# Signal Combination for Language Identification

arXiv: https://arxiv.org/abs/1910.09687 · HTML: https://mlsanity.com/paper/1910.09687/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Oct 2019.

## Built on by (most cited first, 4 of 4)

- [Streaming End-to-End Multilingual Speech Recognition with Joint Language Identification](https://mlsanity.com/paper/2209.06058/) (2022)
- [Attentive Temporal Pooling for Conformer-based Streaming Language Identification in Long-form Speech](https://mlsanity.com/paper/2202.12163/) (2022)
- [Confidence-based Ensembles of End-to-End Speech Recognition Models](https://mlsanity.com/paper/2306.15824/) (2023)
- [Improving Multilingual ASR in the Wild Using Simple N-best Re-ranking](https://mlsanity.com/paper/2409.18428/) (2024)

## Abstract (arXiv)

Google's multilingual speech recognition system combines low-level acoustic signals with language-specific recognizer signals to better predict the language of an utterance. This paper presents our experience with different signal combination methods to improve overall language identification accuracy. We compare the performance of a lattice-based ensemble model and a deep neural network model to combine signals from recognizers with that of a baseline that only uses low-level acoustic signals. Experimental results show that the deep neural network model outperforms the lattice-based ensemble model, and it reduced the error rate from 5.5% in the baseline to 4.3%, which is a 21.8% relative reduction.