audio signal output from the tuner, wherein: a voice recognition unit for recognizing the audio signal received by the tuner; A search unit for searching for a predetermined keyword from the text data output from the voice recognition unit; and a storage unit for storing text data of a portion where the keyword is searched by the search unit. A radio apparatus comprising a voice synthesizing means for voice-synthesizing text data stored in said storage means in response to an external input and outputting a voice signal synthesized with said voice to said speaker. 2. A radio apparatus comprising: a tuner for receiving a radio broadcast; and a speaker for externally outputting an audio signal output from the tuner, wherein: a voice recognition unit for recognizing the audio signal received by the tuner; A search unit for searching for a predetermined keyword from the text data output from the voice recognition unit; and a storage unit for storing text data of a portion where the keyword is searched by the search unit. A radio device further comprising a display unit for displaying text data stored in said storage means in response to an external input. 3. The radio apparatus according to claim 1, wherein a second tuner connected to the speaker is provided on the tuner.