聽障者在噪音環境下對語音的理解能力遠比一般人差，要在噪音環境下提升聽障者對語音訊號的理解力，首先要做的是將語音增強，亦即作噪音去除，本論文使用了具聽覺遮蔽效應之概念來做語音增強。當噪音去除之後，使用了等效矩形頻寬的分頻法(equivalent rectangular bandwidth scale)，搭配上圓通化指數(rounded exponential)模型，將增強後的語音轉換，以期在噪音環境下對聽障者提供最大之幫助。一個語音訊號如果被雜訊所干擾，對一般人來說，會產生辨認率的下降及耳朵的不舒服的感覺，對聽障者來說更為嚴重。所以我們在做語音增強的時候，第一步要做的就是將帶有雜訊的語音訊號中的雜訊去除，語音增強的處理，運用到了聽覺遮蔽效應的概念，典型的方式就是將語音訊號的功率頻譜(power spectrum)乘上一增益函數(Gain function) 。聽障者對於聽聲音有一定的困難度，不論是聽不清楚或聽不到，會導致這樣的結果一定是有其原因的。對一個需要配戴助聽器的人來說，一定要讓助聽器跟聽障者的聽力特性達到一個最佳匹配，才能得到戴助聽器的效果。本研究期望能找到讓聽障者聽不清楚或聽不到聲音的原因，針對這個原因，去做語音訊號上的處理，讓語音訊號跟聽障者的聽力特性達到最佳的配合效果。每個聽障者的情況不盡相同，本研究只是針對一般聽障者會有的情形，對訊號做適當的轉換。一般語音訊號在頻譜上變化迅速，聽障者可能無法完全接收或理解，而且比較聽不到高頻的成份，所以第二步驟的處理是將語音訊號的低頻變化及變動幅度降低，且提高高頻的頻譜值，以符合聽障者的需要。

The speech comprehension for a hand-of-hearing person is far worse than a hearing-normal people under the noisy environment. In order to improve the speech perception under the noisy environment,the speech enhancement,namely the noise reduction,must be performed.This thesis employs the masking effect to the speech enhancement. After the noise is reduced,we use the equivalent rectangular bandwidth (ERB)scale and matching rounded exponential(ROEX) model to convert the speech in frequency domain.By doing so,we may help those hand-of- hearing persons in improving their speech perception.

[1] 謝逸博,“以語音合成技術發展聽障者語言學習輔助系統,”
國立清華大學電機工程研究所碩士論文,2001
[2] Whimal,N.A.,Rutledge,J.C.,“Noise reduction algorithm for digital hearing aids,”IEEE ,3-6 Nov.1994,pp.1294-
1295
[3] Moore,B.C.J.,“Speech processing for the hearing- impaired:successes,failures,and implications for speech mechanisms,” Speech Commun.Vol 41,81-91,2003
[4] Jonhston,J.D.,“Transform coding of audio signal using perceptual noise criteria,”IEEE J.Select.Areas Commum.,
Vol.6,pp.314-323,Feb.1988
[5] Tsoukalas,D.E.Mourjoupoulos,J.and Kokkinakis,G. “Speech enhancement based on audible noise suppression,”
IEEE Trans.Speech & Audio Proc.,5(6):497-514,1997
[6] Patterson,R.D.,Nimmo-Smith,I.,Weber,D.L.,andMilroy,R.
(1982).“The deterioration of hearing with age:Frequency selectivity,the critical ratio,the audiogram and speech threshold,”J.Acoust.Soc.Amer.,vol.72,1788-1803
[7] Deller,Jr.J.R.,Hansen.J.H.L.,Proakis,J.G.“Discrete-
Time Procesng of Speech Signals,”An IEEE PRESS Classic
Reissue 1993
[8] Steven,F.B.,“Suppression of Acoustic Noise in Speech Using Spectral Subtraction,”IEEE Trans.on Acoustics, Speech,and Signal Processing,Vol.ASSP-27,No.2,pp.113-
120,April 1979
[9] Arehart,K.H.,Hansen,J.H.L.,Gallant,S.and Kalstein,L. “Evaluation of An auditory masked threshold noise
suppression algorithm in normal-hearing and hearing-
impaired listeners,”Speech Commun.,Vol 40(4):575-
592 June 2003
[10] Baer,T.,and Moore,B.C.J.(1993). “Effects of spectral smearing on the intelligibility of sentences in the presence of noise,”J.Acoust.Soc.Amer.94,1229-1241.
[11] http://www.ling.su.se/staff/hartmut/bark.htm
[12] Fillon,T.,Prado,J. “Evaluation of an ERB frequency scale noise reduction for hearing aids:A comparative study,” Speech Commun.Vol 39,23-32,2003
[13] Virag,N. “Speech Enhancement Based on Masking Properties of the Auditory System,”IEEE ICASSP, Detroit,MI,pp.796-799,May 1995
[14] Virag,N. ”Single Channel Speech Enhancement Based on Masking Properties of the Human Auditory System,”IEEE Trans.On Speech and Audio Proc,vol.7,no.2,pp.126-137
,March 1999
[15] M.R.Schroeder,B.S.Atal,and J.L.Hall, “Optimizing digital speech coders by exploiting masking properties of the human ear,”J.Acoust. Soc.Amer.,vol.66,pp.1647-1652, Dec.1979
[16] 林輝彥, “應用具聽覺效應之模型於噪音環境中語音辨識,”國立成功大學資訊工程研究所碩士論文,2001
[17] Doblinger,G.“Computationally efficient speech enhancement by spectral minima tracking in subbands,”
EUROSPEECH 1995,pp.1513-1516.
[18] Thomas,F.Q.,“Discrete-Time Speech Signal Processing,
”PRINCIPLES AND PRACTICE 2002
[19] Nejime,Y.,Moore,B.C.J.,(1997). “Simulation of the effect of threshold elevation and loudness recruitment combined with reduced frequency selectivity on the intelligibility of speech in noise,” J.Acoust.Soc.Amer.102,603-615
[20] Natarajan,A.,Hansen,J.H.L.,Arehart,K.,Rossi-Katz,J.A. “Perceptual based speech enhancement for normal-hearing
& hearing-impaired individuals,”Eurospeech 2003,pp
1425-1428
[21] http://www. indiana.edu/~spl/people/shgoodma/code/
expattern.html
[22] Moore,B.C.J.,and Glasberg,B.R.(1983). “Suggested formulae for calculating auditory-filter bandwidths and exciation patterns,”J.Acoust.Soc.Amer.74,750-753.