---
title: "Is word-to-phone mapping better than phone-phone mapping for"
description: "The authors use only the native Telugu phone set and compare two options. 8 references."
authors: ["Naresh Kumar Elluru", "Anandaswarup Vadapalli", "Raghavendra Elluru", "Hema Murthy", "Kishore Prahallad"]
year: 2013
venue: "Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)"
source: "https://aclanthology.org/P13-2035/"
licence: "CC BY-NC-SA 3.0 (ACL Anthology, before 2016)"
licence_url: "https://creativecommons.org/licenses/by-nc-sa/3.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/elluru-2013-is-word-phone-mapping-better/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/elluru-2013-is-word-phone-mapping-better/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2013](https://md.research.elamur.ai/free/en/papers/2013/page/3/) / Is word-to-phone mapping better than phone-phone mapping for handling English words?

# Is word-to-phone mapping better than phone-phone mapping for handling English words?

**Authors:** Naresh Kumar Elluru, Anandaswarup Vadapalli, Raghavendra Elluru, Hema Murthy and Kishore Prahallad · **Year:** 2013 · **Venue:** [Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2013](https://md.research.elamur.ai/free/en/venues/acl/2013/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY-NC-SA 3.0 (ACL Anthology, before 2016)](https://creativecommons.org/licenses/by-nc-sa/3.0/)

**Links:** [Publisher's page](https://aclanthology.org/P13-2035/) · [PDF](https://aclanthology.org/P13-2035.pdf) · [OpenAlex](https://openalex.org/W2134583295)

**Citations:** 5 citations (OpenAlex, 2026-10-14)

## Summary
The paper looks at how a Telugu text-to-speech system should pronounce English words that appear inside Telugu text. Such code mixing is common in Indian web writing; in one Telugu blog, English made up roughly 20–30% of the text. The authors use only the native Telugu phone set and compare two options. The first swaps each US English phone for the closest Telugu phone (phone-phone). The second maps the whole English spelling directly to a Telugu phone sequence (word-phone). In a small manual pilot, native listeners clearly preferred word-phone mapping. The authors then learned these mappings automatically. They aligned letters to phones with an EM-style epsilon scattering procedure and trained CART letter-to-sound models. Word-level accuracy for English-word-to-Telugu-phone mapping was higher than for the CMU dictionary English-phone mapping, likely because Telugu speakers tend to pronounce words as they are spelled. Once the learned rules were added to an HMM-based Telugu TTS system, listeners rated it almost the same as hand-written mappings. Bilingual TTS can therefore handle foreign words without a combined phoneset or a multilingual speaker.

## Key points
- **Pilot study:** 10 bilingual utterances were rated by 5 native listeners. Word-phone mapping scored MOS 3.48 and phone-phone mapping 2.66. In ABX, listeners chose word-phone 32/50 times, phone-phone 4/50, and no preference 14/50.
- **Alignment and models:** letters were aligned to phones with automatic epsilon scattering (Pagel et al., 1998), which places "empty" phones for silent letters. Two CART models were trained: EW-EP, based on the CMU pronunciation dictionary, and EW-TP, mapping English words to Telugu phones.
- **Test setup:** the held-out set was every ninth lexicon word, plus a separate test set from another domain. Accuracy was measured per letter and per word, and training sizes ranged from 1,000 to 100,000 words.
- **Accuracy results:** EW-TP trained on 10,000 words reached 71.67% word accuracy on held-out data and 70.9% on the other domain, with about 95–97% letter accuracy. EW-EP stayed near 55–56% word accuracy even with 100,000 training words.
- **Final listening test:** 25 sentences were judged by 10 listeners. The manual system (TM) scored MOS 3.48 and the automatic system (TA) 3.43. In ABX, listeners chose TM 51/250 times, TA 38/250, and no preference 161/250.

## Interesting ideas
- An EM loop alternates between estimating letter–phone match probabilities and re-aligning each word, inserting empty slots where a letter has no phone; this turns uneven sequence pairs into fixed-length training examples for a simple classifier.
- Before automating, the authors hand-built a few outputs for both competing designs and had listeners compare them, settling the design choice cheaply before any engineering.
- Accuracy is reported against training-set size and on both a held-out split and an out-of-domain set, which shows whether gains come from data volume or fail to transfer.
- The target representation is chosen to fit the listener's inventory (native phones) rather than to faithfully copy the source language's units, and listeners preferred this.
- The ABX test includes an explicit "no preference" option, so a near-tie between the manual and automatic systems shows up as evidence of parity rather than forced noise.

## For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

- **I1** (tokens): the same alignment could pair word forms with lemmas or morphological analyses, so that inflection or lemmatization edit rules can be learned per character and remain explainable.
- **I2** (learn): when choosing between two representations (e.g., two frame encodings), hand-annotate a handful of sentences both ways and run a quick preference check before building either pipeline.
- **I3** (learn): parser and tagger evaluations could routinely include learning curves and an out-of-domain test set, such as fables versus school texts, to detect overfitting to silver data.
- **I4** (back): generation and translation through the meta-world could render concepts in the reader's own vocabulary and constructions, instead of mirroring the source structure unit by unit.
- **I5** (learn): when LLM teacher tiers or human judges compare two parser or repair-rule versions, allowing a "no difference" vote would separate real improvements from cosmetic changes.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [International Institute of Information Technology, Hyderabad](https://md.research.elamur.ai/free/en/universities/international-institute-of-information-technology-hyderabad/) — University, Hyderabad, India · 38 works · 1,821 citations
- [Indian Institute of Technology Madras](https://md.research.elamur.ai/free/en/universities/indian-institute-of-technology-madras/) — University, Chennai, India · 16 works · 2,499 citations

