Quantifying Language Variation Acoustically with Few Resources

05/05/2022
by   Martijn Bartelds, et al.
0

Deep acoustic models represent linguistic information based on massive amounts of data. Unfortunately, for regional languages and dialects such resources are mostly not available. However, deep acoustic models might have learned linguistic information that transfers to low-resource languages. In this study, we evaluate whether this is the case through the task of distinguishing low-resource (Dutch) regional varieties. By extracting embeddings from the hidden layers of various wav2vec 2.0 models (including new models which are pre-trained and/or fine-tuned on Dutch) and using dynamic time warping, we compute pairwise pronunciation differences averaged over 10 words for over 100 individual dialects from four (regional) languages. We then cluster the resulting difference matrix in four groups and compare these to a gold standard, and a partitioning on the basis of comparing phonetic transcriptions. Our results show that acoustic models outperform the (traditional) transcription-based approach without requiring phonetic transcriptions, with the best performance achieved by the multilingual XLSR-53 model fine-tuned on Dutch. On the basis of only six seconds of speech, the resulting clustering closely matches the gold standard.

READ FULL TEXT
research
06/24/2020

Multilingual Jointly Trained Acoustic and Written Word Embeddings

Acoustic word embeddings (AWEs) are vector representations of spoken wor...
research
10/13/2021

Morphosyntactic Tagging with Pre-trained Language Models for Arabic and its Dialects

We present state-of-the-art results on morphosyntactic tagging across di...
research
12/12/2022

Implementing Deep Learning-Based Approaches for Article Summarization in Indian Languages

The research on text summarization for low-resource Indian languages has...
research
08/02/2019

Multilingual Speech Recognition with Corpus Relatedness Sampling

Multilingual acoustic models have been successfully applied to low-resou...
research
07/14/2022

Multilinguals at SemEval-2022 Task 11: Complex NER in Semantically Ambiguous Settings for Low Resource Languages

We leverage pre-trained language models to solve the task of complex NER...
research
04/10/2019

A Grounded Unsupervised Universal Part-of-Speech Tagger for Low-Resource Languages

Unsupervised part of speech (POS) tagging is often framed as a clusterin...
research
03/18/2022

CaMEL: Case Marker Extraction without Labels

We introduce CaMEL (Case Marker Extraction without Labels), a novel and ...

Please sign up or login with your details

Forgot password? Click here to reset