KR20050090398A - Method and apparatus for selectable rate playback without speech distortion - Google Patents

Abstract

A method and an apparatus for selectable rate playback of a selected first portion of a separately stored synchronized video and audio content, without distortion of speech due to the selectable rate playback of the playback content and without loss of synchronization of the selected first portion of a separately stored synchronized video and audio content.

Description

TECHNICAL AND APPARATUS FOR SELECTABLE RATE PLAYBACK WITHOUT SPEECH DISTORTION}

The present invention relates generally to the field of television. More particularly, the present invention relates to an apparatus and method for playing television programs at selectable speeds without distorting the audio portion of the program.

It is known to play video content at selectable speeds from various storage media such as video cassette recorders (VCRs). The audio portion of the playback content can be suppressed during playback at a selectable rate to avoid distortion of the audio portion. There is a need to reproduce the audio portion of the playback content without distortion while playing back at a selectable speed. Then, the "distortion" of the audio portion of the reproduced content means that the reception or reproduction fidelity is lowered due to a change in the reproduction speed of the audio portion of the reproduced content as compared to the rate of storing the audio portion of the reproduced content.

1 illustrates the functionality and logic of an apparatus for starting playback of a playback content at a selectable speed, ie for starting normal viewing, in accordance with an embodiment of the present invention.

2 illustrates the functionality and logic of an apparatus for playing playback content at a selectable speed in accordance with an embodiment of the present invention.

3 shows a playlist for selecting a first portion of separately stored synchronized video and audio playback content.

4 illustrates a graphical user interface (GUI) for selecting a first portion of separately stored synchronized video and audio playback content.

5 illustrates a method for playing playback content at a selectable speed in accordance with an embodiment of the present invention.

The present invention provides a method of playing a playback content at a selectable speed.

Selecting a first portion of separately stored video and audio playback content, wherein the playback content is stored at a storage rate, the video and audio are synchronized as stored, and the separately stored synchronized video and audio content is synchronized Selecting a first portion, retrievable for playback, the first portion;

Selecting a playback speed of the playback content from the selectable speed, wherein the selected playback speed is different from the storage speed;

Tagging voice on the selected first portion of the playback content;

Recognizing at least one phrase within the tagged voice;

Playing the first portion of playback content at the playback speed, wherein the play simultaneously searches for the tagged voice, and the playback at the playback speed is performed even if the playback speed is different from the storage speed; Playing a first portion, not causing distortion of voice in the playback content, wherein the video and audio are synchronized at the playback speed during the play

It provides a method for playing the playback content at a selectable speed, including.

A second embodiment of the present invention is an apparatus for playing a playback content at a selectable speed,

Separately stored video and audio playback content, the playback content being stored at a storage rate;

The selected first portion of the separately stored video and audio playback content in a storage medium, wherein the selected first portion of the video and audio content is synchronized and the voice portion of the audio content is tagged and;

A speech recognition device for tagging speech portions of the audio content;

A phrase recognition device for determining valid words for phrases from the tagged speech, the valid words being connected within the phrase;

A playback device for playing the selected first portion of the playback content at a selected speed from the selectable speed, wherein the selected speed is different from the storage speed, and playback at the selected speed is tagged with the audio content Searching for a voice part simultaneously, playback at the selected speed does not cause distortion of the voice in the playback content, even if the selected speed is different from the storage speed, and the video and audio content is Playback device, synchronized at the selected speed

Disclosed is an apparatus for playing a playback content at a selectable speed, including.

The present invention provides for playing back the audio portion of the playback content without distortion during playback at a selectable speed.

While certain preferred embodiments of the invention have been illustrated and described in detail, it goes without saying that various changes and modifications may be made without departing from the scope of the appended claims. Thus, the scope of the present invention should never be limited by the number of its components, its material, its shape, its relative arrangement, etc., which is merely disclosed as an example of the preferred embodiment. The features and advantages of the invention are illustrated in detail in the accompanying drawings, wherein like reference numerals refer to like elements throughout. Although the drawings are intended to illustrate the invention, they are not necessarily drawn to scale.

The present invention relates generally to the field of television. More specifically, the present invention relates to an apparatus and method for playing selected video and audio playback content at a selectable speed without distorting the voice due to playing the playback content at a selectable speed.

