Content reproduction device, content reproduction method, and content reproduction program

Abstract

To provide a content reproduction device capable of displaying a caption obtained by accurately translating a script.SOLUTION: A voice recognition unit 2 converts a voice signal in a first language included in content data reproduced by a reproduction unit 1 into text data in the first language. A translation unit 3 generates text data in a second language by translating the text data in the first language into the second language. A text evaluation unit 4 compares the text data in the second language included in the content data with the text data translated into the second language. A text image generation unit 8 generates a caption text image based on the text data translated into the second language based on comparison of the text data by the text evaluation unit 4.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a content playback device, a content playback method, and a content playback program. [Background technology]

[0002] In content such as foreign movies, subtitles that translate the dialogue in a foreign language may be displayed at the edge of the frame. When playing back content recorded on a packaged medium such as a DVD (registered trademark) disc or Blu-ray (registered trademark) disc, it is possible to display subtitles that translate the dialogue in a foreign language in the frame or to hide the subtitles. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2009-141810 A Summary of the Invention [Problem to be solved by the invention]

[0004] Foreign movies can be used for language learning. However, when subtitles that translate foreign dialogue are displayed on a frame, there is a limit to the number of characters that can be displayed per second, so the dialogue and the subtitles may not match because some of the dialogue is omitted or translated freely. Therefore, there is a need to display subtitles that accurately translate the dialogue.

[0005] An object of the present invention is to provide a content playback device, a content playback method, and a content playback program that are capable of appropriately displaying subtitles. [Means for solving the problem]

[0006] The present invention provides a content playback device comprising: a playback unit that plays content data; a voice recognition unit that converts an audio signal in a first language included in the content data into text data in the first language; a translation unit that generates text data in a second language by translating the text data in the first language into a second language different from the first language; a text evaluation unit that compares the text data in the second language included in the content data with the text data translated into the second language; and a text image generation unit that generates a subtitle text image based on the text data translated into the second language based on the comparison of text data by the text evaluation unit.

[0007] The present invention provides a content playback method in which a playback unit plays content data, a voice recognition unit converts a voice signal in a first language included in the content data into text data in the first language, a translation unit generates text data in a second language by translating the text data in the first language into a second language different from the first language, a text evaluation unit compares the text data in the second language included in the content data with the text data translated into the second language, and a text image generation unit generates a subtitle text image based on the text data translated into the second language based on the comparison of the text data by the text evaluation unit.

[0008] The present invention provides a content playback program that causes a computer to execute the steps of playing content data, converting an audio signal in a first language included in the content data into text data in the first language, generating text data in a second language by translating the text data in the first language into a second language different from the first language, comparing the text data in the second language included in the content data with the text data translated into the second language, and generating a subtitle text image based on the text data translated into the second language based on the comparison of the text data. Effect of the Invention

[0009] According to the content reproducing device, the content reproducing method, and the content reproducing program of the present invention, subtitles can be displayed appropriately. [Brief description of the drawings]

[0010] [Figure 1] FIG. 1 is a block diagram showing a content playback device according to an embodiment. [Diagram 2] FIG. 2 is a block diagram showing a specific example of the configuration of the voice recognition unit 2. As shown in FIG. [Diagram 3] FIG. 3 is a flowchart showing the operation of the content reproducing device according to an embodiment and the content reproducing method according to an embodiment. [Figure 4] FIG. 4 is a flow chart showing a method for adjusting the number of video frames in step S8 of FIG. [Diagram 5] FIG. 5 is a block diagram showing an example of the configuration of a computer that executes a content reproduction program according to an embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS A content playback device, a content playback method, and a content playback program according to an embodiment will be described below with reference to the accompanying drawings.

[0012] FIG. 1 is a block diagram showing a content reproducing device according to an embodiment. In FIG. 1, the content reproducing device 100 includes a reproducing unit 1, a voice recognition unit 2, a translation unit 3, a text evaluation unit 4, a subtitle control unit 5, a video adjustment unit 6, a text image generation unit 8, a superimposition unit 9, a display unit 10, a voice reproduction adjustment unit 11, and a voice output unit 12. The display unit 10 and the voice output unit 12 may be external components of the content reproducing device 100. In this case, the display unit 10 and the voice output unit 12 are externally attached to the content reproducing device 100. The voice recognition unit 2, the translation unit 3, the text evaluation unit 4, the subtitle control unit 5, the video adjustment unit 6, the text image generation unit 8, the superimposition unit 9, and the voice reproduction adjustment unit 11 of the content reproducing device 100 may be configured, for example, in cooperation with a program, as a computer including a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), and the like.

