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

By Thomas Drugman, Janne Pylkkönen, Reinhard Kneser. 2016

66 citations recorded by the source corpus.

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.

Subfields: Optimization & Training, Speech & Audio

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Optimization & Training

In Speech & Audio

Citations in the corpus

You Do Not Need More Data: Improving End-To-End Speech Recognition by Text-To-Speech Data Augmentation (2020, background): “There are other approaches, such as transfer and active learning [6], to tackle low-resource challenges, but they are beyond the scope of this paper.”
An Overview of Deep Semi-Supervised Learning (2020, background): “[41] demonstrates a signiﬁcant error reduction with limited labeled data for speech understanding, [129] proposes an active semi-supervised learning system for pedestrian detection, [192] combines AL and SSL using Gaussian ﬁelds applied to synthetic datasets, and [51] exploits both labeled and…”
Evaluation of Lifelong Learning Systems (2020, background): “…to measure the quality of this adaptation process by considering the dependence between cost of interactions and performance of the system (Krogh and Vedelsby, 1995; Siddhant and Lipton, 2018; Drugman et al., 2019; Beluch et al., 2018; P´erez-Dattari et al., 2018; Celemin and Ruiz-del Solar, 2019).”