📚 Shelves (7): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [💭 Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/) · 1,552 works · [💭 Experimental and Cognitive Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/experimental-and-cognitive-psychology/) · 870 works · [🔊 Signal Processing](https://md.research.elamur.ai/free/en/shelves/computer-science/signal-processing/) · 452 works

🧭 Topics (1): [English](https://md.research.elamur.ai/free/en/topics/english/) · 2,263 works

## Cite

Cite as: Naresh Kumar Elluru, Anandaswarup Vadapalli, Raghavendra Elluru, Hema Murthy and Kishore Prahallad. 2013. Is word-to-phone mapping better than phone-phone mapping for handling English words?. Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{elluru2013is,
  title = {{Is word-to-phone mapping better than phone-phone mapping for handling English words?}},
  author = {Naresh Kumar Elluru, Anandaswarup Vadapalli, Raghavendra Elluru, Hema Murthy and Kishore Prahallad},
  booktitle = {Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)},
  year = {2013},
  url = {https://aclanthology.org/P13-2035/}
}
```

- [← previous Dudley North visits North London: Learning When to Transliterate to Arabic](https://md.research.elamur.ai/free/en/papers/azab-2013-dudley-north-visits-north-london/)
- [next → Sub-lexical Dialogue Act Classification in a Spoken Dialogue System Support for the Elderly with Cognitive Disabilities](https://md.research.elamur.ai/free/en/papers/sadohara-2013-sub-lexical-dialogue-act-classification/)
- [↑ back to papers of 2013](https://md.research.elamur.ai/free/en/papers/2013/page/3/)

## References

8 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. A.W. Black and K. Lenzo. 2004. Multilingual Text to Speech synthesis. In Proceedings of ICASSP, Montreal, Canada. [find](https://scholar.google.com/scholar?q=A%2EW%2E+Black+and+K%2E+Lenzo%2E+2004%2E+Multilingual+Text+to+Speech+synthesis%2E+In+Proceedings+of+ICASSP%2C+Montreal%2C+Canada%2E)
2. N. Campbell. 1998. Foreign language speech synthesis. In Proceedings ESCA/COCOSDA workshop on speech synthesis, Jenolan Caves, Australia. [find](https://scholar.google.com/scholar?q=N%2E+Campbell%2E+1998%2E+Foreign+language+speech+synthesis%2E+In+Proceedings+ESCA%2FCOCOSDA+workshop+on+speech+synthesis%2C+Jenolan+Caves%2C+Australia%2E)
3. N. Campbell. 2001. Talking foreign. Concatenative speech synthesis and the language barrier. In Proceedings Eurospeech, pages 337–340, Aalborg, Denmark. [find](https://scholar.google.com/scholar?q=N%2E+Campbell%2E+2001%2E+Talking+foreign%2E+Concatenative+speech+synthesis+and+the+language+barrier%2E+In+Proceedings+Eurospeech%2C+pages+337%E2%80%93340%2C+Aalborg%2C+Denmark%2E)
4. J. Latorre, K. Iwano, and S. Furui. 2006. New approach to polygot speech generation by means of an HMM based speaker adaptable synthesizer. Speech Communication, 48:1227–1242. [find](https://scholar.google.com/scholar?q=J%2E+Latorre%2C+K%2E+Iwano%2C+and+S%2E+Furui%2E+2006%2E+New+approach+to+polygot+speech+generation+by+means+of+an+HMM+based+speaker+adaptable+synthesizer%2E+Speech+Communication%2C+48%3A1227%E2%80%931242%2E)
5. V. Pagel, K. Lenzo, and A.W. Black. 1998. Letter to sound rules for accented lexicon compression. In Proceedings of ICSLP 98, volume 5, Sydney, Australia. [find](https://scholar.google.com/scholar?q=V%2E+Pagel%2C+K%2E+Lenzo%2C+and+A%2EW%2E+Black%2E+1998%2E+Letter+to+sound+rules+for+accented+lexicon+compression%2E+In+Proceedings+of+ICSLP+98%2C+volume+5%2C+Sydney%2C+Australia%2E)
6. Suzzane Romaine and Braj Kachru. 1992. The Oxford Companion to the English Language. Oxford University Press. [find](https://scholar.google.com/scholar?q=Suzzane+Romaine+and+Braj+Kachru%2E+1992%2E+The+Oxford+Companion+to+the+English+Language%2E+Oxford+University+Press%2E)
7. C. Traber, K. Huber, K. Nedir, B. Pfister, E. Keller, and B. Zellner. 1999. From multilingual to polyglot speech synthesis. In Proceedings of Eurospeech 99, pages 835–838. [find](https://scholar.google.com/scholar?q=C%2E+Traber%2C+K%2E+Huber%2C+K%2E+Nedir%2C+B%2E+Pfister%2C+E%2E+Keller%2C+and+B%2E+Zellner%2E+1999%2E+From+multilingual+to+polyglot+speech+synthesis%2E+In+Proceedings+of+Eurospeech+99%2C+pages+835%E2%80%93838%2E)
8. H. Zen, T. Nose, J. Yamagishi, S. Sako, T. Masuko, A.W. Black, and K. Tokuda. 2007. The HMM-based speech synthesis system version 2.0. In Proceedings of ISCA SSW6, Bonn, Germany. [find](https://scholar.google.com/scholar?q=H%2E+Zen%2C+T%2E+Nose%2C+J%2E+Yamagishi%2C+S%2E+Sako%2C+T%2E+Masuko%2C+A%2EW%2E+Black%2C+and+K%2E+Tokuda%2E+2007%2E+The+HMM%2Dbased+speech+synthesis+system+version+2%2E0%2E+In+Proceedings+of+ISCA+SSW6%2C+Bonn%2C+Germany%2E)

*Updated 1 November 2026*