Related Experiment Video
Updated: Jun 24, 2026
09:09
Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody
Published on: September 27, 2024
Automatic syllabification in English: a comparison of different algorithms
Yannick Marchand1, Connie R Adsett, Robert I Damper
1Institute for Biodiagnostics (Atlantic), National Research Council Canada.
Language and Speech
|April 2, 2009
Summary
Data-driven methods, particularly syllabification by analogy (SbA), significantly outperform rule-based systems for automatic word syllabification. Syllabification is easier using pronunciation than spelling data.
Area of Science:
- Computational Linguistics
- Natural Language Processing
- Phonology
Background:
- Automatic syllabification is complex due to the ambiguous definition of a syllable.
- Existing approaches include rule-based and data-driven methods, but no standard algorithm is widely accepted.
- Evaluating syllabification accuracy is challenging due to the lack of a definitive gold standard.
Purpose of the Study:
- To compare the performance of rule-based and data-driven automatic syllabification algorithms.
- To investigate the impact of using consensus data from multiple lexicons for training and evaluation.
- To determine the most effective approach for automatic syllabification.
Main Methods:
- Compared two rule-based approaches (Hammond's and Fisher's implementation of Kahn's) and three data-driven techniques (look-up, exemplar-based generalization, and syllabification by analogy - SbA).
- Utilized three databases derived from two independent lexicons, including a consensus lexicon of 13,594 words.
- Evaluated performance based on word and juncture accuracies in both pronunciation and spelling domains.
Main Results:
- Data-driven techniques significantly outperformed rule-based systems in accuracy.
- Syllabification based on pronunciation data yielded better results than spelling data.
- Syllabification by Analogy (SbA) consistently achieved the best performance across all databases.
Conclusions:
- Data-driven methods, especially SbA, are superior to rule-based systems for automatic syllabification.
- Pronunciation-based syllabification is more tractable than spelling-based syllabification.
- Consensus data from multiple lexicons improves the robustness of syllabification evaluation and training.
Related Concept Videos
02:52Predicting Products: Substitution vs. Elimination
When a nucleophile and an alkyl halide react, nucleophilic substitution and β-elimination reactions compete to generate products.
The following factors can influence the mechanisms competing against each other:
The following factors can influence the mechanisms competing against each other:
01:27Air-entraining Agents
Air-entraining agents improve the durability and workability of concrete in climates with frequent freezing and thawing. These agents prevent cracks by introducing small air bubbles into the mix, creating spaces accommodating water expansion when temperatures drop. The air-entraining agents lower the surface tension of water, forming stable, small air bubbles. This method is more effective than having accidental large voids, as the intentional, smaller, and evenly distributed air voids improve...
01:23Mnemonic Devices
Mnemonic devices are cognitive tools that facilitate memory retention by linking new information to familiar patterns or organizational strategies. These techniques are beneficial for remembering complex or lengthy sets of information by simplifying and structuring them in easily retrievable ways.
Acronyms
Acronyms are created by using the initial letters of a series of words to form a new word or phrase. This approach condenses complex information into a single, memorable entity. For example,...
Acronyms
Acronyms are created by using the initial letters of a series of words to form a new word or phrase. This approach condenses complex information into a single, memorable entity. For example,...
01:12Trial and Error and Algorithm
A problem-solving strategy is a plan of action used to find a solution. Different strategies have distinct action plans. Trial and error involves trying different solutions until one works. For instance, to fix a broken printer, you might check ink levels, ensure the paper tray isn't jammed, and verify the printer's connection to your laptop. This method can be time-consuming but is commonly used. Thomas Edison, for example, used trial and error to find a suitable filament for the light bulb,...