FIG. 1 is a flow diagram 70 in FIG. 5 and described herein, according to a method for playing playback content at a selectable speed and in accordance with an embodiment of the present invention. A flow diagram illustrating the functional and logical description of the device 10 for playback at a possible speed. 1 illustrates that a user may continue normal viewing 61 such as viewing independently of this device 10 or may “start” playback at a selectable speed in step 65. "Starting" playback 65 of playback content at a selectable speed includes three inputs, namely "stop" 64 inputs of playback at a selectable speed; Input of “pause” 67 of playback at a selectable speed; And " selected speed " 49 input. The user may choose to provide these inputs 64, 67, 49 from a programmable logic controller (PLC) with appropriate software or alternatively from a central processing unit (CPU).

In one embodiment, when determining that playback has not been paused at decision step 55 and determining that playback has not been stopped at decision step 50, the user may at step 65 by providing an input of " selected speed " Playback can be started at a selectable speed. The input "Selected Speed" 49 may slow down or speed up the playback speed used to store the playback content. In one embodiment, the "selected rate" 49 ranged from about 50% to about 150% of the rate used for storing playback content or for any other reason. However, the user may select any suitable " selected speed " 49 which allows the viewer or listener of the playback content to play the selected separately stored synchronized video and audio playback content 1, which can be more clearly or clearly understood. Can be. The "selectable speed" or "selectable speed" then stores the selected separately stored synchronized video and audio playback content 1 without distortion of the voice in the playback content, as shown in FIG. 2 and described below. Means increasing or decreasing the playback speed or speed of the selected separately stored synchronized video and audio playback content 1 relative to the storage speed or speed. This playback can be paused by providing a "pause" input 67 at decision step 55. This playback can be stopped by providing a "stop" input 64 to decision step 50. When playback is shown on an audio and video device such as, for example, a television and playback is stopped by providing a "pause" input 67 for a time longer than "x" minutes, or playback is stopped When stopped by providing a "stop" input 64, normal viewing 61 can be made on the audio and video device. Normal viewing 61 then refers to the operation or television operation of any suitable audio and video viewing device, for example, irrespective of the apparatus or method for playback at a selectable rate of the present invention. When playback is stopped for longer than "x" minutes, a "pause" input 67 is provided to decision step 53 to allow normal viewing 61. Alternatively, if playback is not stopped for longer than "x" minutes, the "pause" input 67 returns to decision step 55 and then when the "pause" input 67 is removed again. Return to decision step 53 until. If the pause input 67 is removed, the device 10 proceeds to step 65 to "start" playback at a selectable speed. In one embodiment, "x" is less than two (2) minutes. Alternatively, "x" may be a time period less than five (5) minutes. The value of "x" is any positive real number representing the number of minutes the user wants to wait to automatically return to normal viewing 61 after the "pause" input 67 is provided to the device 10. Can be.

In one embodiment, in decision step 50 it may be determined whether or not a “stop” input 64 has been provided, allowing normal viewing 61. If yes in decision step 50, normal viewing 61 is possible. Alternatively, if the "stop" 64 input is not passed to decision block 50, the device 10 moves to step 65 to "start" playback at a selectable rate.

FIG. 2 is an extension of the apparatus 10 of FIG. 1, including in accordance with a method for playing playback content at a selectable speed, as shown in the flow chart 70 in FIG. 5 and described later. According to an embodiment of the invention, the selection and tagging portion 9; A phrase and token recognition portion 2; And the addition of the portion 4 to reproduce at a selectable speed.

The selection and tagging portion 9 allows for playback at the selectable speed of FIG. 1, in accordance with an embodiment of the present invention, including in accordance with steps 75 and 90 of the flowchart 70 illustrated in FIG. 5 and described later. A step 65 of "starting" comprises a selection engine 13 provided. In addition to receiving a "start" 65 input, the selection engine 13 also receives input from separately stored synchronized video and audio content 1, a playlist 109, and a graphical user interface 16. can do.

During the search, the selection engine 13 provides the audio recognition and tagging system 12 with audio content synchronized with the video content, tagging portions of the content 1 that are speech and portions that are noisy and tagged. (7) The storage medium and tagged noise 23 are provided in the storage medium. The speech recognition and tagging system 12 also enters individual words or tokens into the tagged voice 7. A "token" is then a contiguous group of non-delimiter characters that appear in a string preceding the delimiter (or at the beginning of this string), where delimiter is an example. For example, it may be a punctuation form such as a comma or a space between words. Then, "synchronization" of a word or phrase written in voice or text with video content means that words are pronounced or written with the corresponding video content when the video content is displayed. Audio content synchronized with video content is available because the synchronized video and audio content 1 are stored separately and the separately stored synchronized video and audio content 1 can be retrieved for synchronized playback. Do.

