Multi-lingual phoneme recognition exploiting acoustic-phonetic similarities of sounds

نویسنده

  • Joachim Köhler
چکیده

The aim of this work is to exploit the acoustic-phonetic similarities between several languages. In recent work cross{ language HMM-based phoneme models have been used only for bootstrapping the language{dependent models and the multi{lingual approach has been investigated only on very small speech corpora. In this paper, we introduce a statistical distance measure to determine the similarities of sounds. Further, we present a new technique to model multi-lingual phonemes. The experiments are conducted with the OGI Multi-Language Telephone Speech Corpus for the languages American English, German and Spanish. In the rst experiment phoneme recognition rates between 39.0% and 53.9% are achieved using language{dependent models. Using cross{ language models yields for some phonemes improvement, but in average a degradation of recognition performance is observed. However, cross{language models speeds up the cross{language transfer and reduces the size of the phoneme inventory of multi-lingual speech recognition systems. Finally, a new method of modelling multi-lingual phonemes, which can be used for a variety of language, is presented. This technique reduces the number of phoneme-based units in a multi-lingual speech recognition system.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Allophone-based acoustic modeling for Persian phoneme recognition

Phoneme recognition is one of the fundamental phases of automatic speech recognition. Coarticulation which refers to the integration of sounds, is one of the important obstacles in phoneme recognition. In other words, each phone is influenced and changed by the characteristics of its neighbor phones, and coarticulation is responsible for most of these changes. The idea of modeling the effects o...

متن کامل

Cross Lingual Modelling Experiments for Indonesian

The extension of Large Vocabulary Continuous Speech Recognition (LVCSR) to resource poor languages such as Indonesian is hindered by the lack of transcribed acoustic data and appropriate pronunciation lexicons. Research has generally been directed toward establishing robust cross-lingual acoustic models, with the assumption that phonetic lexicons are readily available. This is not the case for ...

متن کامل

طراحی الگوریتم بازشناسی واجها با به کارگیری همبسته های آکوستیکی مشخصه های واجی

In the present paper, the phonological feature geometry of the Persian phonemes is analyzed in the form of articulate-free and articulate-bound features based on the articulator model of the nonlinear phonology. Then, the reference phonetic pattern of each feature that consists of one or a set of acoustic correlates, characterized by the quantitative or qualitative values in its phonological re...

متن کامل

A welsh speech database: preliminary results

A speech database for Welsh was recorded in a studio from read text by a few speakers. The purpose is to investigate the acoustic characteristics of Welsh speech sounds and prosody. It can also serve as a resource for future work in speech synthesis and recognition. The speech is labelled by hand at the acoustic phonetic level, and labelled semi-automatically at the phoneme, syllable, and word ...

متن کامل

Concurrent Constraint Programming and Tree-Based Acoustic Modelling

The design of acoustic models is key to a reliable connection between acoustic waveform and linguistic message in terms of individual speech units. We present an original application of concurrent constraint programming in this important area of spoken language processing. The application presented here employs concurrent constraint programming – represented by Mozart/Oz [1] – to overcome the p...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1996