語音識別系統 的英文怎麼說
中文拼音 [yǔyīnzhìbiéxìtǒng]
語音識別系統
英文
speech recognition system- 語 : 語動詞[書面語] (告訴) tell; inform
- 音 : 名詞1. (聲音) sound 2. (消息) news; tidings 3. [物理學] (音質) tone 4. (姓氏) a surname
- 識 : 識Ⅰ動詞[書面語] (記) remember; commit to memory Ⅱ名詞1. [書面語] (記號) mark; sign 2. (姓氏) a surname
- 別 : 別動詞[方言] (改變) change (sb. 's opinion)
- 系 : 系動詞(打結; 扣) tie; fasten; do up; button up
- 統 : Ⅰ名詞1 (事物間連續的關系) interconnected system 2 (衣服等的筒狀部分) any tube shaped part of ...
- 語音 : speech sounds; pronunciation; voice
- 識別 : 1 (辯別; 辯認) discriminate; distinguish; discern; tell the difference; spot 2 [計算機] identif...
- 系統 : 1. (按一定關系組成的同類事物) system 2. (有條理的;有系統的) systematic
-
The speech recognition ' s system ( in this paper we mainly discuss ibm viavoice ) has the certain capacity of self - adaptation to the speech velocity, volume and tone, but the capacity of those is not enough with different enunciator
目前的語音識別系統(本文中主要是指ibm的viavoice語音識別系統)對語速、音量和音調都具有一定的自適應調整能力。This thesis tries to update the cmdsr system to achieve the characters below : real - time, better robust, higher recognition rate, non - special - man. considering the disadvantages of traditional improved spectrum subtraction speech enhancement, this thesis proposes the theory of fuzzy spectrum subtraction based on the fuzzy theory and improved spectrum subtraction speech enhancement ; as for the difficulties of detecting the endpoint of speech signal, the thesis gives the table of initial and the improved parameters, with which we can confirm the endpoints of mandarin digit speech ; the thesis puts forward two - level digit real - time speech recognition system, the first level is based on discrete hidden markov model which is linear predictive coding cepstrum ( lpcc ) and difference linear predictive coding cepstrum ( dlpcc ), the second level is based on formant parameters ; as for the realization of hardware, the thesis depicts the realization of every part of cmdsr based on the tms320vc5402 in detail ; as for the development of software, the thesis gives the software design flow chart of cmdsr, simulates the basic theory with matlab language and gives the simulation results
針對傳統的「改進譜相減法語音增強」參數設定單一、環境適應能力差的缺點,提出了一種利用模糊理論和「改進的譜相減法」結合的「模糊譜相減法語音增強」 ;針對語音信號端點檢測困難的特點,通過matlab模擬試驗,給出了能夠準確確定數碼語音端點的初始和改進參數表;提出了利用基於線性預測編碼倒譜參數和差分線性預測編碼倒譜參數相結合的離散隱含馬爾可夫模型進行第一級識別、利用共振峰參數進行第二級識別的兩級漢語數碼語音識別系統,在保證系統實時性的同時,實現連接漢語數碼語音識別系統識別率的提高;在硬體實現上,詳細闡述了基於tms320vc5402的連接漢語數碼語音識別系統各部分硬體設計;在軟體開發上,給出了連接漢語數碼語音識別的軟體設計各部分的流程圖,並對各部分進行了matlab模擬,並給出了模擬結果。At the same time according to the low recognition rate in speech recognition system, the author used the method of fundamental frequency analysis to build male / female recognition model respectively
同時針對語音識別系統中識別率不高的問題,採用基音頻率分析的方法分別建造男女聲識別模型。Mandarin continuous speech recognizer based on classical hmm
基於經典隱馬爾可夫模型的漢語連續語音識別系統In the theory introduction part, after simply introduces the basis knowledge of voice signal, a systemic and concise brief of the preceding disposal, endpoint detection, parameter pick - up and matching - method of speech recognition according the basic framework of speech recognition system are given
在語音識別理論介紹部分,文中在簡單介紹了語音信號的基本知識之後,根據語音識別系統的基本結構,依次對語音識別技術的前端處理、起止點檢測、特徵提取和識別判決方法部分一一進行了系統而簡明的闡述。Speech enhancement as the front - end processing module is used to improve the signal - to - noise ratio ( snr ) of the input signal for recognition in the latter stages
為了讓語音識別系統在安靜的環境和有噪聲的環境中都獲得令人滿意的工作性能,研究了一個將語音增強器和語音識別器級連起來的系統。Then this spectral subtraction method is applied to noise speech recognition system as the front - end processing. noise speech signal are processed to improve its snr before recognition. so the recognition rate can be improved in noise environments
並將改進譜減演算法作為噪聲下語音識別系統的前端處理過程,即通過對含噪的語音進行語音增強以提高信號的信噪比,從而提高語音識別系統的抗噪聲性能。This thesis also focuses on the way of modeling and evaluating the language model for lvsr and introduces detailed the linear and kneser - ney smoothing techniques and the strategy to estimate the discounting parameters using maximum - likelihood criterion
同時本文還就大詞匯表語音識別系統的語言模型的構建以及評估問題進行深入探討,詳細介紹了線性平滑和kneser - ney平滑技術,並用最大似然估計的方法獲得其平滑參數。Improving the performance of continuous mandarin digit string recognition system by using tones
利用聲調提高中文連續數字串語音識別系統性能In this thesis, first we analyzed and designed a traditional continued speech recognition system, which based on hmm and mfcc speech features. then we researched some noise robust technologies based on that system