Referring to FIG. 2, the phrase and token recognition portion 2 of the device 10 includes a decision step 29 for determining valid words for the phrase, where the decision is a test for validity. It is based on acceptable word 21 input and phrase database 42 input. The word "word" or "speech" shall then mean English or any other language written or spoken in letters. This decision 29 provides the output to the word concatenation step 31 in the phrase. The test allowable word 21 for validity may receive the input pronunciation rule 39. Here, the test allowable word 21 for validity may use a pronunciation rule so that the valid words are pronounced correctly at the time of reproduction. Then, "pronouncing correctly" means correcting a voice for pronunciation error due to accent or wrong pronunciation. Consecutive valid words and phrase database 42 are entered into decision step 29 to determine whether the consecutive valid words are valid words for the phrase. If yes, successive valid words for the phrase are entered into the word concatenation 31 step in the phrase. If no, successive valid words for the phrase are entered into the stored playback content buffer 37 as invalid words for the phrase. Decision step 29 may apply a process that may include comparing the phrase database 42 with this consecutive valid word. Valid words that exist in a phrase database 42, such as a phrase, may be linked to a step in word phrase 31 in a phrase. Dictionaries, Lexicons, and the like are examples of the phrase database 42. Some examples of phrases include phrases such as "good morning" where the constituent words are often used together. Since the words of the phrase need to be pronounced together, the words of the phrase are pronounced together when the corresponding video content of the separately stored synchronized video and audio content 1 is played. The user may also have the option to enter additional words or rules into the test allowable word 21 for validity so that other words that are not part of the set language may also be linked together in the phrase in step 31.

Referring to FIG. 2, the portion 4 for playing back at a selectable speed includes a stored playback content buffer 37, an engine 67 for playing back at a selectable speed, and a viewing 73 for playing back at a selectable speed. Include. The phrase may be transferred from the word concatenation step 31 in the phrase into the stored playback content buffer 37. Alternatively, the valid word may be provided to the stored playback content buffer 37 when it is determined in decision step 29 that it is not a valid word for the phrase. Alternatively, noise 23 can be delivered to the stored playback content buffer 37. In one embodiment, the engine 67 for playing back at a selectable speed provides the engine 67 for playing back the stored playback content buffer 37 at a selectable speed. The engine 67, which plays back at a selectable speed, passes to the viewing step 73, which plays back at a selectable speed for viewing 73, which plays back at a selectable speed of the selected separately stored synchronized video and audio playback content 1 selected. Provide input. One purpose of the viewing 73 to reproduce at a selectable speed is related to when the scene content in the video program is unclear or when the user does not understand the spoken word. In the example where the user does not clearly understand the spoken word, the validity of the test allowable word 21 is to use a pronunciator device that correctly pronounces the word or phrase after entering the pronunciation rule 39. Can be. Thus, words incorrectly pronounced by an actor can be correctly pronounced by the pronunciation device. The user may be provided with an option as to whether the valid word should use the pronunciation device for pronunciation or, for example, as if spoken by the actor in a video program.

3 shows an example of the list 110 of reproduction contents from the reproduction list 109. This playlist includes a playlist item 120 of "y" minutes, where y represents the time from when separately stored synchronized video and audio content 1 (see FIG. 2) was stored. The time from when the separately stored synchronized video and audio content 1 is stored depends on the storage capacity of the stored playback content buffer 37, as shown in FIG. 2 and described herein. The storage capacity of this stored playback content buffer 37 may be any suitable capacity needed to accommodate separately stored synchronized video and audio content 1. In one embodiment, the storage capacity of the stored playback content buffer 37 is less than two minutes. Alternatively, the storage capacity of the stored playback content buffer 37 may be less than 5 minutes. Alternatively, the storage capacity of the stored playback content buffer 37 may be the capacity required to store separately stored synchronized video and audio content 1 of a movie or video program, where the video program may be a television program.

The playlist 109 is a keyword that can be generated by the user based on keywords or phrases that the user memorizes from listening to or watching a program or movie included in the separately stored synchronized video and audio content 1. The phrase list item 130 is included.

The playlist 109 includes a key frame list item 140, where each entry of the key frame list item 140 may be selected by subtracting the intensity "z" of each of two consecutive frames, If the difference "Δz" of the intensity "z" between successive frames is larger than the threshold "t", the frame having the higher intensity is selected as the key frame. The user can select the list item 120, 130, or 140 via the remote selection device or manually. Selecting list item 120, 130, or 140 may provide input to selection engine 13.

