Turkish speech corpora and recognition tools developed by porting SONIC: Towards multilingual speech recognition

Date

2007-10-01

Author

Salor, Ozgul
Pellom, Bryan L.
Çiloğlu, Tolga
Demirekler, Mubeccel

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

135
views

0
downloads

This paper presents work on developing speech corpora and recognition tools for Turkish by porting SONIC, a speech recognition tool developed initially for English at the Center for Spoken Language Research of the University of Colorado at Boulder. The work presented in this paper had two objectives: The first one is to collect a standard phonetically-balanced Turkish microphone speech corpus for general research use. A 193-speaker triphone-balanced audio corpus and a pronunciation lexicon for Turkish have been developed. The corpus has been accepted for distribution by the Linguistic Data Consortium (LDC) of the University of Pennsylvania in October 2005, and it will serve as a standard corpus for Turkish speech researchers. The second objective was to develop speech recognition tools (a phonetic aligner and a phone recognizer) for Turkish, which provided a starting point for obtaining a multilingual speech recognizer by porting SONIC to Turkish. This part of the work was the first port of this particular recognizer to a language other than English; subsequently, SONIC has been ported to over 15 languages. Using the phonetic aligner developed, the audio corpus has been provided with word, phone and HMM-state level alignments. For the phonetic aligner, it is shown that 92.6% of the automatically labeled phone boundaries are placed within 20 ins of manually labeled locations for the Turkish audio corpus. Finally, a phone recognition error rate of 29.2% is demonstrated for the phone recognizer.

Subject Keywords

Speech recognition, Speech corpora, Language porting, Phone recognizer, Phonetic aligner

URI

https://hdl.handle.net/11511/41393

Journal

COMPUTER SPEECH AND LANGUAGE

DOI

https://doi.org/10.1016/j.csl.2007.01.001

Collections

Department of Electrical and Electronics Engineering, Article

Suggestions

OpenMETU
Core

Turkish large vocabulary continuous speech recognition by using limited audio corpus Susman, Derya; Yazıcı, Adnan; Köprü, Selçuk; Department of Computer Engineering (2012) Speech recognition in Turkish Language is a challenging problem in several perspectives. Most of the challenges are related to the morphological structure of the language. Since Turkish is an agglutinative language, it is possible to generate many words from a single stem by using suffixes. This characteristic of the language increases the out-of-vocabulary (OOV) words, which degrade the performance of a speech recognizer dramatically. Also, Turkish language allows words to be ordered in a free manner, whic...
On lexicon creation for turkish LVCSR Kadri, Hacıoğlu; Bryan, Pellom; Çiloğlu, Tolga; Öztürk, Özlem; Mikko, Kurimo; Mathias, Creutz (null; 2003-09-14) In this paper, we address the lexicon design problem in Turkish large vocabulary speech recognition. Although we focus only on Turkish, the methods described here are general enough that they can be considered for other agglutinative languages like Finnish, Korean etc. In an agglutinative language, several words can be created from a single root word using a rich collection of morphological rules. So, a virtually infinite size lexicon is required to cover the language if words are used as the basic units. T...
Wireless speech recognition using fixed point mixed excitation linear prediction (MELP) vocoder Acar, D; Karci, MH; Ilk, HG; Demirekler, Mübeccel (2002-07-19) A bit stream based front-end for wireless speech recognition system that operates on fixed point mixed excitation linear prediction (MELP) vocoder is presented in this paper. Speaker dependent, isolated word recognition accuracies obtained from conventional and bit stream based front-end systems are obtained and their statistical significance is discussed. Feature parameters are extracted from original (wireline) and decoded speech (conventional) and from the quantized spectral information (bit stream) of t...
Bimodal automatic speech segmentation based on audio and visual information fusion Akdemir, Eren; Çiloğlu, Tolga (2011-07-01) Bimodal automatic speech segmentation using visual information together with audio data is introduced. The accuracy of automatic segmentation directly affects the quality of speech processing systems using the segmented database. The collaboration of audio and visual data results in lower average absolute boundary error between the manual segmentation and automatic segmentation results. The information from two modalities are fused at the feature level and used in a HMM based speech segmentation system. A T...
Spectral modification for context-free voice conversion using MELP speech coding framework Salor, O; Demirekler, Mübeccel (2004-10-22) In this work, we have focused on spectral modification of speech for voice con version from one speaker to another. Speech conversion aims to modify the speech of one speaker such that the modified speech sounds as if spoken by another speaker. MELP (Mixed Excitation Linear Prediction) speech coding algorithm has been used as speech analysis and synthesis framework. Using a 230-sentence triphone balanced database of the two speakers, a mapping between the 4-stage vector quantization indexes for line spectra...

Citation Formats

O. Salor, B. L. Pellom, T. Çiloğlu, and M. Demirekler, “Turkish speech corpora and recognition tools developed by porting SONIC: Towards multilingual speech recognition,” COMPUTER SPEECH AND LANGUAGE, pp. 580–593, 2007, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/41393.