Embedded speaker - independent continuous speech recognition system based on mpc 5200的嵌入式非特定人連續(xù)語(yǔ)音識(shí)別系統(tǒng)
Continuous speech recognition 連續(xù)語(yǔ)音識(shí)別
Speaker - independent continuous speech recognition based on the biomimetic pattern recognition 基于仿生模式識(shí)別的非特定人連續(xù)語(yǔ)音識(shí)別的研究
Research on chinese continuous speech recognition system and knowledge based search strategies 漢語(yǔ)連續(xù)語(yǔ)音識(shí)別系統(tǒng)與知識(shí)導(dǎo)引的搜索策略研究
Forward and backward hidden markov model with their application to continuous speech recognition 中文信息檢索的主要研究包括索引單元和檢索模型等研究。
Now research on voice recognition turns to large vocabulary speaker - independent continuous speech recognition and natural language understanding 語(yǔ)音識(shí)別研究也轉(zhuǎn)向了大詞匯非認(rèn)人連續(xù)語(yǔ)音識(shí)別和自然語(yǔ)言理解。
Considerable progress has been made in continuous speech recognition ( csr ) technology over last decade , which promotes various successful applications 二十世紀(jì)九十年代以來(lái),連續(xù)語(yǔ)音識(shí)別技術(shù)取得了突破性的進(jìn)展,推動(dòng)了多種應(yīng)用的發(fā)展。
Automatic speech recognition is used more and more widely in people ’ s life , which is categorized into continuous speech recognition and keyword spotting 自動(dòng)語(yǔ)音識(shí)別技術(shù)在當(dāng)代人們的生活中有了越來(lái)越廣泛的應(yīng)用。目前自動(dòng)語(yǔ)音識(shí)別又大致分為連續(xù)語(yǔ)音識(shí)別和關(guān)鍵詞識(shí)別。
An error - tolerant algorithm in decoding module of mandarin continuous speech recognition is examined to correct substitution , insertion and deletion errors in acoustic recognition 摘要本文研究了漢語(yǔ)連續(xù)語(yǔ)音識(shí)別音字轉(zhuǎn)換中的容錯(cuò)算法,以糾正聲學(xué)識(shí)別的替代、插入、刪除錯(cuò)誤。
A combined clustering algorithm of acoustic modeling for continuous speech recognition . journal of chinese information processing , 2003 , 17 : 33 - 38 . 73 yu sheng - min , zhang shu - wu , xu bo 我國(guó)研究者在這兩個(gè)方面均進(jìn)行了探索,在跨語(yǔ)言信息檢索方面主要側(cè)重于中英兩種語(yǔ)言之間的雙向跨語(yǔ)言檢索研究。