[0013] The reproducing unit 1 reproduces content data including a video signal, an audio signal, and subtitle data. The content data is data including an audio signal, subtitle data, and a video signal, which is created, for example, in a DVD video format or a BDMV or BDAV format for a Blu-ray disc. The reproducing unit 1 may reproduce package media such as a DVD disc or a Blu-ray disc that records content data, or may reproduce content data stored in any storage medium such as a semiconductor memory. The reproducing unit 1 reproduces content consisting of video, audio, and subtitles by decoding content data encoded in a predetermined format according to the format. The reproducing unit 1 is specifically an optical disc reproducing device capable of reproducing optical discs such as a DVD disc or a Blu-ray disc.

[0014] The audio signal may include at least an English audio signal and a Japanese audio signal, and the language of the audio signal to be reproduced may be specified by the audio instruction signal. The audio signal may further include an audio signal translated into another language. In this case, the reproduction unit 1 selects the language of the audio signal to be reproduced by the audio instruction signal.

[0015] As an example, the audio signal includes dialogue in English (first language). The subtitle data includes, for example, at least subtitles translated from English into Japanese (second language). A subtitle instruction signal instructing whether or not to display subtitles is input to the playback unit 1 by an operation unit (not shown). When instructed to display subtitles by the subtitle instruction signal, the playback unit 1 supplies a video signal onto which the subtitle data instructed by the subtitle instruction signal is superimposed to the video adjustment unit 6.

[0016] The subtitle data may include at least English subtitles and Japanese subtitles, and may be configured such that the language of the subtitles to be displayed by the playback unit 1 can be specified by a subtitle instruction signal. The subtitle data may further include subtitles translated into other languages. In this case, the playback unit 1 selects the language of the subtitles to be displayed by the playback unit 1 by the subtitle instruction signal. Depending on the length of the English dialogue, the translation of the Japanese subtitles may be adjusted due to the limit on the number of characters that can be displayed per second. In this case, the English dialogue and the Japanese subtitles may not match.

[0017] The voice recognition unit 2 converts the voice signal of the lines in the language specified by the voice instruction signal into text data in the language specified by the voice instruction signal, and supplies the text data to the translation unit 3. The voice recognition unit 2 may be composed of a computer.

[0018] Fig. 2 is a block diagram showing a specific example of the configuration of the voice recognition unit 2. In Fig. 2, an acoustic analysis unit 21 extracts various features of an input voice signal, such as the frequency, strength, interval between adjacent sounds, and time series, and processes the voice signal so that a computer can easily recognize the voice. A phoneme extraction unit 22 refers to an acoustic model stored in an acoustic model 23 and extracts phonemes, which are the smallest units of sound waves. A language processing unit 24 refers to a language model stored in a language model 25, which pairs words and their pronunciations, and converts the phonemes into meaningful words to generate text data of lines. The acoustic model 23 and the language model 25 are compatible with at least English and Japanese, and may be compatible with other languages.

[0019] The voice recognition unit 2 is not limited to the configuration shown in FIG. 2 as long as it has a configuration for converting the voice of the lines into text data in the language specified by the voice instruction signal.

[0020] Returning to FIG. 1, the translation unit 3 supplies text data based on the audio signal in accordance with the instructions of the audio instruction signal and the instructions of the subtitle instruction signal to the text evaluation unit 4. If the language of the dialogue audio based on the instructions of the audio instruction signal is different from the language of the subtitles based on the instructions of the subtitle instruction signal, the translation unit 3 machine-translates the text data converted from the dialogue audio supplied from the speech recognition unit 2 into text data in the language of the subtitles based on the instructions of the subtitle instruction signal, and supplies the machine-translated text data to the text evaluation unit 4. If the language of the audio and the language of the subtitles are the same, the translation unit 3 supplies the text data converted from the dialogue audio supplied from the speech recognition unit 2 to the text evaluation unit 4 as is, without making any changes.

[0021] Machine translation is a method of automatically translating one language into another using a computer. Specifically, methods such as rule-based machine translation, statistics-based machine translation, and neural machine translation can be used.

