Kazakh

McCollum, Adam G.; Chen, Si

doi:10.1017/s0025100319000185

Cited by 5 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, the methodology used here does not always produce results consistent with gradient phonology. Second, the same general pattern of gradient fronting of back vowels is found in neighboring Kazakh (McCollum 2015;McCollum & Chen 2019). Furthermore, the Kazakh results have persisted across three different phrasal contexts, which more firmly establishes that this result is not due to the particular protocol used in this study.…”

Section: Discussionsupporting

confidence: 72%

Gradient morphophonology: Evidence from Uyghur vowel harmony

McCollum

2019

AMP

View full text Add to dashboard Cite

For the Structuralists and early Generativists (e.g. Bloomfield 1933; Chomsky & Halle 1968), all grammatical knowledge was by definition discrete and categorical. Since phonetic patterns are gradient, early work argued that phonetics was extra-grammatical. However, a significant body of work has since shown that phonetic patterns are language-specific and must constitute part of a speaker’s knowledge about their language (e.g. Keating 1985). As a result, linguistic knowledge is not ontologically categorical. For other areas of the grammar, though, much work continues to assume that linguistic knowledge is categorical. In this paper, I investigate the categoricality of phonological patterns using acoustic vowel harmony data from Uyghur. By comparing subphonemic variation in Uyghur with attested patterns of phonetic reduction and interpolation, I demonstrate that gradience is not always derivable from phonetic forces. On these grounds I argue that vowel harmony, and by extension phonology, may be gradient. Furthermore, the claim that gradience plays a larger role in linguistic representations is also supported by a number of descriptive works, which suggest that gradient harmony may occur in a wide range of languages. Building on experimental, and typological evidence, I thus contend that gradience isn’t restricted to phonetics, but pervades both the phonological and phonetic modules of the grammar.

show abstract

Section: Discussionsupporting

confidence: 72%

Gradient morphophonology: Evidence from Uyghur vowel harmony

McCollum

2019

AMP

View full text Add to dashboard Cite

show abstract

“…Actually, since our focus in the paper was the three languages in China, the observations could be different from those found for the same languages in the middle of Asia. For example, the language description of Kazakh we presented in Appendix B is quite different from recent accounts by other authors [167,168], although both were carefully designed and checked by linguists. Besides, for Uyghur, Kazakh, and Kyrgyz, based on the one-to-one letter-to-phoneme mapping, uncertainty in pronunciation will be reflected in the writing system, leading to noise in the vocabularies and language models.…”

Section: Conclusion and Discussionmentioning

confidence: 99%

Automatic Speech Recognition for Uyghur, Kazakh, and Kyrgyz: An Overview

Maimaitiyiming

Nijat

et al. 2022

Applied Sciences

View full text Add to dashboard Cite

With the emergence of deep learning, the performance of automatic speech recognition (ASR) systems has remarkably improved. Especially for resource-rich languages such as English and Chinese, commercial usage has been made feasible in a wide range of applications. However, most languages are low-resource languages, presenting three main difficulties for the development of ASR systems: (1) the scarcity of the data; (2) the uncertainty in the writing and pronunciation; (3) the individuality of each language. Uyghur, Kazakh, and Kyrgyz as examples are all low-resource languages, involving clear geographical variation in their pronunciation, and each language possesses its own unique acoustic properties and phonological rules. On the other hand, they all belong to the Altaic language family of the Altaic branch, so they share many commonalities. This paper presents an overview of speech recognition techniques developed for Uyghur, Kazakh, and Kyrgyz, with the purposes of (1) highlighting the techniques that are specifically effective for each language and generally effective for all of them and (2) discovering the important factors in promoting the speech recognition research of low-resource languages, by a comparative study of the development path of these three neighboring languages.

show abstract

“…We used the method of PCA to reduce the dimension of the vectors to two-dimensional in order to compactly visualize them (Figure 5). It can be noted by the example of the letters of the area highlighted by the circle that their vectors were generated appropriately since these letters are combined with each other in accordance with the laws of synharmonism [5]. Another option would be to use pre-trained Word2Vec embeddings for words, and then use these embeddings to generate character embeddings.…”

Section: Character Embedding In the Corpusmentioning

confidence: 99%

“…In the Kazakh language, we use 15 letters to represent vowel sounds and 25 for consonant sounds [5]. But for the optimality of the experiments, the letter "ё" was excluded from the list of vowels and the letter "у" was also duplicated in the list of consonants, since it can be both a vowel and a consonant, depending on the context of the sounds and extended with separating letters "ъ" and "ь", although they are found only inside loanwords.…”

Section: Constructing a Filter From Embedding Vectors For A Convoluti...mentioning

confidence: 99%

See 1 more Smart Citation

The Development of a Kazakh Speech Recognition Model Using a Convolutional Neural Network with Fixed Character Level Filters

Kadyrbek

Mansurova

Shomanov

et al. 2023

BDCC

View full text Add to dashboard Cite

This study is devoted to the transcription of human speech in the Kazakh language in dynamically changing conditions. It discusses key aspects related to the phonetic structure of the Kazakh language, technical considerations in collecting the transcribed audio corpus, and the use of deep neural networks for speech modeling. A high-quality decoded audio corpus was collected, containing 554 h of data, giving an idea of the frequencies of letters and syllables, as well as demographic parameters such as the gender, age, and region of residence of native speakers. The corpus contains a universal vocabulary and serves as a valuable resource for the development of modules related to speech. Machine learning experiments were conducted using the DeepSpeech2 model, which includes a sequence-to-sequence architecture with an encoder, decoder, and attention mechanism. To increase the reliability of the model, filters initialized with symbol-level embeddings were introduced to reduce the dependence on accurate positioning on object maps. The training process included simultaneous preparation of convolutional filters for spectrograms and symbolic objects. The proposed approach, using a combination of supervised and unsupervised learning methods, resulted in a 66.7% reduction in the weight of the model while maintaining relative accuracy. The evaluation on the test sample showed a 7.6% lower character error rate (CER) compared to existing models, demonstrating its most modern characteristics. The proposed architecture provides deployment on platforms with limited resources. Overall, this study presents a high-quality audio corpus, an improved speech recognition model, and promising results applicable to speech-related applications and languages beyond Kazakh.

show abstract

Kazakh

Cited by 5 publications

References 12 publications

Gradient morphophonology: Evidence from Uyghur vowel harmony

Gradient morphophonology: Evidence from Uyghur vowel harmony

Automatic Speech Recognition for Uyghur, Kazakh, and Kyrgyz: An Overview

The Development of a Kazakh Speech Recognition Model Using a Convolutional Neural Network with Fixed Character Level Filters

Contact Info

Product

Resources

About