Lithuanian Speech Recognition Using Purely Phonetic Deep Learning

Laurynas Pipiras, Rytis Maskeliūnas, Robertas Damaševičius

Computers 2019 article cited by 12

Source Open-access PDF More in Software & Coding

importance 4/10 solved Speech Recognition and Synthesis speech recognition stage: research

Problem

Automatic speech recognition for Lithuanian had attracted little research, and models built for languages like English could not be directly adopted due to complicated language structure and scarce data.

Why it matters

Lithuanian speakers lack speech recognition tools available for widely spoken languages.

What the AI did

Two deep learning encoder-decoder models (traditional and with attention) identify spoken Lithuanian words purely from their phoneme sequences.

Results

Accuracy 0.993 on isolated speech recognition; 0.992 on long phrase recognition

Impact

Demonstrated near-99% accuracy on the authors' Lithuanian speech recognition tasks.

Record

Venue	Computers
Published	2019
Work type	article
Authors	Laurynas Pipiras, Rytis Maskeliūnas, Robertas Damaševičius
Citations	12 (OpenAlex, at import time)
References	58
Model or method	Encoder-decoder models, one with attention mechanism
Organization	not stated in source
Primary source	https://doi.org/10.3390/computers8040076
Open access	gold
Keywords	speech recognition, Lithuanian, deep learning, encoder-decoder, phonemes, attention

Importance rating

4 / 10

real but narrower advance

Addresses lack of ASR for a less-studied language; real but narrow benefit for Lithuanian speakers, no scale stated.

Basis: inferred. Judged from the source text, which gives no explicit scale. Stated scale: not stated in source. Method and limits.

More in Software & Coding

#	Paper	Year	Citations	Importance
1	ImageNet classification with deep convolutional neural networks Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton	2017	106,345	8
2	Deep Residual Learning for Image Recognition Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun	2016	221,134	8
3	Faster sorting algorithms discovered using deep reinforcement learning Daniel J. Mankowitz, Andrea Michi, Anton Zhernov, Marco Gelmi, Marco S...	2023	175	8
4	A deep learning‐based approach for software vulnerability detection using code metrics Fazli Subhan, Xiaoxue Wu, Lili Bo, Xiaobing Sun, Muhammad Rahman	2022	42	7
5	Deep Learning-Based Attack Detection and Classification in Android Devices Alfonso Gómez, Antonio Muñoz	2023	41	7