201027377 六、發明說明: 【發明所屬之技術領域】 本發明係有關於-種聽聲彩㈣統,特別指使用者 將聲音輸入並轉換為圖畫影像輸出者。 【先前技術】 按,目前習知技術並無透過聲音來產生圖像畫作的方 法,因此,有中華民國專利第1272511號「動畫生成系統 癰以及方法」’其提供預先儲存有音頻訊號解析規則、音包單 元與發音之對應表以及發音與動晝嘴形參數之對應表的資 料庫,並透過解析機制依據該音頻訊號解析規則將接收到 的音頻訊號予以解析成至少一個音包單元,再藉由辨識機 制依據該音包單元與發音之對應表辨識該音包單元所代表 之發音,接著透過輸出機制依據該發音與動畫嘴形參數之 對應表擷取出對應該發音的嘴形參數 應用程式,俾供該動畫製作應用程式生成嘴形動=畫= ❹係將圖畫之嘴型及音頻訊號分別紀錄,並利用程式產生連 結關係,其雖可利用音頻產生各式嘴型動畫,但其並無法 表現該音頻之情感,只單純對應系統中儲存之各式嘴型。 【發明内容】 爰此,有鑑於習知無法藉由聲音產生圖像畫作之缺 點,故本發明提供一種聽聲彩繪系統,包括有: 整合座體。 主機,其内建有語音辨識程式及互動式音樂小畫家分 析程式’且係組設於整合座體上。 3 201027377 輸入元件,係連接於主機上 輸出元件,係連接於主機上 以供使用者利用該麥克 並連接至一樂器,以供 上述該輸入元件係為麥克風 風輸入聲音。 上述該輸入元件係為音源線 使用者彈奏樂器輸入聲音。 上述該輸出元件料投影機、印表機或燒錄器。 上述該主機另外接有音響喇n八。 上述該π a辨識程式係整合色彩音樂理論、線條音樂 理論並具分析音調、音f、音頻、音色或節奏域之程式, 並使用c語言撰寫。 上述該互動式音樂小畫家分析程式係整合色彩音樂理 t、線條音樂理論並具分析音調、音f、音頻、音色或節 奏起伏之程式,並使用C語言撰寫。 本發明具有以下優點: ❿ 1.藉由將聲音#換為圖畫影像輸出,讓使用者可以產 生曰樂和繪晝溶合在一起的情境,更加可以表達出使用者 心中的情感和想法。 、2·因看不見光、看不見顏色,導致大部份的盲人朋友 無=從事繪晝藝術創作,透過本創作可以幫助盲人朋友透 過曰歌或疋彈奏音樂來表達内心的情感,進而轉換出圖像 晝作,讓我們可以了解到盲人朋友眼中的世界到底是什麼 樣的顏色和情境。 【實施方式] 201027377 r先,請參閱第一圖所示,本發明係為一種聽聲彩繪 系統’包括有: 整合座體(1)。 主機(2),其内建有語音辨識程式(21)及互動式音 樂小晝家分析程式(22),聽組設於整合座體上⑴, 該語音辨難式(21)及互動式音樂小晝家純程式(22) 3整合色彩音樂理論、線條音樂理論並具有分析音調、 音質、音頻、音色或節奏起伏之程式,並使用C語言撰寫; 輸入几件(3)’係連接於主機(2)上,該輸人元件⑺ 可:麥克風’以供使用者利用該麥克風輸入聲音,其亦可 =曰源線’並連接至—樂器(B),以供使用者彈奏樂器(B) 輸入聲音。 ^元件(4),係連接於主機(2)上,該輸出元件(4) 馨i又衫機、印表機或燒錄器,投影機可供圖畫影像和 曰5步輸出’的表機可將該圖畫影 ❾錄器則可㈣畫影像及聲音備份燒錄於_片上。 使用時’如第二圖之系統架構示意圖所示,使用者使 入7L件?)將聲音輸入組設於整合座體⑴中之主 使用者之内聲’音右會:二=之二入元件(3)為麥克風’則 各式音調、音質、音頻、音色或節奏起 頻、線條音樂理論分析各式音調、音質、音 曰色或卽奏起伏’而由輪出元件⑷輸出各式圖畫影 201027377 ’該主機(2)另外接有音㈣βΛ(Α),輸出圖 =時’聲音亦可由音響,卜八U)直接輸出,產生聲音 旦H容合在—起的情境’而若使用者使用之輪入元 3為連接至樂|| (Β)之音源線則輸人主機(2)後, :直接由互動式音樂小晝家分析程式(22)將圖畫影像輪 出。 藉由將聲音轉換為g晝影像’同時輸出聲音及圖晝影 ❹=’讓使用纟可以產生聲音及圖畫影像溶合在一起的情 i兄更加可以表達出使用者心中的情感和想法亦可幫助 盲人朋友透過唱歌或是彈奏音樂來表達内心的情感進而 轉換出圖像晝作,讓我們可以了解到盲人朋友眼中的世界 到底是什麼樣的顏色和情境。 【圖式簡單說明】201027377 VI. Description of the Invention: [Technical Field] The present invention relates to a kind of listening sound color (four) system, in particular to a user who inputs and converts sound into a picture image output. [Prior Art] According to the prior art, there is no method for generating image painting by sound. Therefore, there is a method for pre-storing audio signal analysis rules in the Republic of China Patent No. 1272511 "Animation Generation System and Method". a correspondence table between the sound packet unit and the pronunciation, and a database of correspondence tables of the pronunciation and the mouth shape parameters, and parsing the received audio signal into at least one sound packet unit according to the audio signal analysis rule through the analysis mechanism, and then borrowing The recognition mechanism recognizes the pronunciation represented by the sound packet unit according to the corresponding correspondence table of the sound packet unit and the pronunciation, and then extracts the mouth shape parameter application corresponding to the sound according to the corresponding table of the pronunciation and the animation mouth shape parameter through the output mechanism.俾 该 该 该 该 该 该 该 该 该 该 该 该 该 该 该 该 该 该 该 该 该 该 该 该 该 该 该 该 该 该 该 该 该 该 该 该 该 该 该 该 该 该 该 该 该 该 该 该 该 该 该 该Expressing the emotion of the audio, it only corresponds to the various types of mouths stored in the system. SUMMARY OF THE INVENTION Accordingly, the present invention provides a listening and sounding system, including: an integrated body, in view of the inability to produce image painting by sound. The main unit, which has a voice recognition program and an interactive music painter analysis program, is set up on the integrated body. 3 201027377 The input component is connected to the output component of the mainframe and is connected to the mainframe for the user to use the microphone and is connected to an instrument for the input of the microphone as the microphone input sound. The input element described above is the audio source user playing the instrument input sound. The output component is a projector, a printer or a burner. The host