TREN- Turkish speech recognition platform

Abstract

TREN (Turkish Recognition ENgine) is a modular, HMMbased (Hidden Markov Model) and speaker-independent speech recognition system whose system software architecture is based on Distributed Component Object Model (DCOM). TREN contains specialized modules that allow a full interoperable platform including a Turkish speech recognizer, feature extractor, end-point detector and a performance monitoring module. TREN has basically two layers: First layer is the central server that distributes the recognition calls to the appropriate remote servers according to their current CPU load of the recognition process after some speech signal preprocessing and the second layer consists of the remote servers which performs the critical recognition task. This component-based architecture enables TREN applicable to distributed environments. TREN is also trained by considering a wide variety of very common words those best represent the Turkish language. In order to obtain a such database a very large word corpus is collected and statistically the widest span of triphones representing Turkish is examined. TREN has been used to assist speech technologies which require a modular and multithreaded recognizer with dynamic load sharing facilities.

A detailed survey of Turkish automatic speech recognition

“…The alphabet has 29 letters [22]. Today, the development of voice, communication, and processing technologies necessitates the development of robust and reliable speech recognition engines that take into consideration the vocabulary, acoustic parameters, communication structures, and language models of the Turkic languages, which are considered as the languages of the Silk Road and are spoken by about 100 million people [23].…”

“…Even though there are many papers in the literature on speech recognition, very few of those studies are on the Turkish language. The majority of studies are on languages such as English, Chinese, Spanish, German, and French [23]. In development of intelligent devices, speech recognition techniques for many foreign languages, especially English, are largely used, and new technological devices come with speech recognition support, but none have Turkish support [31].…”

Customized deep learning based Turkish automatic speech recognition system supported by language model

“…Given that these challenges vary across different languages, designing an ASR system, especially for agglutinative languages like Turkish, is notably more complex than other languages. The structure of the Turkish language allows for the generation of billions of different morphological forms ( Palaz et al, 2005 ; Oyucu & Polat, 2023 ). In Turkish, which is in the agglutinative language group, the variety of words is significantly greater compared to languages such as English.…”

Analysis and Compensation of Sparse Packet Losses in Distributed Turkish Continuous Speech Recognition System

“…Dağıtık yapıda ses tanıma uygulamalarında ön işlem ve ses analizi bir bilgisayarda yapılırken, tanıma işlemi başka bilgisayarlarda yapılır [6] [7]. Haberleşme protokolü ve uygulamaya dönük olarak sistemin yapısını çok değişik sistemlerde, örneğin yük paylaşımı ya da çoklu kullanıma uygun tanımlamak mümkündür [7]. Dağıtılmış yapıda ses tanıma sistemlerinde band genişliğini düşürmek için ses öznitelik vektörlerini kodlayıp göndermek mümkündür [8].…”

“…IP üzerinden ise merkezi bir sunucu gerekli ses analizini yapıp tanıma işlemleri için en uygun uzak sunuculara paketleri gönderebilir[7]. Şekil 1'de örnek olarak dağıtık yapıda konuşma tanıma modeli gösterilmiştir.…”