The main goal of this work is to describe a new model for a large vocabulary continuous speech recognition system using a phonetic-phonological approach. This work proposes a statistical phonetic structure, applied at the phoneticphonological level, to improve the speech recognition performance in systems with phonetic-phonological modeling. It is showed that the general likelihood scores are i...

A Conditional Random Field is a mathematical model for sequences that is similar in many ways to a Hidden Markov Model, but is discriminative rather than generative in nature. In this paper, we explore the application of the CRF model to ASR processing of discriminative phonetic features by building a system that performs first-pass phonetic recognition using discriminatively trained phonetic f...

A system is described that automatically generates phonetic transcriptions for German orthographic words. The entire generative process consists of two main steps. In the first step, the system segments the words into their morphs, or prefixes, stems, and suffixes. This segmentation is very important for the transcription of German words, because the pronunciation of the letters depends also on...

A Conditional Random Field is a mathematical model for sequences that is similar in many ways to a Hidden Markov Model, but is discriminative rather than generative in nature. In this paper, we explore the application of the CRF model to ASR processing of discriminative phonetic features by building a system that performs first-pass phonetic recognition using discriminatively trained phonetic f...

There are very few input systems supporting Taiwanese and Hakka on the market at present. Our purpose is to provide an input system supporting Mandarin and Taiwanese which is toneless and complies with multiple types of phonetic symbols, we hope that such an approach can resolve the problems resulting from tone and phonetic symbols. In this paper, we use an algorithm based on three continuous l...

This paper describes the exploration of text-independent speaker identification using novel approaches based on speakers’ phonetic features instead of traditional acoustic features. Different phonetic speaker identification approaches are discussed in this paper and evaluated using two speaker identification systems: one multilingual system and one single language multiple-engine system. Furthe...

This paper presents our study on different phonetic segmentation methods based on hidden Markov models evaluated against a Hebrew speech corpus. We investigated methods for fully automatic phonetic segmentation using only the corpus which should be segmented and automatically generated phonetic transcriptions. A new method for phonetic boundary correction based on spectral variation of the spee...

In this paper, we investigate multiple approaches for automatically detecting intoxicated speakers given samples of their speech. Intoxicated speech in a given language can be viewed simply as a different accent of this language; therefore we adopt our recent approach to dialect and accent recognition to detect intoxication. The system models phonetic structural differences across sober and int...

The approach to phonological comparison adopted in UPSID as well as other studies fails to recognize the abstract nature of even the most phonetically based definition of a phonemic system. Phonemes receive a simple phonetic translation based on one allophone. Phonological comparison is therefore carried out using no more than arbitrary selections of the phonetics of the languages involved. Pho...