發(fā)布時間：2019-01-18 08:43

【摘要】：語音識別技術(shù)是實現(xiàn)計算機與人之間進行語言交流的關(guān)鍵技術(shù)之一,語音識別技術(shù)在交互方面具有極高的應(yīng)用價值。隨著關(guān)鍵詞檢測、語音合成、聲紋識別等技術(shù)的進步,人們對語音技術(shù)的需求逐漸加深,語音識別產(chǎn)品正在走進我們的工作生活,逐漸深入到各個領(lǐng)域。 本文主要是對漢語語音識別系統(tǒng)中關(guān)鍵詞技術(shù)進行研究,通過兩類不同的實際應(yīng)用場景對關(guān)鍵詞檢測技術(shù)進行驗證,主要的工作成果如下： 1、針對智能電話客服的應(yīng)用深入研究了基于垃圾模型(Garbage Model)關(guān)鍵詞檢測技術(shù)。完成了端點檢測技術(shù)的改進、垃圾語料建模選取、以及確定垃圾模型和關(guān)鍵詞模型網(wǎng)絡(luò)權(quán)重值,再此基礎(chǔ)上與人合作實現(xiàn)了關(guān)鍵詞檢測引擎,通過對接國內(nèi)某電腦生產(chǎn)商維修預(yù)約客服電話系統(tǒng),實現(xiàn)對關(guān)鍵詞檢測技術(shù)的驗證,該系統(tǒng)中典型的關(guān)鍵詞有硬盤問題、開機故障、系統(tǒng)崩潰等。通過話術(shù)引導(dǎo)、合理增加關(guān)鍵詞長度或者合并關(guān)鍵詞顯著提高關(guān)鍵詞檢出率。 2、面向語音文檔檢索應(yīng)用需求,系統(tǒng)研究了基于音節(jié)網(wǎng)絡(luò)(Syllable)的關(guān)鍵詞檢測技術(shù),完成了對保險業(yè)和旅游業(yè)的的聲學(xué)模型的訓(xùn)練,引入語言學(xué)知識提高關(guān)鍵詞識別效果。借助保險業(yè)和旅游業(yè)的客服錄音記錄進行測試表明：可依據(jù)預(yù)先設(shè)定的關(guān)鍵詞實現(xiàn)語音文檔檢索功能。
[Abstract]:Speech recognition technology is one of the key technologies to realize the language communication between computers and people. Speech recognition technology has a high application value in the aspect of interaction. With the development of key word detection, speech synthesis, voiceprint recognition and other technologies, the demand for speech technology is deepening. Speech recognition products are coming into our work and life, and gradually into every field. This paper mainly studies the keyword technology in the Chinese speech recognition system, and verifies the keyword detection technology through two different kinds of practical application scenes. The main work results are as follows: 1. Aiming at the application of smart phone customer service, the (Garbage Model) keyword detection technology based on garbage model is studied. The improvement of endpoint detection technology, the selection of garbage corpus modeling, and the determination of network weights of garbage model and keyword model are completed. On this basis, the keyword detection engine is implemented in cooperation with people. By docking a domestic computer manufacturer's maintenance reservation customer service telephone system, the key words in the system can be verified. The typical keywords in the system are hard disk problem, boot failure, system collapse and so on. Through the guidance of words, the reasonable increase of keyword length or the combination of keywords significantly improve the detection rate of keywords. 2. In order to meet the requirement of speech document retrieval, the keyword detection technology based on syllable network (Syllable) is studied systematically. The acoustic model of insurance industry and tourism industry is trained, and linguistic knowledge is introduced to improve the effect of keyword recognition. With the help of customer service recording of insurance industry and tourism industry, it is shown that voice document retrieval can be realized according to predefined keywords.
【學(xué)位授予單位】：北京郵電大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2015
【分類號】：TN912.34

【參考文獻】

相關(guān)期刊論文 前10條

1 甄斌,吳璽宏,劉志敏,遲惠生;語音識別和說話人識別中各倒譜分量的相對重要性[J];北京大學(xué)學(xué)報(自然科學(xué)版);2001年03期

2 劉加;漢語大詞匯量連續(xù)語音識別系統(tǒng)研究進展[J];電子學(xué)報;2000年01期

3 張鵬遠;韓疆;顏永紅;;關(guān)鍵詞檢測系統(tǒng)中基于音素網(wǎng)格的置信度計算[J];電子與信息學(xué)報;2007年09期

4 馬曉梅;沈潔;;垃圾模型技術(shù)在關(guān)鍵詞檢測系統(tǒng)中的應(yīng)用[J];信息技術(shù);2009年06期

5 榮薇;陶智;顧濟華;趙鶴鳴;;基于改進LPCC和MFCC的漢語耳語音識別[J];計算機工程與應(yīng)用;2007年30期

6 劉鑫,陸林生;關(guān)鍵詞檢測系統(tǒng)中聲學(xué)置信度的應(yīng)用[J];計算機工程;2004年08期

7 幸璐璐,謝莎莎,孫甲松,王作英;在線廢料建模在特定領(lǐng)域語音識別中的應(yīng)用[J];計算機應(yīng)用;2005年12期

8 倪崇嘉;劉文舉;徐波;;漢語大詞匯量連續(xù)語音識別系統(tǒng)研究進展[J];中文信息學(xué)報;2009年01期

9 宋戰(zhàn)江,鄭方,徐明星,武健,吳文虎;漢語連續(xù)語音識別系統(tǒng)與知識導(dǎo)引的搜索策略研究[J];自動化學(xué)報;2000年04期

10 孟猛;王曉瑞;梁家恩;徐波;;一種基于互補聲學(xué)模型的多系統(tǒng)融合語音關(guān)鍵詞檢測方法[J];自動化學(xué)報;2009年01期

相關(guān)博士學(xué)位論文 前2條

1 李偉;基于內(nèi)容的漢語語音檢索技術(shù)研究與系統(tǒng)實現(xiàn)[D];清華大學(xué);2011年

2 李寶祥;語音關(guān)鍵詞檢索若干問題的研究[D];北京郵電大學(xué);2013年

，

本文編號：2410518