Revisiting speech segmentation and lexicon learning with better features
We revisit a self-supervised method that segments unlabelled speech into word-like segments. We start from the two-stage duration-penalised dynamic programming method that performs zero-resource segmentation without learning an explicit lexicon. In the first acoustic unit discovery stage, we replace contrastive predictive coding features with HuBERT. After word segmentation in the second stage, we get an acoustic word embedding for each segment by averaging HuBERT features. These embeddings are clustered using K-means to get a lexicon. The result is good full-coverage segmentation with a lexicon that achieves state-of-the-art performance on the ZeroSpeech benchmarks.
Code (0)
등록된 구현이 없습니다.
Tasks
Acoustic Unit DiscoverySegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
DP-Parse: Finding Word Boundaries from Raw Speech with an Instance Lexicon
Finding word boundaries in continuous speech is challenging as there is little or no equivalent of a 'space' delimiter between words. Popular Bayesian non-parametric models for text segmentation use a Dirichlet process t…
Language ModelingLanguage ModellingSegmentationText SegmentationUnsupervised Word Discovery: Boundary Detection with Clustering vs. Dynamic Programming
We look at the long-standing problem of segmenting unlabeled speech into word-like segments and clustering these into a lexicon. Several previous methods use a scoring model coupled with dynamic programming to find an op…
Boundary DetectionClusteringDeveloping Resources for Automated Speech Processing of Quebec French
The analysis of the structure of speech nearly always rests on the alignment of the speech recording with a phonetic transcription. Nowadays several tools can perform this speech segmentation automatically. However, none…
SegmentationText NormalizationRevisiting Lexicon Evaluation in Unsupervised Word Discovery
Building a lexicon from discovered word-like units is a central goal in zero-resource speech processing. But do our evaluations provide a trustworthy indication of lexicon quality? A common metric, normalized edit distan…
Lexicon Enhanced Chinese Sequence Labeling Using BERT Adapter
Lexicon information and pre-trained models, such as BERT, have been combined to explore Chinese sequence labelling tasks due to their respective strengths. However, existing methods solely fuse lexicon features via a sha…
named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)Part-Of-Speech Tagging