Use Your Mouth, Not Your Hand More Accurate Recognition Technology for Smartphones 動口不動手智慧型手機 辨識技術更精準
With a next-generation iPhone, users may input simple instructions through its voice interface when the “make phone calls” or “play music” feature is enabled. If they want to call David on their contacts list, all they have to do is activate the voice capability and say “Call David”. The iPhone then calls David with the message “Dialing David’s mobile” appearing on the screen. With Kindle – a reading device – the text in a piece of writing may be converted into voice and read out loud to users. This feature also comes in handy when users’ eyes are tired or they have problems using their hands.
以iPhone而言，新一代系統主打語音介面，使用者在打電話與播放音樂功能中，可以輸入簡單的命令，若要打給聯絡名單中的大衛，在語音功能被開啟的狀態下說出「打給大衛」，iPhone就會撥電話給大衛，並出現「正在打大衛的行動電話」的確認。至於Kindle，文字轉語音的朗讀功能可將文章的文字內容轉換成聲音朗讀給使用者聽，也提供使用者眼睛疲憊或雙手不便時閱讀。
As a smart device, iPhone responds to users’ instructions, whereas Kindle reads for users. Just like the voice interface in the Knight Rider, future voice interfaces will combine the capabilities of iPhone and Kindle to create an interactive mode that transmits voice both ways.
智慧型裝置中，iPhone所做的部分是聽取使用者的需求與命令；而Kindle則是將內容說給使用者聽。就像霹靂車的語音溝通介面，未來語音介面的發展也就是將兩者結合，形成雙向利用聲音傳遞需求(命令)與內容的互動模式。
As recognition technology advances, iPhone and the next-generation OS are getting better at recognizing voices and text. After inputting instructions (“Call Wang”, for example), the system provides adequate feedback and takes the proper action. The only drawback is that ordering computers to do things this way still feels unnatural. The next step would be to allow users to speak in a way they normally speak when telling these devices to do things.
隨著辨識技術的發展，iPhone與新一代的作業系統提高了在辨識上的準確度，輸入規定的命令語句後（如：打電話給老王)，系統也能提供恰當的回饋與執行。只是這樣命令電腦做事的溝通方式還是太不自然。下一步的語音輸入方式，使用者能透過日常語言說出需求與內容，將有彈性更大的對話模式與架構。
以iPhone而言，新一代系統主打語音介面，使用者在打電話與播放音樂功能中，可以輸入簡單的命令，若要打給聯絡名單中的大衛，在語音功能被開啟的狀態下說出「打給大衛」，iPhone就會撥電話給大衛，並出現「正在打大衛的行動電話」的確認。至於Kindle，文字轉語音的朗讀功能可將文章的文字內容轉換成聲音朗讀給使用者聽，也提供使用者眼睛疲憊或雙手不便時閱讀。
As a smart device, iPhone responds to users’ instructions, whereas Kindle reads for users. Just like the voice interface in the Knight Rider, future voice interfaces will combine the capabilities of iPhone and Kindle to create an interactive mode that transmits voice both ways.
智慧型裝置中，iPhone所做的部分是聽取使用者的需求與命令；而Kindle則是將內容說給使用者聽。就像霹靂車的語音溝通介面，未來語音介面的發展也就是將兩者結合，形成雙向利用聲音傳遞需求(命令)與內容的互動模式。
As recognition technology advances, iPhone and the next-generation OS are getting better at recognizing voices and text. After inputting instructions (“Call Wang”, for example), the system provides adequate feedback and takes the proper action. The only drawback is that ordering computers to do things this way still feels unnatural. The next step would be to allow users to speak in a way they normally speak when telling these devices to do things.
隨著辨識技術的發展，iPhone與新一代的作業系統提高了在辨識上的準確度，輸入規定的命令語句後（如：打電話給老王)，系統也能提供恰當的回饋與執行。只是這樣命令電腦做事的溝通方式還是太不自然。下一步的語音輸入方式，使用者能透過日常語言說出需求與內容，將有彈性更大的對話模式與架構。