技術摘要 / Our Technology: |
隨著文字、聲音以及多媒體資訊在網際網路上迅速累積並廣泛地被使用,發展以文字或語音型式的查詢指令(text or speech queries)去檢索文字或語音型式的資訊(text or speech information)的技術說顯得愈來愈為重要。以語音為基礎之資訊檢索(speech-based information retrieval)指的是使用者的查詢指令以及被檢索的資訊兩者其中至少之一是語音型式。在本發明中,考慮中文的單音節結構(monosyllabic structure)特性,發展出來一系列以音節(syllable)為基礎的索引特徵(indexing terms),包括了重疊音節片段(overlapping syllable segments)及可間隔若干音節之雙音節(syllable pairs separated by a few syllables),同時也驗證了這一系列以音節為基礎的索引特徵的確具有極強的鑑別能力。此外,在本發明裡也發展出進一步融合以中文的字與詞為基礎的索引特徵的方法,以及若干特別的處理方法,來增強上述這些音節索引特徵的檢索鑑別能力。
The present invention is directed to a method for speech-based information retrieval in Mandarin Chinese, considering a monosyllabic structure of the Chinese language, and a whole class of syllable-based indexing terms, including overlapping segments of syllables and syllable pairs separated by a few syllables. The strong discriminating capabilities of such syllable-based indexing, terms have been verified. Special approaches for better utilizing such capabilities, including fusion with the word- and character-level information and improved approaches to obtain better syllable-based features and query expressions and so on, are disclosed too.
|
專利簡述 / Intellectual Properties: |
|
|
聯繫方式 / Contact: |
臺大產學合作總中心 / Center of Industry-Academia Collaboration, NTU |
|
Email:ordiac@ntu.edu.tw |
電話/Tel:02-3366-9945 |
|
|
|
|