A new tightly coupled speech and natural language integration model is presented for a TDNN-based continuous possibly large vocabulary speech recognition system for Korean. Unlike popular n-best techniques developed for integrating mainly HMM-based speech recognition and natural language processing in a word level, which is obviously inadequate for morphologically complex agglutinative language...

Nowadays, speech interfaces have become widely employed in mobile devices, thus recognition speed and power consumption are becoming new metrics of Automatic Speech Recognition (ASR) performance. For ASR systems using continuous Hidden Markov Models (HMMs), the computation of the state likelihood is one of the most time consuming parts. Hence, we propose in this paper novel multi-level Gaussian...

The Chinese language is syllabic in nature with frequent homonym phenomena and severe word boundary uncertainty problem. This makes the Chinese continuous speech recognition (CSR) slightly difficult. In order to solve these problems, a Chinese syllable-synchronous network search (SSNS) algorithm is proposed. Together with the vocabulary word search tree and the N-gram based language model, the ...

Objectives: This paper studies the effect of Persian Cued Speech on the perception of Persian language phonemes and monosyllabic words with and without sound in hearing impaired children. Cued Speech is a sound based mode of communication for hearing impaired people that is comprised of a limited series of hand complements and the normal pattern of speech. And it is shown that it effectively ca...

Today, speech interfaces have become widely employed in mobile devices, thus recognition speed and resource consumption are becoming new metrics of Automatic Speech Recognition (ASR) performance. For ASR systems using continuous Hidden Markov Models (HMMs), the computation of the state likelihood is one of the most time consuming parts. In this paper, we propose novel multi-level Gaussian selec...

This paper describes preliminary results of automatic recognition of Korean broadcast-news speech. We have been working on flexible vocabulary isolated-word speech recognition, and the same HMM models are used for broadcast-news continuous speech recognition. The recognizer is trained by using phonetically balanced isolated words speech, rather than the broadcast news speech itself. In this res...

In this paper we have designed and implemented speech recognition models in phone recognition level to model phones coarticulation effects. We have inspired these models from two human cognitive systems: neocortex and hippocampus. In the model inspired from the neocortex the first step is a primary and coarse classification of inputs, then model adapts itself to contexts extracted from these pr...

The variance of the performance of a continuous speech recognition system subjected to replica utterances of the same sentence spoken by the same speaker has been investigated. In an experiment with three di erent speech recognition systems in three different languages with two di erent grammar conditions it is shown that the sentence word error rate has a variance that can be described in term...

In this contribution we introduce speech emotion recognition by use of continuous hidden Markov models. Two methods are propagated and compared throughout the paper. Within the first method a global statistics framework of an utterance is classified by Gaussian mixture models using derived features of the raw pitch and energy contour of the speech signal. A second method introduces increased te...

This paper describes creation of a test collection for Persian Part of Speech Tagging experiments. This collection was created by modifying a manually Part of Speech (POS) tagged Persian corpus with over two million tagged words. The original collection had a tag set of 550 tags that are more than what any machine learning algorithm can handle. The number of tags for these experiments was reduc...