[0022] If there is a difference of a predetermined number of characters or more between the number of characters in the text data in the subtitle language based on the subtitle instruction signal and the text data based on the audio signal supplied from the translation unit 3, the text evaluation unit 4 determines that the text data based on the audio signal should be displayed, and instructs the subtitle control unit 5, the video adjustment unit 6, and the text image generation unit 8 to display the text data based on the audio signal.

[0023] The text evaluation unit 4 acquires text data from the subtitle data of the content data. Specifically, if the content supports closed captions, the text evaluation unit 4 acquires text data directly from the closed caption data. Note that if the content does not support closed captions but supports subtitles (sub-screen images), the text evaluation unit 4 may acquire text data by performing image recognition on the subtitle images. Then, the text evaluation unit 4 detects a change in subtitles from a change in the acquired text data.

[0024] The text evaluation unit 4 compares the number of characters between the text data based on the subtitle data and the text data based on the audio signal each time the subtitles change. If the difference between the number of characters between the text data based on the subtitle data and the text data based on the audio signal is not a predetermined number of characters or more, the text evaluation unit 4 determines that the text data based on the subtitle data should be displayed, and instructs the subtitle control unit 5, the video adjustment unit 6, and the text image generation unit 8 to display the subtitles based on the subtitle data.

[0025] The text evaluation unit 4 may compare the number of syllables per word in the text data based on the subtitle data with the number of syllables per word in the text data based on the audio signal, and if there is a difference of a predetermined number or more in the number of syllables, may instruct the subtitle control unit 5, the video adjustment unit 6, and the text image generation unit 8 to display the text data based on the audio signal. Note that, if there is a difference of a predetermined number of characters between the text data based on the subtitle data and the text data based on the audio signal, the number of characters in the text data based on the subtitle data is often less than the number of characters in the text data based on the audio signal by a predetermined number of characters or more, and the same is true for the comparison of the number of syllables. Note that the number of syllables is the number of syllables when the text is a spoken voice, or the number of moras, which are a segmentation unit of phonemes having a predetermined time length.

[0026] The text evaluation unit 4 may compare the contents of the text data based on the subtitle data with the contents of the text data based on the audio signal, instead of comparing the number of characters between the text data based on the subtitle data and the text data based on the audio signal, and if the contents differ by a predetermined percentage or more, instruct the subtitle control unit 5 to display the text data based on the audio signal. It is possible to determine whether the contents of the text data based on the subtitle data differ from the contents of the text data based on the audio signal by comparing the contents of the text data based on the subtitle data with the contents of the text data based on the audio signal. Note that the comparison of the contents of the text data can be performed using a method such as BoW (Bug of Words), which compares the contents of the text data based on the number of occurrences of words obtained by morphological analysis of natural language.

[0027] The subtitle control unit 5 controls the display of subtitles by the playback unit 1 based on a comparison between the text data of the subtitle data by the text evaluation unit 4 and the text data based on the audio signal. When instructed by the text evaluation unit 4 to display the text data based on the subtitle data, the subtitle control unit 5 controls the playback unit 1 to display the subtitles based on the subtitle data. When instructed by the text evaluation unit 4 to hide the text data based on the subtitle data, the subtitle control unit 5 controls the playback unit 1 to hide the subtitles based on the subtitle data.

[0028] The video adjustment unit 6 adjusts the number of video frames based on a comparison made by the text evaluation unit 4 between the text data of the subtitle data and the text data based on the audio signal, and supplies the video signal with the adjusted number of video frames to the superposition unit 9. The video adjustment unit 6 stores the video signal supplied from the playback unit 1 in a memory such as a ring buffer (not shown), and adjusts the number of video frames by changing the read address of the video signal stored in the memory in response to an instruction from the text evaluation unit 4.

[0029] When the text evaluation unit 4 issues an instruction to display text data based on an audio signal, the video adjustment unit 6 analyzes the speaker's mouth movement from the feature amount of each video frame and identifies video frames with no or almost no speaker's mouth movement. The video adjustment unit 6 adjusts the number of video frames so as to repeat or skip frames with no or almost no speaker's mouth movement.

[0030] When adjusting the number of video frames so as to repeat video frames, the video adjustment unit 6 repeats the process of reading out the video signal from the read address of the predetermined video frame identified as having no or almost no mouth movement of the speaker.When adjusting the number of video frames so as to skip video frames, the video adjustment unit 6 skips the process of reading out the video signal from the read address of the predetermined video frame identified as having no or almost no mouth movement of the speaker, and resumes the process of reading out the video signal from the read address next to the skipped read address.

