Learning to Pronounce Chinese Without a Pronunciation Dictionary
Published 1 January 2020Open access
Christopher Chu, Scot Fang, Kevin Knight
Citations3
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
A program that learns to pronounce Chinese text in Mandarin, without a pronunciation dictionary, from non-parallel streams of Chinese characters and Chinese pinyin syllables, which significantly exceeds the 22% accuracy of prior work.
Abstract
We demonstrate a program that learns to pronounce Chinese text in Mandarin, without a pronunciation dictionary. From non-parallel streams of Chinese characters and Chinese pinyin syllables, it establishes a many-to-many mapping between characters and pronunciations. Using unsupervised methods, the program effectively deciphers writing into speech. Its token-level character-to-syllable accuracy is 89%, which significantly exceeds the 22% accuracy of prior work.
Keywords
Computer Science
Transactions of the Association for Computational LinguisticsEnriching Word Vectors with Subword Information
9,784 Citations2017Piotr Bojanowski, Édouard Grave +2 more
A new approach based on the skipgram model, where each word is represented as a bag of character n-grams, with words being represented as the sum of these representations, which achieves state-of-the-art performance on word similarity and analogy tasks.
IEEE Transactions on Information TheoryError bounds for convolutional codes and an asymptotically optimum decoding algorithm
6,705 Citations1967Andrew J. Viterbi
The upper bound is obtained for a specific probabilistic nonsequential decoding algorithm which is shown to be asymptotically optimum for rates above R_{0} and whose performance bears certain similarities to that of sequential decoding algorithms.
Speech CommunicationJoint-sequence models for grapheme-to-phoneme conversion
603 Citations2008M. Bisani, Hermann Ney
A novel estimation algorithm is presented that demonstrates high accuracy on a variety of databases and studies the impact of the maximum approximation in training and transcription, the interaction of model size parameters, n-best list generation, confidence measures, and phoneme-to-grapheme conversion.
Unsupervised Statistical Machine Translation
325 Citations2018Mikel Artetxe, Gorka Labaka +1 more
This paper proposes an alternative approach based on phrase-based Statistical Machine Translation (SMT) that significantly closes the gap with supervised systems, and profits from the modular architecture of SMT.
Behavior Research Methods, Instruments, & ComputersEmpirically derived probabilities for grapheme-to-phoneme correspondences in english
179 Citations1987Rita Sloan Berndt, James A. Reggia +1 more
Prior probabilities of graphemes and conditional probabilities for their pronunciation as specific phonemes are given based on a corpus of 17,310 English words to provide an index of the strength of particular grapheme-phoneme associations in English.
A Computational Approach to Deciphering Unknown Scripts
53 Citations1999Kevin Knight, Kenji Yamada
This work proposes and evaluates computational techniques for deciphering unknown scripts and considers which scripts are easy or hard to decipher, how much data is required, and whether the techniques are robust against language change over time.
Massively Multilingual Neural Grapheme-to-Phoneme Conversion
42 Citations2017Ben Peters, Jon Dehdari +1 more
A neural sequence-to-sequence approach to g2p which is trained on spelling–pronunciation pairs in hundreds of languages, allowing it to utilize the intrinsic similarities between different writing systems.
arXiv (Cornell University)When Does Unsupervised Machine Translation Work?
33 Citations2020Kelly Marchisio, Kevin Duh +1 more
An extensive empirical evaluation using dissimilar language pairs, dissimilar domains, and diverse datasets finds that unsupervised MT performance declines when source and target languages use different scripts, and very poor performance on authentic low-resource language pairs.
Be Appropriate and Funny: Automatic Entity Morph Encoding
20 Citations2014Boliang Zhang, Hongzhao Huang +7 more
A wide variety of novel approaches to automatically encode proper and interesting morphs, which can effectively pass decoding tests are developed.
Grapheme-to-phoneme conversion for Chinese text-to-speech
6 Citations2004Jun Xu, Guohong Fu +1 more
A complete G2P framework is presented, which includes a two-stage statistical word segmentation module, a hidden Markov model (HMM) based part-of-speech (POS) tagging module and a word-to-pinyin conversion module, which involves augmented word grapheme is augmented by its POS tag in an effort to resolve the pronunciation disambiguation in G1P.
ACM Transactions on Asian and Low-Resource Language Information ProcessingFrom Image to Translation
4 Citations2016Tongtao Zhang, Aritra Chowdhury +6 more
This paper developed an end-to-end system to read a scanned hand-written Nyushu article, segment it into characters, link them to standard characters, and then translate the article into Mandarin Chinese.