2010 · 10 citations · 16 references
Language StudiesLinguisticsAcousticsPhoneticsPhonologyAcoustic PhoneticsSpeech AcousticsSpeech RecognitionVowel PhoneticsAcoustic Vowel AnalysisRobust Speech RecognitionSpeaker-dependent Speech RecognitionSpectral TiltSpeech Recognition AcousticsVoice RecognitionVowel Formant AnalysisVowel Recognition
This paper describes an approach for enhancing the robustness of isolated words recognizer by extending its flexibility in the domain of speaker's variable vocal effort level. An analysis of spectral properties of spoken vowels in four various speaking modes (whispering, soft, normal, and loud) confirm consistent spectral tilt changes. Severe impact of vocal effort variability on the accuracy of a speaker-dependent word recognizer is presented and an efficient remedial measure using multiple-model framework paired with accurate speech mode detector is proposed.
16
HMM adaptation using vector taylor series for noisy speech recognition
Alex Acero, Li Deng, Trausti Kristjansson et al. · 2000 · 279 citations