An Experimental Study on Dynamic Features of Speech Structure
スポンサーリンク
概要
- 論文の詳細を見る
One of the greatest difficulties in automatic speech recognition (ASR) is how to deal with variations in speech signals caused by nonlinguistic information, such as age and gender. Various methods have been proposed to compensate for the variations and one of them is speech structure. Speech structure, which extracts only contrastive features and discards absolute features, is proven to be transform-invariant mathematically and to be very robust with the nonlinguistic variations experimentally. Although the conventional speech structure extracts local and distant contrastive features, it doesnot extract dynamic features explicitly, which are supposed to exist in the contrastive features. In this paper, we reformulate speech structure based on trajectory Hidden Markov Model (HMM) and derive trajectory structure (TSR), in which dynamic and contrastive features can be defined and used in ASR. We carry out an experiment of n-best rescoring of isolated word recognition using trajectory structure and obtain a 28.5% relative decrease in the word error rate.
- 信号処理学会の論文
信号処理学会 | 論文
- A study on audio watermarking method based on the cochlear delay characteristics
- Estimation of fundamental frequency of reverberant speech by utilizing complex cepstrum analysis
- 反響音を有する畳み込み形混合過程に対するブラインドソースセパレーションの学習法
- A Model-Concept of the Selective Sound Segregation : A Prototype Model for Selective Segregation of Target Instrument Sound from the Mixed Sound of Various Instruments
- Study of Control Strategy Mimicking Speech Motor Learning for a Physiological Articulatory Model