A Study on Robust Speech Recognition with Time Varying Speech Features

• Material Type: 博士論文
• Title: A Study on Robust Speech Recognition with Time Varying Speech Features
• Author/Editor: Mufungulwa, George
• Author Heading: Mufungulwa, George
• Publication, Distribution, etc.: Hokkaido University
• Publication Date: 2017-12-25
• Publication Date (W3CDTF): 2017-12-25
• Alternative Title: 音声の時変特徴量を用いた雑音ロバスト音声認識に関する研究
• Contributor: 宮永, 喜一; 大鐘, 武雄; 齊藤, 晋聖; 筒井, 弘
• Degree grantor/type: 北海道大学
• Date Granted: 2017-12-25
• Date Granted (W3CDTF): 2017-12-25
• Dissertation Number: 甲第12944号
• Degree Type: 博士(情報科学)
• Conferring No. (Dissertation): 甲第12944号
• Text Language Code: eng
• NDC: 500
• Target Audience: 一般
• Note (General): Speech feature extraction algorithms have become popular. Speech features can be usedfor various applications: biometric recognition, speech recognition, speaker identification,and so on. In these applications, a good speech feature can be obtained usingMel frequency cepstrum Coefficients (MFCC), Linear Predictive Coding (LPC), Timevarying LPC (TVLPC), Perceptual Linear Predictive (PLP) among others. This thesisfocuses on the use of TVLPC among feature extraction algorithms to improve the robustnessof automatic speech recognition (ASR) systems against various multiplicative andadditive noises. Time varying speech features (TVSF) are implemented in ASR withthe aim of improving the recognition accuracy on a number of small set of referencespeech databases. The significance of the study is based on the fact that both additiveand multiplicative noises cause great performance degradation of ASR systems, therebylimiting the speech recognition accuracy in real environments. For this reason, featurecorrection, feature compensation and normalization approaches are considered in orderto improve the robustness of a speech recognition system.The performance degradation is partly due to statistical mismatch between trainedacoustic model of clean speech features and noisy testing speech features. For the purposeof reducing the feature-model mismatch, corrective, compensation as well as normalizationtechniques are employed both during training and testing of speech features.In order to achieve improved system performance, normalization in modulationspectrum domain is used to remove non-speech components over a certain frequencyrange using running spectrum analysis (RSA) as a band pass filter. In comparison toother noise reduction techniques used in this study on robust speech recognition, theRSA filter has an advantage due to its adaptable parameters, that is, the first and secondpass band frequencies can easily be adjusted accordingly. In addition, speech featureenhancement using dynamic range adjustment (DRA) is utilized. The enhancement isaimed at correcting the difference between clean and noisy speech features by normalizingamplitude of speech features. For the purpose of channel normalization, cepstrummean subtraction (CMS) is used in this study.Two alternative time varying speech features (TVSF) methods are being proposedand compared with conventional Mel frequency cepstral coefficients (MFCC) featuresfor noisy speech recognition.The first experimental study shows that fast Fourier transform (FFT) based Mel frequencycepstrum coefficients (MFCCs) with directly converted time varying linear prediction(TVLPC) based MFCCs, which in this study is defined as time varying speechfeatures (TVSF), shows a competitive recognition accuracy performance to that of FFTbased MFCCs alone.In the second experimental study, robustness of speech recognition is further improvedby applying mel filtering and logarithmic transformations to short time windowedtime varying coefficients before converting to cepstrum coefficients in place ofdirect-converted TVLPC speech features. Results show that RSA produces better performancethan DRA and CMS/DRA on both similar pronunciation phrases and phrasesuttered by elderly persons. Experimental study shows that the use of time varying speechfeatures (TVSP) can produce improved speech recognition accuracy even if there is amismatch between the training and testing data sets.; (主査) 教授 宮永 喜一, 教授 大鐘 武雄, 教授 齊藤 晋聖, 准教授 筒井 弘; 情報科学研究科（メディアネットワーク専攻）
• DOI: 10.14943/doctoral.k12944; https://doi.org/10.14943/doctoral.k12944
• Persistent ID (NDL): info:ndljp/pid/11039854; https://dl.ndl.go.jp/pid/11039854
• Collection: 障害者向け資料
• Collection (Materials For Handicapped People:1): テキストデータ
• Collection (particular): 国立国会図書館デジタルコレクション > デジタル化資料 > 博士論文; https://dl.ndl.go.jp/collections/A00014
• Acquisition Basis: 博士論文（自動収集）
• Date Accepted (W3CDTF): 2018-02-03T13:25:44+09:00
• Format (IMT): PDF
• Access Restrictions: 国立国会図書館内限定公開
• Service for the Digitized Contents Transmission Service: 図書館・個人送信対象外
• Availability of remote photoduplication service: 可
• Periodical Title (URI): http://dx.doi.org/10.14943/doctoral.k12944; http://hdl.handle.net/2115/68114
• Is Referenced By (URI): http://hdl.handle.net/2115/68113
• Data Provider (Database): 国立国会図書館 : 国立国会図書館デジタルコレクション; https://dl.ndl.go.jp

• Summary, etc.: Speech feature extraction algorithms have become popular. Speech features can be usedfor various applications: biometric recognition, speech recogniti...