[0031] The video adjustment unit 6 does not adjust the number of video frames when the text evaluation unit 4 instructs to display text data based on the subtitle data. When the video signal is coded according to the MPEG standard, the video adjustment unit 6 preferably repeats or skips frames in units of GOPs (Group of Pictures) (e.g., 0.5 seconds) for a specific video frame that has been identified as having no or almost no mouth movement of a speaker.

[0032] When the text evaluation unit 4 issues an instruction to display text data based on an audio signal, the video adjustment unit 6 adjusts the number of video frames taking into consideration the number of characters a person can read in a given time (hereinafter, the maximum number of characters). The maximum number of characters is, for example, 4 characters per second for Japanese and 12 characters per second for English. The video adjustment unit 6 calculates the adjustment number of video frames based on the maximum number of characters and the number of characters that is the difference between the text data based on the subtitle data and the text data based on the audio signal. The video adjustment unit 6 may, for example, set the adjustment number of video frames to an integer value obtained by dividing the number of characters that is the difference in the text data by the maximum number of characters.

[0033] When the text data based on the audio signal is longer than the text data based on the subtitle data, the video adjustment unit 6 repeats the process of reading out the video signal from the read address of the frame of the predetermined video identified as having no or almost no movement of the speaker's mouth in accordance with the adjustment number of the video frames, thereby increasing the number of video frames. When the text data based on the audio signal is shorter than the text data based on the subtitle data, the video adjustment unit 6 skips the process of reading out the video signal from the read address of the frame of the predetermined video identified as having no or almost no movement of the speaker in accordance with the adjustment number of the video frames, and resumes the process of reading out the video signal from the read address next to the skipped read address, thereby reducing the number of video frames. Note that the video adjustment unit 6 does not adjust the number of video frames when the adjustment number of the video frames is less than 1.

[0034] When the video adjustment unit 6 adjusts the number of video frames, it supplies the adjusted number of video frames to the audio reproduction adjustment unit 11. Specifically, when the number of video frames is adjusted to be increased by 3, the video adjustment unit 6 supplies the increased adjusted number of video frames as "+3" to the audio reproduction adjustment unit 11. Also, when the number of video frames is adjusted to be decreased by 3, the video adjustment unit 6 supplies the decreased adjusted number of video frames as "-3" to the audio reproduction adjustment unit 11. The adjusted number of video frames supplied to the audio reproduction adjustment unit 11 is not limited to the number of video frames, and may be a time calculated from the number of video frames.

[0035] The text image generation unit 8 generates a subtitle text image in accordance with an instruction from the text evaluation unit 4, and supplies the generated subtitle text image to the superimposition unit 9. When instructed by the text evaluation unit 4 to display text data based on an audio signal, the text image generation unit 8 generates a subtitle text image based on the text data based on the audio signal, and supplies the generated subtitle text image to the superimposition unit 9. When instructed by the text evaluation unit 4 to display text data based on an audio signal, the text image generation unit 8 does not supply the subtitle text image to the superimposition unit 9.

[0036] The superimposition unit 9 superimposes the subtitle text image generated by the text image generation unit 8 on the video of each frame of the video signal supplied from the video adjustment unit 6 and supplies the result to the display unit 10. When the superimposition unit 9 is supplied with a subtitle text image from the text image generation unit 8, the superimposition unit 9 superimposes the subtitle text image on the video of each frame and supplies the result to the display unit 10. When the superimposition unit 9 is not supplied with a subtitle text image from the text image generation unit 8, the superimposition unit 9 supplies the video signal supplied from the video adjustment unit 6 to the display unit 10 as is.

[0037] The display unit 10 displays an image based on the video signal supplied from the superimposing unit 9. The display unit 10 can be configured, for example, by a liquid crystal panel.

[0038] The audio reproduction adjustment unit 11 adjusts the playback position of the audio signal according to the adjusted number of video frames supplied from the video adjustment unit 6, and supplies the audio signal with the adjusted playback position to the audio output unit 12. The audio reproduction adjustment unit 11 stores the audio signal supplied from the reproduction unit 1 in a memory such as a ring buffer (not shown), and adjusts the playback position of the audio signal by changing the read address of the audio signal stored in the memory according to the adjusted number of video frames supplied from the video adjustment unit 6.

