# Implicit spoken language diarization

arXiv: https://arxiv.org/abs/2306.12913 · HTML: https://mlsanity.com/paper/2306.12913/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 25 references that are in the map.
- First posted on arXiv 22 Jun 2023.

## Builds on (most cited first, 6 of 6)

- [SpeechBrain: A General-Purpose Speech Toolkit](https://mlsanity.com/paper/2106.04624/) (2021)
- [A Review of Speaker Diarization: Recent Advances with Deep Learning](https://mlsanity.com/paper/2101.09624/) (2021)
- [CLSRIL-23: Cross Lingual Speech Representations for Indic Languages](https://mlsanity.com/paper/2107.07402/) (2021)
- [Exploiting Spectral Augmentation for Code-Switched Spoken Language Identification](https://mlsanity.com/paper/2010.07130/) (2020)
- [Spoken language change detection inspired by speaker change detection](https://mlsanity.com/paper/2302.05265/) (2023)
- [Joint Language Identification of Code-Switching Speech using Attention based E2E Network](https://mlsanity.com/paper/1907.06342/) (2019)

## Abstract (arXiv)

Spoken language diarization (LD) and related tasks are mostly explored using the phonotactic approach. Phonotactic approaches mostly use explicit way of language modeling, hence requiring intermediate phoneme modeling and transcribed data. Alternatively, the ability of deep learning approaches to model temporal dynamics may help for the implicit modeling of language information through deep embedding vectors. Hence this work initially explores the available speaker diarization frameworks that capture speaker information implicitly to perform LD tasks. The performance of the LD system on synthetic code-switch data using the end-to-end x-vector approach is 6.78% and 7.06%, and for practical data is 22.50% and 60.38%, in terms of diarization error rate and Jaccard error rate (JER), respectively. The performance degradation is due to the data imbalance and resolved to some extent by using pre-trained wave2vec embeddings that provide a relative improvement of 30.74% in terms of JER.