Přístupnostní navigace
E-application
Search Search Close
Publication detail
BASKAR, M. ROSENBERG, A. RAMABHADRAN, B. ZHANG, Y. MORENO, P.
Original Title
Ask2Mask: Guided Data Selection for Masked Speech Modeling
Type
journal article in Web of Science
Language
English
Original Abstract
Masked speech modeling (MSM) methods such as wav2vec2 or w2v-BERT learn representations over speech frames which are randomlymaskedwithin an utterance. While thesemethods improve performance of Automatic Speech Recognition (ASR) systems, they have one major limitation. They treat all unsupervised speech samples with equal weight, which hinders learning as not all samples have relevant information to learn meaningful representations. In this work, we address this limitation. We propose ask2mask (ATM), a novel approach to focus on specific samples during MSM pre-training. ATM employs an external ASR model or scorer to weight unsupervised input samples in two different ways: 1) A fine-grained data selection is performed by masking over the highly confident input frames as chosen by the scorer. This allows themodel to learnmeaningful representations. 2) ATM is further extended to focus at utterance-level by weighting the final MSM loss with the utterance-level confidence score. We conduct fine-tuning experiments on two well-benchmarked corpora: LibriSpeech (matching the pre-training data) and Commonvoice, TED-LIUM, AMI and CHiME-6 (not matching the pre-training data). The results substantiate the efficacy of ATM on significantly improving the recognition performance under mismatched conditions (up to 11.6% relative over published results and upto 4.46% relative over our internal baseline) while still yielding modest improvements under matched conditions.
Keywords
Guided Data Selection, Masked Speech Modeling
Authors
BASKAR, M.; ROSENBERG, A.; RAMABHADRAN, B.; ZHANG, Y.; MORENO, P.
Released
1. 10. 2022
ISBN
1932-4553
Periodical
IEEE J-STSP
Year of study
16
Number
6
State
United States of America
Pages from
1357
Pages to
1366
Pages count
10
URL
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9806175
BibTex
@article{BUT182529, author="Murali Karthick {Baskar} and Andrew {Rosenberg} and Bhuvana {Ramabhadran} and Yu {Zhang} and Pedro {Moreno}", title="Ask2Mask: Guided Data Selection for Masked Speech Modeling", journal="IEEE J-STSP", year="2022", volume="16", number="6", pages="1357--1366", doi="10.1109/JSTSP.2022.3186162", issn="1932-4553", url="https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9806175" }