Performance and Evaluation
This chapter presents the results achieved by modeling cross-word pronunciation variation problem of MSA. We practically investigated two MSA phonological rules (Idgham and Iqlaab) which significantly enhanced recognition accuracy. Three ASR’s metrics were measured: word error rate (WER), out of vocabulary (OOV), and perplexity (PP).
KeywordsLanguage Model Compound Word Baseline System Word Error Rate Substitution Error
- Gallwitz F, Noth E, et al (1996) A category based approach for recognition of out-of-vocabulary words. In: Proceedings of fourth international conference on spoken language, 1996. ICSLP 96Google Scholar
- Jelinek F (1999) Statistical methods for speech recognition, Language, speech and communication series. MIT, Cambridge, MAGoogle Scholar
- Jurafsky D, Martin J (2009) Speech and language processing, 2nd edn. Pearson, NJGoogle Scholar
- Plötz T (2005) Advanced stochastic protein sequence analysis, Ph.D. thesis, Bielefeld UniversityGoogle Scholar