# Automatic Speech Recognition with Very Large Conversational Finnish and Estonian Vocabularies

arXiv: https://arxiv.org/abs/1707.04227 · HTML: https://mlsanity.com/paper/1707.04227/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jul 2017.

## Built on by (most cited first, 5 of 5)

- [Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies](https://mlsanity.com/paper/2407.13623/) (2024)
- [Lahjoita puhetta -- a large-scale corpus of spoken Finnish with some benchmarks](https://mlsanity.com/paper/2203.12906/) (2022)
- [Hierarchical Softmax for End-to-End Low-resource Multilingual Speech Recognition](https://mlsanity.com/paper/2204.03855/) (2022)
- [The Current State of Finnish NLP](https://mlsanity.com/paper/2109.11326/) (2021)
- [Finnish Parliament ASR corpus - Analysis, benchmarks and statistics](https://mlsanity.com/paper/2203.14876/) (2022)

## Abstract (arXiv)

Today, the vocabulary size for language models in large vocabulary speech recognition is typically several hundreds of thousands of words. While this is already sufficient in some applications, the out-of-vocabulary words are still limiting the usability in others. In agglutinative languages the vocabulary for conversational speech should include millions of word forms to cover the spelling variations due to colloquial pronunciations, in addition to the word compounding and inflections. Very large vocabularies are also needed, for example, when the recognition of rare proper names is important.