Next Article in Journal
CAAP: Context-Adaptive Adversarial Policy Learning Under Partial Observability
Previous Article in Journal
GPU-Parallelization of the Numerical Solution of Large-Scale Transient Partial Differential Equations
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Computers
Volume 15
Issue 10
10.3390/computers15100674
computers-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

Toward an Adaptive Speech-to-Summary Pipeline for Turkic Languages: Language-Specific ASR, Conditional Morphology-Aware Correction, Pivot Translation, and Summarization

by
Ualsher Tukeyev
,
Assem Shormakova
*,
Aidana Karibayeva
,
Diana Rakhimova
,
Balzhan Abduali
,
Oleg Myssov
,
Dina Amirova
,
Talgat Zhabayev
,
Nazym Rakhmanberdi
,
Zhansaya Segizbayeva
,
Rashid Aliyev
,
Nazerke Omarkhaliyeva
and
Dilnaz Akhmetova
Faculty of Information Technology and Artificial Intelligence, Farabi University, Almaty 050040, Kazakhstan
*
Author to whom correspondence should be addressed.
Computers 2026, 15(10), 674; https://doi.org/10.3390/computers15100674 (registering DOI)
Submission received: 14 August 2026 / Revised: 25 September 2026 / Accepted: 26 September 2026 / Published: 1 October 2026
(This article belongs to the Section AI-Driven Innovations)
Versions Notes

Abstract

Speech-to-Summary cascade performance for low-resource, morphologically rich languages depends on interactions among language, recognition errors, and translation direction. This study develops an adaptive Speech-to-Summary pipeline for six Turkic languages—Azerbaijani, Kazakh, Kyrgyz, Turkish, Turkmen, and Uzbek—integrating ASR, conditional morphology-aware post-processing (MAPP), MT, pivot routing, and summarization. Whisper-family models lead external benchmarks for Turkish, Kazakh, and Azerbaijani; MMS for Kyrgyz, Uzbek, and Turkmen. The Uzbek benchmark-best model proves unreliable on real recordings, requiring a different deployed model. Pause-based segmentation reduces ASR errors for Kazakh, Azerbaijani, Uzbek, and Kyrgyz but is not universally beneficial. MAPP shows no consistent improvement on strong real-ASR outputs; only 3.6% of real Uzbek substitution errors are reachable by the correction rules, supporting conditional rather than mandatory correction. MT evaluation across 22 FLORES-200 directions reveals direction-dependent performance and sensitivity to script compatibility. Pivot selection is language-dependent: direct-Kazakh routing performs better for Kazakh, Turkmen, and Turkish, whereas Azerbaijani benefits from an English pivot. The results support replacing a fixed cascade with a configurable architecture selecting ASR, segmentation, correction, MT, and pivot routing by language, error patterns, and deployment constraints. Routing decisions are currently made offline based on empirical evidence; automatic routing is left for future work.
Keywords: Turkic languages; Speech-to-Summary; automatic speech recognition; morphology-aware post-processing; machine translation; pivot translation; abstractive summarization; low-resource languages Turkic languages; Speech-to-Summary; automatic speech recognition; morphology-aware post-processing; machine translation; pivot translation; abstractive summarization; low-resource languages

Share and Cite

MDPI and ACS Style

Tukeyev, U.; Shormakova, A.; Karibayeva, A.; Rakhimova, D.; Abduali, B.; Myssov, O.; Amirova, D.; Zhabayev, T.; Rakhmanberdi, N.; Segizbayeva, Z.; et al. Toward an Adaptive Speech-to-Summary Pipeline for Turkic Languages: Language-Specific ASR, Conditional Morphology-Aware Correction, Pivot Translation, and Summarization. Computers 2026, 15, 674. https://doi.org/10.3390/computers15100674

AMA Style

Tukeyev U, Shormakova A, Karibayeva A, Rakhimova D, Abduali B, Myssov O, Amirova D, Zhabayev T, Rakhmanberdi N, Segizbayeva Z, et al. Toward an Adaptive Speech-to-Summary Pipeline for Turkic Languages: Language-Specific ASR, Conditional Morphology-Aware Correction, Pivot Translation, and Summarization. Computers. 2026; 15(10):674. https://doi.org/10.3390/computers15100674

Chicago/Turabian Style

Tukeyev, Ualsher, Assem Shormakova, Aidana Karibayeva, Diana Rakhimova, Balzhan Abduali, Oleg Myssov, Dina Amirova, Talgat Zhabayev, Nazym Rakhmanberdi, Zhansaya Segizbayeva, and et al. 2026. "Toward an Adaptive Speech-to-Summary Pipeline for Turkic Languages: Language-Specific ASR, Conditional Morphology-Aware Correction, Pivot Translation, and Summarization" Computers 15, no. 10: 674. https://doi.org/10.3390/computers15100674

APA Style

Tukeyev, U., Shormakova, A., Karibayeva, A., Rakhimova, D., Abduali, B., Myssov, O., Amirova, D., Zhabayev, T., Rakhmanberdi, N., Segizbayeva, Z., Aliyev, R., Omarkhaliyeva, N., & Akhmetova, D. (2026). Toward an Adaptive Speech-to-Summary Pipeline for Turkic Languages: Language-Specific ASR, Conditional Morphology-Aware Correction, Pivot Translation, and Summarization. Computers, 15(10), 674. https://doi.org/10.3390/computers15100674

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop