# Automatic Spoken Language Identification using a Time-Delay Neural Network

arXiv: https://arxiv.org/abs/2205.09564 · HTML: https://mlsanity.com/paper/2205.09564/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 21 references that are in the map.
- First posted on arXiv 19 May 2022.

## Builds on (most cited first, 5 of 5)

- [MLS: A Large-Scale Multilingual Dataset for Speech Research](https://mlsanity.com/paper/2012.03411/) (2020)
- [TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptation](https://mlsanity.com/paper/1805.04699/) (2018)
- [The Multilingual TEDx Corpus for Speech Recognition and Translation](https://mlsanity.com/paper/2102.01757/) (2021)
- [MediaSpeech: Multilanguage ASR Benchmark and Dataset](https://mlsanity.com/paper/2103.16193/) (2021)
- [Att-HACK: An Expressive Speech Database with Social Attitudes](https://mlsanity.com/paper/2004.04410/) (2020)

## Abstract (arXiv)

Closed-set spoken language identification is the task of recognizing the language being spoken in a recorded audio clip from a set of known languages. In this study, a language identification system was built and trained to distinguish between Arabic, Spanish, French, and Turkish based on nothing more than recorded speech. A pre-existing multilingual dataset was used to train a series of acoustic models based on the Tedlium TDNN model to perform automatic speech recognition. The system was provided with a custom multilingual language model and a specialized pronunciation lexicon with language names prepended to phones. The trained model was used to generate phone alignments to test data from all four languages, and languages were predicted based on a voting scheme choosing the most common language prepend in an utterance. Accuracy was measured by comparing predicted languages to known languages, and was determined to be very high in identifying Spanish and Arabic, and somewhat lower in identifying Turkish and French.