結合人工電子耳與助聽器對中文語音辨識率的影響

Effects of Speech Recognition to Chinese-speaking Cochlear Implant Patients Combined with Acoustic Hearing

鄭惟仁(Wei-Jen Cheng)

指導教授 ： 吳炤民

國立中央大學/資訊電機學院/電機工程學系/碩士(2006年)

摘要

本研究主要的目的是想對一般植入人工電子耳的聽障者，在背景環境噪音下，提升他們對中文語音的辨識能力。研究指出，語音的基本頻率(Fundamental frequency，F0)與週期性訊息對中文語音辨識非常重要。若能搭配助聽器恢復殘存的低頻聽力，可能會提升對這些訊息的感知。為了瞭解增加低頻語音訊息對一般植入人工電子耳聽障者在背景環境噪音下中文語音辨識率的影響，我們模擬三種不同的測試環境：(1)七位具有正常聽力受測者(Normal hearing subject，NH-subject)，一開始只有單耳接收到以四個頻段(Four-channel)連續交替取樣(CIS)編碼策略所模擬的背景噪音下電子耳語音訊息。(2)接著以一低通濾波器模擬助聽器提供的低頻語音訊息，混入原本的電子耳訊息後送至受測者的單耳。(3)最後將這兩種語音訊息分別送至受測者的雙耳中，測試三種模擬環境下他們的語音辨識率。為了驗證模擬實驗所得到的結果，進一步以三位一邊植入電子耳、一邊配戴助聽器的聽障者(Cochlear implant subject，CI-subject)進行三種臨床測試(為了對應三種模擬測試)。初步結果顯示，當噪音環境下的電子耳語音訊息加入助聽器的低頻語音訊息時，正常聽力者與聽障者對中文字詞、聲調的辨識率皆會有所提升(NH-subject；字詞辨識率由3.85%提升至60.86%，聲調辨識率由40.14%提升至97.43%；CI-subject：字詞辨識率由20%提升至37.5%，聲調辨識率由50%提升至90%)。且低頻訊息愈不受噪音污染時，提升效果最明顯。

關鍵字

字詞辨識率 ； 人工電子耳 ； 基本頻率 ； 助聽器 ； 聲調辨識率

並列摘要

The main purpose of this study is to understand how to enhance Chinese speech recognition under the environmental background noise for patients with cochlear implants (CI). Recent studies have shown that fundamental frequency and periodic information of speech signal are important for Chinese speech recognition and perception. This study evaluated the effects of the added low frequency speech signal on Chinese speech recognition under the environmental background noise for normal-hearing (NH) listeners and CI recipients of the Nucleus-24 device with unilateral hearing aid (HA) fitting. Chinese word and tone recognition were measured in seven NH subjects using simulated 4-channel continuous interleaved sampler (CIS) type speech processing strategy under three different conditions; namely, 1) only simulated (CI) signals with modulated Gaussian white noise for monaural stimulation, 2) simulated (CI) signals with modulated Gaussian white noise and simulated HA signals (low-pass speech signals with cutoff frequency of 500 Hz) for monaural stimulation, and 3) simulated (CI) signals with modulated Gaussian white noise to one ear and simulated hearing aid (HA) signals to the other ear for dichotic stimulation. For comparison purpose, Chinese word and tone recognition were also measured in these three CI users using advanced combination encoding (ACE) strategy. A 4dB signal-to-noise ratio (SNR) speech signal was presented to CI users under three similar conditions; namely, 1) one speaker for monaural stimulation (only CI on), 2) on speaker for binaural stimulation (both CI and HA on), and 3) two speakers for binaural stimulation (both CI and HA on). Preliminary results showed that the Chinese word and tone recognition rates of the NH listeners and CI recipients are improved (word and tone recognition rates are improved from 3.85% to 60.86%, 40.14% to 97.43% for NH listeners and 20% to 37.5%, 50% to 90% for CI recipients) when signals for CI with background noise combined with signals of hearing aid, and recognition rates are further improved when clearer low frequency signals were provided.

並列關鍵字

Word Recognition ； Cochlear Implant ； Fundamental Frequency ； Hearing Aid ； Tone Recognition

參考文獻

林永松、陳弘仁、陳順宇　(民86)。“封閉式中文聲母語詞聽閾檢定表的編制”，

楊惠美、吳俊良 (民94)。“學齡前兒童中文語彙毗鄰測驗的編制與驗證”，台灣耳鼻喉頭頸外科雜誌，40，1–12。

王南梅、劉樹玉、詹妍玲、黃俊生 (民86)。“人工電子耳兒童之知聽知覺能力研究”，聽語會刊，1–11。

陳小娟 (民85)。“三至八歲聽障兒童語音聽知覺研究”，特殊教育與復健學報，7，　

Ching, T. Y. C., Incerti, P., and Hill, M. (2004). ‘‘Binaural benefits for adults who use hearing aids and cochlear implants in opposite ears,’’ Ear Hear. 25, 9–21.