[0039] When the adjusted number of video frames supplied from the video adjustment unit 6 is adjusted to increase, the audio reproduction adjustment unit 11 stops the process of reading out the audio signal from a predetermined read address for a period corresponding to the adjusted number of video frames to be increased, or repeats the process of reading out the audio signal from a predetermined read address for a period corresponding to the adjusted number of video frames to be increased. When the adjusted number of video frames supplied from the video adjustment unit 6 is adjusted to decrease, the audio reproduction adjustment unit 11 discards the read address of the audio signal for a period corresponding to the adjustment of the video frames to be decreased, and reads out the audio signal from the read address next to the discarded read address.

[0040] The audio output unit 12 outputs the audio whose reproduction has been controlled by the audio reproduction adjustment unit 11. The audio output unit 12 can be composed of a speaker.

[0041] Fig. 3 is a flowchart showing the operation of the content playback device according to an embodiment and the content playback method according to an embodiment. The operation of the content playback device 100 and the content playback method executed by the content playback device 100 will be described with reference to the flowchart shown in Fig. 3. First, a case where the audio language and the subtitle language are different (the dialogue audio is in English and the subtitles are in Japanese) will be described.

[0042] 3, when the processing of the content playback device 100 is started, the playback unit 1 plays back the content data in step S1. The voice recognition unit 2 converts the dialogue voice into text data in the voice language based on the instruction of the voice instruction signal in step S2. The translation unit 3 determines whether the voice language and the subtitle language are different in step S3. If the voice language and the subtitle language are different (YES), the translation unit 3 performs machine translation in step S4 of the text data based on the voice signal converted from the dialogue voice into text data in the subtitle language based on the instruction of the subtitle instruction signal.

[0043] In step S5, the text evaluation unit 4 determines whether the difference in the number of characters between the text data based on the subtitle data and the text data based on the audio signal is equal to or greater than a predetermined number of characters. If the difference in the number of characters between the text data based on the subtitle data and the text data based on the audio signal is equal to or greater than the predetermined number of characters (YES), in step S6, the subtitle control unit 5 controls the playback unit 1 to not display the subtitles based on the subtitle data, and transitions the process to step S7. In step S7, the text image generation unit 8 generates a subtitle text image in accordance with the instruction from the text evaluation unit 4.

[0044] In step S8, the image adjustment unit 6 analyzes the movement of the speaker's mouth from the feature amount of each frame of the image, and adjusts the number of frames of the image so as to repeat or skip frames with no or almost no movement of the speaker's mouth.

[0045] Fig. 4 is a flowchart showing a method for adjusting the number of video frames in step S8 in Fig. 3. The specific processing content of step S8 will be described using the flowchart shown in Fig. 4. In step S81, video adjustment unit 6 calculates the adjustment number of video frames from the number of characters that is the difference between the text data based on the subtitle data and the text data based on the audio signal. In step S82, video adjustment unit 6 analyzes the speaker's mouth movement from the feature amount of each video frame, and identifies video frames with no or almost no speaker's mouth movement.

[0046] In step S83, the image adjustment unit 6 adjusts the number of image frames according to the adjustment number of image frames calculated in step S81 so as to repeat or skip frames of the image in which there is no or almost no movement of the speaker's mouth.

[0047] Returning to Fig. 3, in step S9, the audio playback adjustment unit 11 adjusts the playback position of the audio signal according to the adjusted number of video frames. In step S10, the display unit 10 displays the video of each frame on which the subtitle text image is superimposed, and then proceeds to step S11.

[0048] On the other hand, if the difference in the number of characters between the text data based on the subtitle data and the text data based on the audio signal is not equal to or greater than the predetermined number of characters in step S5 (NO), the subtitle control unit 5 controls the playback unit 1 to display subtitles based on the subtitle data in step S12, and the process proceeds to step S10. In this case, the display unit 10 displays the video of each frame in which the subtitles based on the subtitle data are displayed in step S10, and the process proceeds to step S11.

[0049] In step S11, the playback unit 1 determines whether or not an instruction to end content playback has been given. If an instruction to end content playback has not been given (NO), the content playback device 100 repeats the processes from step S1 onward. If an instruction to end content playback has been given (YES), the content playback device 100 ends the process.