本論文首先分析並實現了一個以mel頻率倒譜系數( mfcc )作為語音特徵,基於隱馬爾可夫模型( hmm ) ,針對連續數字串識別任務的基本連續語音識別系統。Each unit of a speech recognition system is studied in this paper, which includes the preprocessing, the training of reference patterns, the connected digit speech recognition algorithm and the postprocessing of confusing pairs. the research of endpoint detection includes the endpoint detection not only in the quiet environment but also in the low signal - to - noise ( snr ) situation. as far as the training of the reference patterns is concerned, the modified k - means algorithm is adopted. the most important part of this paper is the research of connected speech recognition algorithm. two kinds of algorithm are put forward, which are based on the existing fruit of mutual - information match theory
其次漢語連續數字發音連續程度較高,這主要由於漢語數字發音中零聲母語音出現的較多。另外漢語連續數字串中各個數字的協同發音現象較嚴重也給漢語連續數字語音識別帶來了困難。本文以互信息理論為基礎,從語音模式間的交互信息量的角度,研究了一個完整的語音識別系統的各個組成部分,其中包括預處理、參考模式的訓練、連續識別演算法以及后續處理部分。The first part of the paper is designing the testing project for grounding resistance and insulation resistance in a new way. using 16bits ad converter with programmable control amplifier replaced the way which used changing resistance to change measure range. lt is not only improved testing precision and develop the system expediently, but also reduced the area of the circuit boardwith the new way. in order to make the electric implement safety testing system have upstanding expansibility, the software and hardware of the system adopted the modularization design. adopted mcu atmegal28 as a master mcu which control mmi, realtime clock and communication with slaver mcu. atemga8 as the slaver mcu to realize testing function. so it is easy to add or reduce the testing project. the testing implement system has been developed successfully, and the comments for the system is that it has high precision, high expansibility and easy maintain. but considering the electric implement system should have intelligence and humanity abi lity. so this paper bring forward a scheme of electric equipment safety testing embedded system with speech control. after introduce the basic theory of speech recognition, the paper expatiate the characters of this system. the system is a noise conditon, not special people, small glossary, insulation word system. with these characters design the speech recognition as fellow. utilizing cross zero ratio and short energy to ensure jumping - off point and end point ; adopting mfcc as the character parameters of speech recognition ; the character parameters than be recognized by dtw. in order to ensure the credibility of this project, first realized by matlab in computer
在介紹了語音識別的基本原理后,闡述了本系統的特點:本系統是一個噪聲環境下非特定人、小詞匯量、孤立詞的語音識別系統。根據本系統的這些特點設計了如下語音識別方案:利用過零率和短時能量相結合的方式確定語音端點;採用mel頻率倒譜系數( mfcc )作為語音識別的特徵參數;得到的特徵參數最後通過動態時間規整( dtw )的模式識別方法進行識別。為了確保本系統實現方案的可靠性,首先通過計算機利用matlab軟體來模擬,在演算法模擬實現后又進一步增加環境的復雜性:加上較大的環境噪聲、突發性的噪聲等,再通過修改參數、修改參考模板、兩級識別等各種提高語音識別精度的方法來提廣東工業大學工學碩士學位論文高識別率。Embedded speaker - independent continuous speech recognition system based on mpc
5200的嵌入式非特定人連續語音識別系統Research on chinese continuous speech recognition system and knowledge based search strategies
漢語連續語音識別系統與知識導引的搜索策略研究The research will lead to a new recognition system for the spontaneous and conversational speech
本課題旨在研究和開發一個具有自然交談風格的大詞匯量連續語音識別系統。A number of techniques have been developed to reduce the mismatch caused by environment noise over the past decades
然後基於此基本連續語音識別系統進行了抗噪聲技術的研究。Application of hmm in automatic speech recognition system
在語音識別系統中的應用A speech recognition system and structure based on the dsp
的語音識別系統及其結構In the phase of training, it gets the sampling data from the wave files which were stored in the voice library by using the mci functions. then calculates the character vector ( 12 ranks of lpc and lpcc ) and trains them by clustering method, so we get the templates used by speech - recognition, this templates were stored in the template library. in the state of recognition, after calculating the character vector of input voice, we compare it with the character vectors of templates, and then find the best one or refuse it
系統的組成模塊與語音識別系統的基本構成模型基本一致,在訓練過程中,通過調用mci ( mcimultimediacontrolinterface )提供的函數從語音庫中的波形文件中讀取采樣數據,分幀計算出由12維線性預測系數和12維線性預測倒譜系數構成的特徵矢量,並按照聚類的方法進行訓練,得到后續語音識別時需要的模板,存放于模板庫中。The design of an effective platform for evaluating speech recognition systems
語音識別系統測試平臺設計分享友人