Improving Pronunciation Accuracy of Proper Names with Language Origin Classes
Explore this paper's citation graph
Summary
This thesis presents an attempt to improve automatic pronunciation of proper names by modeling the way humans do it, and tries to eliminate synthesis errors that humans would never make.
- Type
- article
- Published
- 2001-01-01
- Cited by
- 25
- References
- 52
- OpenAlex
- https://openalex.org/W23098887
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:9855683
Keywords
Pronunciation, Linguistics, Natural language processing, Computer science, Artificial intelligence
References
- Morphology and rhyming: two powerful alternatives to letter-to-sound rules for speech synthesis
- Statistical language learning
- Improvements on a trainable letter-to-sound converter
- Influence of morphology on phoneme identification in spoken croatian.
- Statistically trained orthographic to sound models for Thai
- A language-independent probabilistic model for automatic conversion between graphemic and phonemic transcription of words.
- Automation of the training procedures for neural networks performing multi-lingual grapheme to phoneme conversion.
- Computer Speech and Language
- N-gram-based text categorization
- Book Reviews: Foundations of Statistical Natural Language Processing
- Classification and regression trees
- Letter to sound rules for accented lexicon compression
- A Finite State and Data-Oriented Method for Grapheme to Phoneme Conversion
- Issues in building general letter to sound rules
- Stress Assignment in Letter to Sound Rules for Speech Synthesis
- The architecture of the Festival speech synthesis system
- A post-processing system to yield reduced word error rates: Recognizer Output Voting Error Reduction (ROVER)
- Modularity in Inductively-Learned Word Pronunciation Systems
- Automatic generation of multiple pronunciations based on neural networks
- Name pronunciation in German text-to-speech synthesis
Cited by
- Foreign accents in synthetic speech: development and evaluation
- Inference of string mappings for speech technology
- The predictability of name pronunciation errors in four South African languages
- Determining the Origin and Structure of Person Names
- Grapheme-to-phoneme conversion in the era of globalization
- Proper Name Pronunciations for Speech Technology Applications
- Inference of string mappings for language technology
- Comparative objective and subjective evaluation of three data-driven techniques for proper name pronunciation
- Knowledge acquisition for coreference resolution
- G2P Conversion of Proper Names Using Word Origin Information
- Evaluation and collection of proper name pronunciations online
- Using place name data to train language identification models
- Name Origin Recognition in Chinese Texts Based on Conditional Random Fields
- An Economic and Cultural Commentary
- The New C Standard An Economic and Cultural Commentary
- Subjective Evaluation of Techniques for Proper Name Pronunciation
- Pronunciation modeling for names of foreign origin
- Language identification for proper name pronunciation
- The effect of language identification accuracy on speech recognition accuracy of proper names
- The South African directory enquiries (SADE) name corpus
Related papers
- An Algorithm for High Accuracy Name Pronunciation by Parametric Speech Synthesizer
- Knowledge of language origin improves pronunciation accuracy of proper names
- A multistrategy approach to improving pronunciation by analogy
- Proper Name Pronunciations for Speech Technology Applications
- Evaluating the pronunciation component of text-to-speech systems for English: a performance comparison of different approaches
- Stress assignment in letter‐to‐sound rules for speech synthesis
- Issues in building general letter to sound rules
- The Basis of Correctness in the Pronunciation of Place-Names
- PRONOUNCE: a program for pronunciation by analogy
- A mathematical theory of communication