[0050] Next, the case where the audio language and the subtitle language are the same (when the dialogue and subtitles are both in English) will be described. Since the translation unit 3 determines in step S3 that the audio language and the subtitle language are not different (NO), the text evaluation unit 4 determines in step S5 whether the difference in the number of characters between the text data based on the subtitle data and the text data based on the audio signal converted from the dialogue audio is equal to or greater than a predetermined number of characters. If the difference in the number of characters between the two is equal to or greater than a predetermined number of characters (YES), the process proceeds to step S6 and subsequent steps. Step S6 and subsequent steps are the same as when the dialogue is in English and the subtitles are in Japanese.

[0051] On the other hand, if the difference in the number of characters between the two is not equal to or greater than the predetermined number of characters in step S5 (NO), the subtitle control unit 5 controls the playback unit 1 to display subtitles based on the subtitle data in step S12, and moves the process to step S10. Step S10 and subsequent steps are the same as when the dialogue is in English and the subtitles are in Japanese.

[0052] The content playback device 100 shown in Fig. 1 can be realized by a central processing unit (CPU) of a microcomputer executing a content playback program. Fig. 5 shows a content playback device 100' that plays back content data by a CPU executing the content playback program. The content playback device 100' shows an example of the configuration of a computer that executes the content playback program according to one embodiment.

[0053] 5, the content data reading unit 20 is a data reading unit for any storage medium such as a package media drive device or a semiconductor memory. A CPU 30, a main memory 50, and a storage medium 40 are connected by a bus. The content data reading unit 20 and the CPU 30 may be connected by a bus. The storage medium 40 is any non-transitory storage medium such as a hard disk drive, an optical disk, or a semiconductor memory. A content playback program is stored in the storage medium 40.

[0054] The CPU 30 loads the content reproduction program stored in the storage medium 40 into the main memory 50. The CPU 30 executes each instruction written in the content reproduction program loaded into the main memory 50.

[0055] The CPU 30 reads the content data from the content data reading unit 20, and decodes and plays back the content data. The CPU 30 operates in the same manner as the playback unit 1 to the superimposition unit 9 and the audio playback adjustment unit 11 in Fig. 1. The CPU 30 executes the same process as in Fig. 3, supplies a video signal of the playback content signal to the display unit 10 not shown in Fig. 5, and supplies an audio signal of the playback content signal to the audio output unit 12 not shown in Fig. 5.

[0056] The present invention is not limited to the above-described embodiment, and various modifications are possible without departing from the gist of the present invention. [Explanation of symbols]

[0057] 1 Playback section 2. Voice Recognition Unit 3. Translation Department 4 Text Evaluation Section 5 Subtitle control section 6 Image adjustment section 8 Text image generator 9. Overlapping section 10 Display section 11 Audio playback adjustment section 12 Audio output section 20 Content data reading unit 30 Central Processing Unit 40 Storage medium 50 Main memory 100,100' Content playback device

Claims

1. a playback unit that plays back content data; a voice recognition unit that converts a voice signal in a first language included in the content data into text data in the first language; a translation unit that generates text data in a second language by translating the text data in the first language into a second language different from the first language; a text evaluation unit that compares text data in the second language included in the content data with text data translated into the second language; a text image generating unit that generates a subtitle text image based on the text data translated into the second language based on the comparison of the text data by the text evaluating unit; A content playback device comprising:

2. 2. The content reproducing device according to claim 1, further comprising a video adjustment unit that adjusts the number of frames of a video signal in accordance with the number of characters of the text data translated into the second language.

3. The content reproducing device according to claim 2 , further comprising an audio reproduction adjustment unit that adjusts a reproduction position of the audio signal of the first language in accordance with the number of frames of the video signal.

4. The playback unit plays back the content data, a voice recognition unit converts a voice signal in a first language included in the content data into text data in the first language; a translation unit generating text data in a second language by translating the text data in the first language into a second language different from the first language; a text evaluation unit that compares the text data in the second language included in the content data with the text data translated into the second language; A text image generating unit generates a subtitle text image based on the text data translated into the second language based on the comparison of the text data by the text evaluating unit. How to play content.

5. On the computer, playing content data; converting a voice signal in a first language included in the content data into text data in the first language; generating text data in a second language by translating the text data in the first language into a second language different from the first language; comparing text data in the second language included in the content data with text data translated into the second language; generating a subtitle text image based on the text data translated into the second language based on the comparison of the text data; A content playback program that executes the above.

Images