1 |
Unsupervised Acoustic Unit Discovery by Leveraging a Language-Independent Subword Discriminative Feature Representation ...
|
|
|
|
Abstract:
This paper tackles automatically discovering phone-like acoustic units (AUD) from unlabeled speech data. Past studies usually proposed single-step approaches. We propose a two-stage approach: the first stage learns a subword-discriminative feature representation and the second stage applies clustering to the learned representation and obtains phone-like clusters as the discovered acoustic units. In the first stage, a recently proposed method in the task of unsupervised subword modeling is improved by replacing a monolingual out-of-domain (OOD) ASR system with a multilingual one to create a subword-discriminative representation that is more language-independent. In the second stage, segment-level k-means is adopted, and two methods to represent the variable-length speech segments as fixed-dimension feature vectors are compared. Experiments on a very low-resource Mboshi language corpus show that our approach outperforms state-of-the-art AUD in both normalized mutual information (NMI) and F-score. The ... : Accepted for publication in INTERSPEECH 2021 ...
|
|
Keyword:
Audio and Speech Processing eess.AS; Computation and Language cs.CL; FOS Computer and information sciences; FOS Electrical engineering, electronic engineering, information engineering; Sound cs.SD
|
|
URL: https://arxiv.org/abs/2104.00994 https://dx.doi.org/10.48550/arxiv.2104.00994
|
|
BASE
|
|
Hide details
|
|
2 |
How Phonotactics Affect Multilingual and Zero-shot ASR Performance ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
That Sounds Familiar: an Analysis of Phonetic Representations Transfer Across Languages ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|