This paper addresses some of the issues learned during the course of building a written language resource, called 'Peykare', for the contemporary Persian. After defining five linguistic varieties and 24 different registers based on these linguistic varieties, we collected texts for Peykare to do a linguistic analysis, including cross-register differences. For tokenization of Persian, we propose a descriptive generalization to normalize orthographic variations existing in texts. To annotate Peykare, we use EAGLES guidelines which result to have a hierarchy in the part-of-speech tags. To this aim, we apply a semi-automatic approach for the annotation methodology. In the paper, we also give a special attention to the Ezafe construction and homographs which are important in Persian text analyses.
A novel method for combining bigram model and Probabilistic Latent Semantic Analysis (PLSA) is introduced for language modeling. The motivation behind this idea is the relaxation of the "bag of words" assumption fundamentally present in latent topic models including the PLSA model. An EM-based parameter estimation technique for the proposed model is presented in this paper. Previous attempts to incorporate word order in the PLSA model are surveyed and compared with our new proposed model both in theory and by experimental evaluation. Perplexity measure is employed to compare the effectiveness of recently introduced models with the new proposed model. Furthermore, experiments are designed and carried out on continuous speech recognition (CSR) tasks using word error rate (WER) as the evaluation criterion. The superiority of the new bigram-PLSA model over Nie et al.'s bigram-PLSA and simple PLSA models is demonstrated in the results of our experiments. Experiments on BLLIP WSJ corpus show about 12% reduction in perplexity and 2.8% WER improvement compared to Nie et al.'s bigram-PLSA model.
The first large vocabulary speech recognition system for the Persian language is introduced in this paper. This continuous speech recognition system uses most standard and state-of-the-art speech and language modeling techniques. The development of the system, called Nevisa, has been started in 2003 with a dominant academic theme. This engine incorporates customized established components of traditional continuous speech recognizers and its parameters have been optimized for real applications of the Persian language. For this purpose, we had to identify the computational challenges of the Persian language, especially for text processing and extract statistical and grammatical language models for the Persian language. To achieve this, we had to either generate the necessary speech and text corpora or modify the available primitive corpora available for the Persian language. In the proposed system, acoustic modeling is based on hidden Markov models, and optimized decoding, pruning and language modeling techniques were used in the system. Both statistical and grammatical language models were incorporated in the system. MFCC representation with some modifications was used as the speech signal feature. In addition, a VAD was designed and implemented based on signal energy and zero-crossing rate. Nevisa is equipped with out-of-vocabulary capability for applications with medium or small vocabulary sizes. Powerful robustness techniques were also utilized in the system. Model-based approaches like PMC, MLLR and MAP, along with feature robustness methods such as CMS, PCA, RCC and VTLN, and speech enhancement methods like spectral subtraction and Wiener filtering, along with their modified versions, were diligently implemented and evaluated in the system. A new robustness method called PC-PMC was also proposed and incorporated in the system. To evaluate the performance and optimize the parameters of the system in noisy-environment tasks, four real noisy speech data sets were generated. The final performance of Nevisa in noisy environments is similar to the clean conditions, thanks to the various robustness methods implemented in the system. Overall recognition performance of the system in clean and noisy conditions assures us that the system is a real-world product as well as a competitive ASR engine.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.