DP-Parse: Finding Word Boundaries from Raw Speech with an Instance Lexicon
Open Access
- 19 September 2022
- journal article
- research article
- Published by MIT Press in Transactions of the Association for Computational Linguistics
- Vol. 10, 1051-1065
Abstract
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 (Goldwater et al., 2006, 2009) use a Dirichlet process to jointly segment sentences and build a lexicon of word types. We introduce DP-Parse, which uses similar principles but only relies on an instance lexicon of word tokens, avoiding the clustering errors that arise with a lexicon of word types. On the Zero Resource Speech Benchmark 2017, our model sets a new speech segmentation state-of-the-art in 5 languages. The algorithm monotonically improves with better input representations, achieving yet higher scores when fed with weakly supervised inputs. Despite lacking a type lexicon, DP-Parse can be pipelined to a language model and learn semantic and syntactic representations as assessed by a new spoken word embedding benchmark. 1Keywords
All Related Versions
This publication has 33 references indexed in Scilit:
- A segmental framework for fully-unsupervised large-vocabulary speech recognitionComputer Speech & Language, 2017
- Discriminative acoustic word embeddings: Tecurrent neural network-based approaches2016
- The Zero Resource Speech Challenge 2015: Proposed Approaches and ResultsProcedia Computer Science, 2016
- Librispeech: An ASR corpus based on public domain audio books2015
- Unsupervised lexical clustering of speech segments using fixed-dimensional acoustic embeddings2014
- Efficient spoken term discovery using randomized algorithms2011
- A Bayesian framework for word segmentation: Exploring the effects of contextCognition, 2009
- Unsupervised Pattern Discovery in SpeechIEEE Transactions on Audio, Speech, and Language Processing, 2007
- Contextual dependencies in unsupervised word segmentation2006
- On Estimation of a Probability Density Function and ModeThe Annals of Mathematical Statistics, 1962