Statistical speech recognition using continuousdensity hidden Markov models (CDHMMs) has yielded many practical applications. However, in general, mismatches between the training data and input data significantly degrade recognition accuracy. Various acoustic model adaptation techniques using a few input utterances have been employed to overcome this problem. In this article, we survey these ad...

Standard speaker adaptation algorithms perform poorly on dysarthric speech because of the limited phonemic repertoire of dysarthric speakers. In a previous paper, we proposed the use of “metamodels” to correct dysarthric speech. Here, we report on an improved technique that makes use of a cascade of Weighted Finite-State Transducers (WFSTs) at the confusionmatrix, word and language levels. This...

This paper presents the ATR speech recognition system designed for the DARPA SPINE2 evaluation task. The system is capable of dealing with speech from highly variable, real-world noisy conditions and communication channels. A number of robust techniques are implemented, such as differential spectrum mel-scale cepstrum features, on-line MLLR adaptation, and word-level hypothesis combination, whi...

Sign language recognition (SLR) with large vocabulary and signer independency is valuable and is still a big challenge. Signer adaptation is an important solution to signer independent SLR. In this paper, we present a method of etyma-based signer adaptation for large vocabulary Chinese SLR. Popular adaptation techniques including Maximum Likelihood Linear Regression (MLLR) and Maximum A Posteri...

Gaussian mixture models are the most popular probability density used in automatic speech recognition. During decoding, often many Gaussians are evaluated. Only a small number of Gaussians contributes significantly to probability. Several promising methods to select relevant Gaussians are known. These methods have different properties in terms of required memory, overhead and quality of selecte...

Detecting whether a talker is speaking his native language is useful for speaker recognition, speech recognition, and intelligence applications. We study the problem of detecting nonnative speakers of American English, using two standard speech corpora. We apply approaches effective in speaker verification to this task, including systems based on MLLR, phone N-gram, prosodic, and word Ngram fea...

This paper presents our recent effort on the development of the eigenspace-based linear transformation approach for rapid speaker adaptation. The proposed approach toward prior density selection for the MAPLR framework was developed by introducing a priori knowledge analysis on the training speakers via probabilistic principal component analysis (PPCA), so as to construct an eigenspace for spea...

In conventional Speaker-Identification using GMM-UBM framework, the likelihood of the given test utterance is computed with respect to all speaker-models before identifying the speaker, based on the maximum likelihood criterion. The calculation of likelihood score of the test utterance is computationally intensive, especially when there are tens of thousands of speakers in database. In this pap...

پیوند اعضا از ارکان مهم سیستم‌‌های سلامت است و به درمان بسیاری بیماری‌‌های صعب‌العلاج کمک شایانی کرده است. روزانه 7 تا 10 نفر بیماران نیازمند در ایران علت نرسیدن به‌موقع عضو پیوندی دنیا می‌­روند. با توجه بحرانی­‌بودن زنجیره برای سلامتی انسان، مدیریت برنامه‌ریزی این اهمیت فراوانی برخوردار انتقال بیمار یک بیمارستان محل تأثیر ثانیه‌‌ها بر کیفیت مورد­انتقال موفقیت پیوند، بسیار حائز پژوهش، مدلی ریاض...