# Active and Semi-Supervised Learning in ASR: Benefits on the Acoustic and Language Models

arXiv: https://arxiv.org/abs/1903.02852 · HTML: https://mlsanity.com/paper/1903.02852/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Mar 2019.

## Built on by (most cited first, 16 of 16)

- [Exploring Active 3D Object Detection from a Generalization Perspective](https://mlsanity.com/paper/2301.09249/) (2023)
- [Best Practices in Active Learning for Semantic Segmentation](https://mlsanity.com/paper/2302.04075/) (2023)
- [Making Better Use of Unlabelled Data in Bayesian Active Learning](https://mlsanity.com/paper/2404.17249/) (2024)
- [Visual Transformer for Task-aware Active Learning](https://mlsanity.com/paper/2106.03801/) (2021)
- [Fast Entropy-Based Methods of Word-Level Confidence Estimation for End-To-End Automatic Speech Recognition](https://mlsanity.com/paper/2212.08703/) (2022)
- [Neural Active Learning on Heteroskedastic Distributions](https://mlsanity.com/paper/2211.00928/) (2022)
- [A Practitioner's Guide to Building ASR Models for Low-Resource Languages: A Case Study on Scottish Gaelic](https://mlsanity.com/paper/2506.04915/) (2025)
- [Investigation of Training Label Error Impact on RNN-T](https://mlsanity.com/paper/2112.00350/) (2021)
- [Error-driven Fixed-Budget ASR Personalization for Accented Speakers](https://mlsanity.com/paper/2103.03142/) (2021)
- [Analysis of Self-Supervised Learning and Dimensionality Reduction Methods in Clustering-Based Active Learning for Speech Emotion Recognition](https://mlsanity.com/paper/2206.10188/) (2022)
- [Automatic Speech Recognition System-Independent Word Error Rate Estimation](https://mlsanity.com/paper/2404.16743/) (2024)
- [Investigation on Data Adaptation Techniques for Neural Named Entity Recognition](https://mlsanity.com/paper/2110.05892/) (2021)
- [ST-CoNAL: Consistency-Based Acquisition Criterion Using Temporal Self-Ensemble for Active Learning](https://mlsanity.com/paper/2207.02182/) (2022)
- [Semi-supervised Active Regression](https://mlsanity.com/paper/2106.06676/) (2021)
- [Automated Detection of GDPR Disclosure Requirements in Privacy Policies using Deep Active Learning](https://mlsanity.com/paper/2111.04224/) (2021)
- [Combining X-Vectors and Bayesian Batch Active Learning: Two-Stage Active Learning Pipeline for Speech Recognition](https://mlsanity.com/paper/2406.02566/) (2024)

## Abstract (arXiv)

The goal of this paper is to simulate the benefits of jointly applying active learning (AL) and semi-supervised training (SST) in a new speech recognition application. Our data selection approach relies on confidence filtering, and its impact on both the acoustic and language models (AM and LM) is studied. While AL is known to be beneficial to AM training, we show that it also carries out substantial improvements to the LM when combined with SST. Sophisticated confidence models, on the other hand, did not prove to yield any data selection gain. Our results indicate that, while SST is crucial at the beginning of the labeling process, its gains degrade rapidly as AL is set in place. The final simulation reports that AL allows a transcription cost reduction of about 70% over random selection. Alternatively, for a fixed transcription budget, the proposed approach improves the word error rate by about 12.5% relative.