In this paper, we describe the work on Chinese multi-dialect speech processing. Based on the phonetic analysis of ten Chinese dialects, we have created a Chinese super phonetic system for the Chinese speech recognition. To exam this phonetic system and develop Chinese dialect speech technology, we are building a multi-dialect speech corpus, which includes 10 dialect areas and 2000 speakers.

A multilingual phonetic representation and analysis system for different speech databases is presented. The need for such a system is first justified and then one is proposed based on the Worldbet phonetic alphabet. A phonetic class hierarchy is developed and a description of the hierarchical structural representation follows. Database access is based on the latter and is accomplished by defini...

The phonetic inventories of 13 Italian children at 18, 21, 24 and 27 months of age are presented. The children were taperecorded during a play interaction with the mother, and their vocalizations were phonetically transcribed. The individual phonetic inventories were calculated by applying the criteria put forward by Stoel-Gammon [1]: a consonantal singleton or cluster was attested only if word...

We present a phonetic algorithm that fuses existing techniques and introduces new features. This combination offers improved precision and recall.

Prosodic structure encodes grouping of words into hierarchically layered prosodic constituents, including the prosodic word, intermediate phrase (ip) and intonational phrase (IP). This paper investigates the phonetic encoding of prosodic structure from a corpus of scripted broadcast news speech through analysis of the acoustic correlates of prosodic boundary at three levels of prosodic structur...

In this paper, we present some recent improvements in our automatic speech segmentation system, which only needs the speech signal and the phonetic sequence of each sentence of a corpus to be trained. It estimates a GMM by using all the sentences of the training subcorpus, where each Gaussian distribution represents an acoustic class, which probability densities are combined with a set of condi...

This paper describes a text-independent speaker recognition system that achieves an equal error rate of less than 1% by combining phonetic, idiolect, and acoustic features. The phonetic system is a novel language-independent speakerrecognition system based on differences among speakers in dynamic realization of phonetic features (i.e., pronunciation), rather than spectral differences in voice q...

A phonetic dictionary is an essential component of a speech recognition system or a speech synthesis system. Our work targets the generation of an automatic pronunciation dictionary for the Tunisian Arabic, in particular in the field of rail transport. To do this, we created two tools of phonetic vowelized and unvowelized words in the Tunisian Arabic. The proposed method to automatically genera...

This article discusses the use of phonetic features in automatic speech recognition. The phonetic features are derived from acoustic parameters by means of Kohonen networks. Behind the use of phonetic features instead of standard acoustic parameters lies the assumption that it is useful to help the system to focus on linguistically relevant signal properties. Previous experiments using very sim...