4 shows a list of playback content from a graphical user interface (GUI) 16, where this list is identical to the corresponding list items 120, 130, and 140, as shown in FIG. 3 and described above. A play list item 160 for "y", a keyword or phrase list item 170, and a key frame list item 180 generated in a manner. The playback content list from this GUI 16 includes a scroll bar 190 that can be used to scroll to list items 160, 170, or 180. The user can select list item 160, 170, or 180 manually or via a remote selection device. Selecting this list item 160, 170, or 180 can provide input from the GUI 16 to the selection engine 13 (see FIG. 2). Graphical user interface 16 may be provided with a list of key video frames using key frame extraction. "Key frame extraction" then means that a key frame having an intensity higher than the threshold strength is selected from the GUI 16 into the list of playback content.

5 shows a method 70 for playing playback content at a selectable speed, comprising steps 75, 85, 90, 95, and 97. FIG. In one embodiment, a television program or, alternatively, a movie may be stored on a personal video cassette recorder, DVD, or any suitable storage medium, such as optical or magnetic optical media. The program or movie must be separately stored synchronized video and audio content 1 (see FIG. 2), where the video and audio are synchronized as stored, and the separately stored synchronized video and audio content 1 is synchronized. Searchable for playback. While playing the separately stored synchronized video and audio content 1, the user may encounter program parts that may not be satisfactorily understood, such as because the video part is unclear or the audio part is incomprehensible. At this time, the user first stops playback. In step 75, the user selects a first portion 44 of synchronized video and audio playback content 1 that is stored separately for playback at “selected rate” 49, wherein the selected first portion 44 is It corresponds to the list item 120, 130, or 140 from the play list 109 of FIG. 3, or corresponds to the list item 160, 170, or 180 from the GUI 16 of FIG. The playback content 1 is stored at a storage speed, where the storage speed can be any recording speed for commercial personal video cassette recorders, DVDs, or any suitable storage medium such as optical or magnetic optical media, And this storage rate may be different from the "selected rate" 49. This "selected speed" 49 may be slower or faster than the storage speed for the playback content 1 without distortion of the voice portion of the audio content of the playback content 1.

In step 85, the selected first portion 44 of the separately stored synchronized video and audio playback content 1 corresponding to the list item selected from the playback content from the graphical user interface 16 or the playlist 109 (see FIG. 2). The voice contained in) is tagged by the speech recognition and tagging system 12. In step 90, the acceptable word 7 is recognized by the speech recognition and tagging system 12 (see FIG. 2).

In step 95, at least one phrase in the tagged voice 7 is recognized by the phrase and token recognition portion 2 (see FIG. 2) of the device 10.

In step 97, the selected first portion 44 (see FIG. 2) of the separately stored synchronized video and audio content 1 is selected and tagged engine 65 because the video and audio content are synchronized and stored separately. (See FIG. 1), where the tagged voice 7 and the corresponding video are successively provided, thereby providing separately stored synchronized video and audio content (1) for play. Selecting the first portion 44 (see FIG. 2) of C.sub.2 results in selecting the corresponding tagged voice 7 for play.

The voice may be tagged by the voice recognition and tagging system 12 as shown in FIG. 2 and described in the associated text described above. At least one phrase within the tagged voice 7 may be recognized using the speech recognition system and the tagging system 12, for example, as described in the relevant text shown in FIG. 2 and described above. Can be. The speech recognition and tagging system 12 may use stemming to remove morphological and inflexional endings from English words from the playback content 1. "Stemming" may then be done by a Porter stemming apparatus (or 'porter stemmer'), a process for removing more general morphological and morphological endings from English words. . Its main use is as part of the term normalization process that is commonly performed when setting up information retrieval systems. The "morphological endings" for English words are then verb tense, such as past, present, or future, and the "inflexional endings" for English words are "s." Nouns or verbs such as "es," or "ing", or "er", "ier", "iest" for adjectives of comparative and superlatives.

The selected first portion 44 (see FIG. 2) of the separately stored synchronized video and audio playback content 1 corresponding to the list item selected from the playback content from the graphical user interface 16 or the playlist 109 is selectable. It can be played at speed, the play simultaneously searching for tagged voices 7 such as acceptable words. Playing selected first portion 44 of separately stored synchronized video and audio playback content 1 corresponding to a list item selected from playback content from graphical user interface 16 or playlist 109 at a selected rate There is no distortion in the voice in (1) (see FIG. 2). This video and audio will be synchronized at a selectable speed according to the method as shown by the flow chart 70 in FIG. 5 and described above and according to an embodiment of the invention.