is additionally provided with an acoustic speaker. The above π a recognition program integrates color music theory, line music theory, and has a program for analyzing pitch, sound f, audio, timbre or rhythm, and is written in c language. The interactive music painter's analysis program integrates color music theory, line music theory, and analyzes the pitch, sound f, audio, timbre, or rhythm of the program, and writes in C language. The invention has the following advantages: ❿ 1. By changing the sound # to the picture image output, the user can create a situation in which the music and the painting are dissolved together, and the emotions and thoughts of the user's heart can be expressed. 2) Because of the invisible light and the invisible color, most of the blind friends have no creative work in painting and painting. Through this creation, blind friends can express their inner feelings through singing or playing music. Out of the image, let us know what color and situation the world in the eyes of blind friends is. [Embodiment] 201027377 r First, referring to the first figure, the present invention is an audio-visual painting system' including: an integrated seat (1). The host (2) has a voice recognition program (21) and an interactive music analysis program (22). The listening group is set on the integrated body (1), the voice recognition type (21) and interactive music.小昼家纯程式(22) 3 Integrates color music theory, line music theory and has a program for analyzing pitch, sound quality, audio, tone or rhythm, and writes in C language; input several pieces (3)' is connected to the host (2) The input component (7) can be: a microphone 'for the user to input sound using the microphone, which can also be = source line' and connected to the instrument (B) for the user to play the instrument (B ) Enter the sound. ^ Component (4) is connected to the host (2), the output component (4) is a machine, a printer or a burner, and the projector can be used for drawing images and 曰5-step output. The picture-recording recorder can be used to (4) the image and sound backup to be burned on the _ film. When used, as shown in the system diagram of the second figure, the user enters 7L pieces? ) Set the sound input group to the main user in the integrated base (1). The sound will be right: 2 = 2 into the component (3) is the microphone 'The tone, sound quality, audio, tone or rhythm frequency Line music theory analyzes various tones, sound quality, sounds, or sings and undulates' while the wheeled components (4) output various types of picture shadows 201027377 'The host (2) is additionally connected with sound (four) βΛ(Α), output map = time 'The sound can also be directly output by the sound, Bu 8 U), and the sound is created in the context of the sound. If the user uses the round input 3, the sound source line connected to the music || (Β) is input. After the host (2), the picture image is rotated directly by the interactive music expert analysis program (22). By converting the sound into a g昼 image, and simultaneously outputting the sound and the image ❹ ' ' ' ' 让 让 ' 让 让 让 让 让 让 让 让 让 让 让 让 让 让 让 让 兄 兄 兄 兄 兄 兄 兄 兄 兄 兄 兄 兄 兄 兄 兄Helping blind friends to express their inner feelings by singing or playing music, and then transforming the image, let us know what color and situation the world in the eyes of blind friends is. [Simple description of the map]
第一圖係為本發明之立體外觀示意圖。 第二圖係為本發明之系統架構示意圖。 【主要元件符號說明】 (1) 整合座體 (2) (21) 語音辨識程式 (22)互動式音樂小晝家分析程式 (3 ) 輸入元件 (A) 音響喇口八 (4)輪出元件 (B)樂器The first figure is a schematic view of the stereoscopic appearance of the present invention. The second figure is a schematic diagram of the system architecture of the present invention. [Explanation of main component symbols] (1) Integrated base (2) (21) Speech recognition program (22) Interactive music expert analysis program (3) Input component (A) Acoustic port 8 (4) wheeled component (B) musical instrument