paper-with-me

홈 › Papers

Multilingual Text-to-Speech Synthesis for Turkic Languages Using Transliteration

2023-05-25 · Rustem Yeshpanov, Saida Mussakhojayeva, Yerbolat Khassanov

This work aims to build a multilingual text-to-speech (TTS) synthesis system for ten lower-resourced Turkic languages: Azerbaijani, Bashkir, Kazakh, Kyrgyz, Sakha, Tatar, Turkish, Turkmen, Uyghur, and Uzbek. We specifically target the zero-shot learning scenario, where a TTS model trained using the data of one language is applied to synthesise speech for other, unseen languages. An end-to-end TTS system based on the Tacotron 2 architecture was trained using only the available data of the Kazakh language. To generate speech for the other Turkic languages, we first mapped the letters of the Turkic alphabets onto the symbols of the International Phonetic Alphabet (IPA), which were then converted to the Kazakh alphabet letters. To demonstrate the feasibility of the proposed approach, we evaluated the multilingual Turkic TTS model subjectively and obtained promising results. To enable replication of the experiments, we make our code and dataset publicly available in our GitHub repository.

📄 PDF Abstract BibTeX arXiv:2305.15749

Code (1)

is2ai/turkictts 공식 구현 pytorch

Tasks

Speech Synthesistext-to-speechText to SpeechText-To-Speech SynthesisTransliterationZero-Shot Learning

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
Highway Layer 설명 없음
BiGRU A Bidirectional GRU, or BiGRU, is a sequence processing model that consists of two GRUs. one taking the input in a forward…
Residual Connection 설명 없음
Batch Normalization 설명 없음
Highway Network A Highway Network is an architecture designed to ease gradient-based training of very deep networks. They allow unimpeded information flow across several layers on…
Zoneout Zoneout is a method for regularizing RNNs. At each timestep, zoneout stochastically forces some…

Similar Papers 제목 키워드 기반

Cross-Lingual Transfer and Parameter-Efficient Adaptation in the Turkic Language Family: A Theoretical Framework for Low-Resource Language Models

2026-03-13 · O. Ibrahimzade, K. Tabasaransky arxiv

Large language models (LLMs) have transformed natural language processing, yet their capabilities remain uneven across languages. Most multilingual models are trained primarily on high-resource languages, leaving many la…

parameter-efficient fine-tuningRepresentation LearningCross-Lingual Transfer

TurkicNLP: An NLP Toolkit for Turkic Languages

2026-02-22 · Sherzod Hakimov arxiv

Natural language processing for the Turkic language family, spoken by over 200 million people across Eurasia, remains fragmented, with most languages lacking unified tooling and resources. We present TurkicNLP, an open-s…

Part-Of-Speech TaggingMachine TranslationDependency Parsing

TUMLU: A Unified and Native Language Understanding Benchmark for Turkic Languages

2025-02-16 · Jafar Isbarov, Arofat Akhundjanova, Mammad Hajili, Kavsar Huseynova 외

Being able to thoroughly assess massive multi-task language understanding (MMLU) capabilities is essential for advancing the applicability of multilingual language models. However, preparing such benchmarks in high quali…

Machine TranslationMMLUMulti-task Language Understanding

Bytes are All You Need: End-to-End Multilingual Speech Recognition and Synthesis with Bytes

2018-11-22 · Bo Li, Yu Zhang, Tara Sainath, Yonghui Wu 외

We present two end-to-end models: Audio-to-Byte (A2B) and Byte-to-Audio (B2A), for multilingual speech recognition and synthesis. Prior work has predominantly used characters, sub-words or words as the unit of choice to …

Allspeech-recognitionSpeech RecognitionSpeech Synthesis

Virtuoso: Massive Multilingual Speech-Text Joint Semi-Supervised Learning for Text-To-Speech

2022-10-27 · Takaaki Saeki, Heiga Zen, Zhehuai Chen, Nobuyuki Morioka 외

This paper proposes Virtuoso, a massively multilingual speech-text joint semi-supervised learning framework for text-to-speech synthesis (TTS) models. Existing multilingual TTS typically supports tens of languages, which…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Speech RecognitionSpeech Synthesis+3