As described above, the present invention can be used for playing back a television program at a selectable speed or the like without distorting the audio portion of the program.

Claims (20)

A method for playing playback content at a selectable speed, Selecting a first portion of separately stored video and audio playback content, wherein the playback content is stored at a storage rate, the video and audio are synchronized as stored, and the separately stored synchronized video and audio content is synchronized Selecting a first portion, retrievable for playback, the first portion; Selecting a playback speed of the playback content from the selectable speed, wherein the selected playback speed is different from the storage speed; Tagging voice on the selected first portion of the playback content; Recognizing at least one phase within the tagged voice; Playing the first portion of playback content at the playback speed, wherein the play synchronizes to retrieve the tagged voice, wherein play at the playback speed is different from the storage speed Even if it does not cause distortion of the voice in the playback content, the video and audio being reproduced at the playback speed during the play, the first part being reproduced. Including the playback content at a selectable speed. The method of claim 1, wherein the first portion of the playback content is selected for playing from a playlist. The method of claim 1, wherein the first portion of the playback content is selected for playing from a graphical user interface. 4. The method of claim 3, wherein the graphical user interface includes a list of key video frames provided by key frame extraction. 2. The method of claim 1, wherein tagging the voice further comprises recognizing a plurality of valid words for a phrase in the tagged voice. The method of claim 1, wherein the playback speed is less than the storage speed. The method of claim 1, wherein recognizing at least one phrase within the tagged speech is by speech recognition. The method of claim 1, further comprising removing commoner morphological and inflexional endings from English words from the reproduced content by removing the stem. Way. 10. The method of claim 9, wherein a key frame in the list of key video frames has an intensity higher than a threshold intensity. The playback content of claim 1, wherein the tagged voice and its corresponding video are continuously provided while storing the playback content and playing the first portion of the playback content at the playback speed. How to play. The audio and video device of claim 1, wherein the playing of the first portion of the playback content at the playback speed is performed such that normal viewing of an audio and video device occurs when the play is stopped by a stop input. And playing back at a selectable speed. 2. The method of claim 1, wherein playing the first portion of playback content at the playback speed is greater than x minutes when the play is stopped by a pause input, wherein the play is any positive real number. Playing on an audio and video device such that when stopped for more time, normal viewing of the audio and video device occurs. An apparatus for playing playback content at a selectable speed, the device comprising: Separately stored video and audio playback content, the playback content being stored at a storage rate; The selected first portion of the separately stored video and audio playback content in a storage medium, wherein the selected first portion of the video and audio content is synchronized and the voice portion of the audio content is tagged and; A speech recognition device for tagging speech portions of the audio content; A phrase recognition device for determining valid words for phrases from the tagged speech, the valid words being connected within the phrase; A playback device for playing the selected first portion of the playback content at a selected rate from the selectable rate, wherein the selected rate is different from the storage rate and playback at the selected rate is tagged with the audio content Synchronized search for the portion of the speech, wherein playback at the selected rate does not cause distortion of speech in the playback content, even if the selected rate is different from the storage rate, and the video and audio content Playback device, synchronized at the selected speed during playback And playback the playback content at a selectable speed. The device of claim 13, wherein the playback device for playing the selected first portion of the playback content at the selected rate further comprises a playlist of the selected first portion of separately stored synchronized video and audio playback content. And apparatus for playing the playback content at a selectable speed. The device of claim 13, wherein the playback device for playing the selected first portion of the playback content at the selected rate further comprises a graphical user interface of the selected first portion of separately stored synchronized video and audio playback content. And playback the playback content at a selectable speed. 16. The playback content of claim 15, wherein the graphical user interface includes a key frame list item, wherein each frame of the key frame list item has an intensity that is different from the intensity of frames that are contiguous by a value that exceeds a threshold. Device for playing back at a selectable speed. 15. The device of claim 13, wherein the phrase recognition device for determining valid words for phrases from the tagged speech includes join words into phrases step. Device for playing at speed. 15. The speed of claim 13, wherein the phrase recognition device for determining a valid word for a phrase from the tagged voice comprises a pronunciation rule input for causing the valid word to be pronounced correctly upon playback. Device for playing with. 15. The apparatus of claim 13, wherein the video content is within a video frame. 15. The apparatus of claim 13, wherein the selected playback rate is slower than the storage rate, and play at the selected playback rate is voiced in the playback content even when the selected rate is slower than the storage rate of the playback content. Apparatus for playing back playback content at a selectable speed that does not cause distortion.