In this paper we investigate named entity transliteration based on a phonetic scoring method. The phonetic method is computed using phonetic features and carefully designed pseudo features. The proposed method is tested with four languages – Arabic, Chinese, Hindi and Korean – and one source language – English, using comparable corpora. The proposed method is developed from the phonetic method ...

Annotated speech corpora are indispensable to various areas of speech research. In this paper, we present a novel discriminative training approach for HMM-based automatic phonetic segmentation. The objective of the proposed minimum boundary error (MBE) discriminative training approach is to minimize the expected boundary errors over a set of phonetic alignments represented as a phonetic lattice...

Recent studies have shown that talkers implicitly imitate/accommodate the phonetic properties of recently heard speech [1, 2]. However, it has also been shown that this phonetic imitation effect is not an automatic process [3, 4]: in [3], the artificially lengthened VOT on /p/ was imitated in a non-shadowing task, while shortened VOT (which could jeopardize phonemic contrast) was not imitated, ...

Same-different reaction times (RTs) were obtained to pairs of synthetic speech sounds ranging perceptually from /ba/ through /pa/. Listeners responded "same" if both stimuli in a pair were the same phonetic segments (i.e., /ba/-/ba/ or /pa/-/pa/) or "different" if both stimuli were different phonetic segments (i.e., /ba/-/pa/ or /pa/-/ba/). RT for "same" responses was faster to pairs of acousti...

During speech perception, linguistic elements such as consonants and vowels are extracted from a complex acoustic speech signal. The superior temporal gyrus (STG) participates in high-order auditory processing of speech, but how it encodes phonetic information is poorly understood. We used high-density direct cortical surface recordings in humans while they listened to natural, continuous speec...

The present study aims to establish the most frequently used perceptual cues (and their combinations) to high degree of phonetic prominence (HDP) and low degree of phonetic prominence (LDP) in large units of speech – in this paper they are referred to as ‘phrases’ and ‘phonetic paragraphs’. The language under investigation is Standard British English. The results of the perception experiment su...

The demand and the importance of Chinese teaching have increased continuously. In order to assist the Chinese learners in composing Chinese characters and increase their learning efficiency, Chinese components teaching method is adopted. The learners can find the clues to both the pronunciations and the meanings of Chinese characters from Chinese components, and semantic-phonetic compounds and ...

The usual approach to automatic continuous speech recognition is what can be called the acoustic-phonetic modelling approach. In this approach, voice is considered to hold two different kinds of information—acoustic and phonetic—. Acoustic information is represented by some kind of feature extraction out of the voice signal, and phonetic information is extracted from the vocabulary of the task ...

We pursue an analysis of the relation between qualitative syllable parses and their quantitative phonetic consequences. To do this, we express the statistics of a symbolic organization corresponding to a syllable parse in terms of continuous phonetic parameters which quantify the timing of the consonants and vowels that make up syllables: consonantal plateau durations, vowel durations, and thei...

Phonetic Recognition for FaceMe! William Goldenthal, Keith Waters, Jean-Manuel Van Thong, and Oren Glickman email: fthal, waters, jmvt, [email protected] Digital Equipment Corporation Cambridge Research Laboratory One Kendall Sq., Building 700 Cambridge, Massachusetts 02139 USA ABSTRACT The goal of this work is to use phonetic recognition to drive a synthetic image with speech. Phonetic units a...