A Text Normalization Method for Speech Synthesis Based on Local Attention Mechanism

Speech recognition based on a text-to-speech synthesis system

developing a pattern based on speech acts and language functions for developing materials for the course “ the study of islamic texts translation”

هدف پژوهش حاضر ارائه ی الگویی بر اساس کنش گفتار و کارکرد زبان برای تدوین مطالب درس "بررسی آثار ترجمه شده ی اسلامی" می باشد. در الگوی جدید، جهت تدوین مطالب بهتر و جذاب تر، بر خلاف کتاب-های موجود، از مدل های سطوح گفتارِ آستین (1962)، گروه بندی عملکردهای گفتارِ سرل (1976) و کارکرد زبانیِ هالیدی (1978) بهره جسته شده است. برای این منظور، 57 آیه ی شریفه، به صورت تصادفی از بخش-های مختلف قرآن انتخاب گردید...

Local Monotonic Attention Mechanism for End-to-End Speech Recognition

Recently, encoder-decoder neural networks have shown impressive performance on many sequence-related tasks. The architecture commonly uses an attentional mechanism which allows the model to learn alignments between the source and the target sequence. Most attentional mechanisms used today is based on a global attention property which requires a computation of a weighted summarization of the who...

Myanmar Number Normalization for Text-to-Speech

--Text Normalization is an essential module for Text-to-Speech (TTS) system as TTS systems need to work on real text. This paper describes Myanmar number normalization designed for Myanmar Text-to-Speech system. Semiotic classes forMyanmar language are identified by the study of Myanmar text corpus and Weighted Finite State Transducers (WFST) based Myanmar number normalization is implemented. N...

Residual-based speech modification algorithms for text-to-speech synthesis

This paper presents a set of novel algorithms for the signal modification component of concatenative text-to-speech systems. The algorithms described here are based around the LPC analysis/synthesis framework, and achieve prosodic modification by time-domain processing of the LPC residual. The modified residual is then recombined with the all-pole spectral estimate to synthesise the new speech ...