Subjects: Psychology >> Other Disciplines of Psychology submitted time 2023-05-23
Abstract： The syllable has long been regarded as a one-order phonetic unit without being known as an illusion; vowels and consonants have been the most solid units of phonetics without being known as impostors of letters; and the historical misconception that vowels and consonants make up syllables has gone unrecognized. The article analyzes the reasons why syllables have no linguistic status, describes the confusion over the unknown origin of vowels and consonants, analyzes the relationship between syllables and letters from a chronological perspective,and experimentally explores the unitary form of speech production, and reveals that the temporal structure of articulation prescribes the nature of syllables from a co-temporal perspective. Based on this, the paper redefines syllables in a subversive way, and reshapes the true status and value of vowels and consonants. The article concludes by suggesting that syllables evolved in a long history and eventually produced complex word syllable structures and limited pure syllable forms through shedding, whereby a set of minimal syllable analysis schemes and syncopation principles can be proposed.
Peer Review Status:
Awaiting Review
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-08-13 Cooperative journals: 《计算机应用研究》
Abstract： In view of the low resource of endangered languages, the establishment and research of end-to-end speech recognition model can explore new ways for the protection and transmission of endangered languages. this paper combined dynamic bi-directional long short-term memory network and connectionist temporal classification model into an end-to-end speech recognition model. When performing phoneme-level recognition training, the batch size of the data passed into the model can be adaptively adjusted according to the training model, which not only speeds up the convergence but also improves the generalization of the model. By adjusting the hierarchy of the deep neural network and extracting different phonetic features for model comparison, the experimental results show that both the endangered languages - Lvsu and Tujia have good recognition results.
Hits
Hits
Downloads
Comment