This paper discusses the problem of handling “foreign” speech sounds in Swedish speech technology systems, in particular speech synthesis. A production study is made, where it is shown that Swedish speakers add foreign speech sounds, here termed ‘xenophones’, to their phone repertoire when reading Swedish sentences with embedded English names and words. As a result of the observations, the phon...

hypernasality is a frequently occurring resonance disorder in children with cleft palate. generally an operation is necessary to reduce the hypernasality and therefore an assessment of hypernasality is imperative to quantify the effect of the surgery and design the speech therapy sessions which are crucial after surgery. in this paper, a new quantitative method is proposed to estimate hypernasa...

introduction: speech intelligibility, the ability to be understood verbally by listeners, is the gold standard for assessing the effectiveness of cochlear implantation. thus, the goal of this study was to compare the speech intelligibility between normal-hearing and cochlear-implanted children using the persian intelligibility test.   materials and methods: twenty-six cochlear-implanted childre...

The issue of representing speech rhythm is understood in this paper as the search for relevant primary parameters that will allow the formalisation of speech rhythm. Current speech synthesisers show that phonological models are not satisfactory with respect to the modelling of speech rhythmicity. Our analysis indicates that this may be in part related to the formalisation of rhythmic representa...

Children present a unique challenge to automatic speech recognition. Today’s state-of-the-art speech recognition systems still have problems handling children’s speech because acoustic models are trained on data collected from adult speech. In this paper we describe an inexpensive way to mend this problem. We collected children’s speech when they interact with an automated reading tutor. These ...

In a speech recognition system, environmental mismatch between speech models and test speech causes serious performance degradation. To solve this environmental mismatch problem, smoothing process is one of the most widely used techniques. In this paper, an adaptive signal limiter (ASL) is developed to smooth speech features so that the undesired spectral variations could be effectively reduced...

This paper proposes a deterministic annealing based training algorithm for Bayesian speech recognition. The Bayesian method is a statistical technique for estimating reliable predictive distributions by marginalizing model parameters. However, the local maxima problem in the Bayesian method is more serious than in the ML-based approach, because the Bayesian method treats not only state sequence...

the aim of this paper is to report on an attempt to design and implement an intelligent system capable of generating the correct part of speech for a given sentence while the sentence is totally new to the system and not stored in any database available to the system. it follows the same steps a normal individual does to provide the correct parts of speech using a natural language processor. it...