Toward an automatic system for distinctive feature extraction from speech
نویسندگان
چکیده
منابع مشابه
Distinctive features for use in an automatic speech recognition system
In this paper we develop a method of representing the speech waveform in terms of a set of abstract, linguistic distinctions in order to derive a set of discriminative features for use in a speech recognizer. By combining the distinctive feature representation with our original waveform representation we are able to achieve a reduction in word error rate of 33% on an automatic speech recognitio...
متن کاملAn Interval-Based Algorithm for Feature Extraction from Speech Signals∗
Language disorders can be classified into the three linguistic levels of pronunciation, lexicon, and grammar. To identify the most important linguistic processes leading to disorders in the before-mentioned fields, both standardized test procedures and the analysis of freely spoken language are used in the everyday work of speech therapists. However, especially the analysis of freely spoken lan...
متن کاملPhysiologically Motivated Feature Extraction for Robust Automatic Speech Recognition
In this paper, a new method is presented to extract robust speech features in the presence of the external noise. The proposed method based on two-dimensional Gabor filters takes in account the spectro-temporal modulation frequencies and also limits the redundancy on the feature level. The performance of the proposed feature extraction method was evaluated on isolated speech words which are ext...
متن کاملSoft margin feature extraction for automatic speech recognition
We propose a new discriminative learning framework, called soft margin feature extraction (SMFE), for jointly optimizing the parameters of transformation matrix for feature extraction and of hidden Markov models (HMMs) for acoustic modeling. SMFE extends our previous work of soft margin estimation (SME) to feature extraction. Tested on the TIDIGITS connected digit recognition task, the proposed...
متن کاملAutomatic Speech Feature Extraction for Cognitive Load Classification
Performance of attention-demanding tasks is challenged if motor (e.g., walking) and cognitive (e.g., talking) tasks are carried out simultaneously. These dual-task paradigms have received increasing interest in probing the attentional influence associated with impairments to these systems [1]. For example, gait instabilities in Alzheimer's patients has been suggested to result from impaired att...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: The Journal of the Acoustical Society of America
سال: 1990
ISSN: 0001-4966
DOI: 10.1121/1.2028474