# Exploring the Use of an Unsupervised Autoregressive Model as a Shared Encoder for Text-Dependent Speaker Verification

arXiv: https://arxiv.org/abs/2008.03615 · HTML: https://mlsanity.com/paper/2008.03615/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Aug 2020.

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

- [Probing self-supervised speech models for phonetic and phonemic information: a case study in aspiration](https://mlsanity.com/paper/2306.06232/) (2023)
- [Bi-APC: Bidirectional Autoregressive Predictive Coding for Unsupervised Pre-training and Its Application to Children's ASR](https://mlsanity.com/paper/2102.06816/) (2021)
- [Low Resource German ASR with Untranscribed Data Spoken by Non-native Children -- INTERSPEECH 2021 Shared Task SPAPL System](https://mlsanity.com/paper/2106.09963/) (2021)
- [Learning from human perception to improve automatic speaker verification in style-mismatched conditions](https://mlsanity.com/paper/2206.13684/) (2022)
- [Attention-based conditioning methods using variable frame rate for style-robust speaker verification](https://mlsanity.com/paper/2206.13680/) (2022)

## Abstract (arXiv)

In this paper, we propose a novel way of addressing text-dependent automatic speaker verification (TD-ASV) by using a shared-encoder with task-specific decoders. An autoregressive predictive coding (APC) encoder is pre-trained in an unsupervised manner using both out-of-domain (LibriSpeech, VoxCeleb) and in-domain (DeepMine) unlabeled datasets to learn generic, high-level feature representation that encapsulates speaker and phonetic content. Two task-specific decoders were trained using labeled datasets to classify speakers (SID) and phrases (PID). Speaker embeddings extracted from the SID decoder were scored using a PLDA. SID and PID systems were fused at the score level. There is a 51.9% relative improvement in minDCF for our system compared to the fully supervised x-vector baseline on the cross-lingual DeepMine dataset. However, the i-vector/HMM method outperformed the proposed APC encoder-decoder system. A fusion of the x-vector/PLDA baseline and the SID/PLDA scores prior to PID fusion further improved performance by 15% indicating complementarity of the proposed approach to the x-vector system. We show that the proposed approach can leverage from large, unlabeled, data-rich domains, and learn speech patterns independent of downstream tasks. Such a system can provide competitive performance in domain-mismatched scenarios where test data is from data-scarce domains.