Non-native English lexicon creation for bilingual speech synthesis

TL;DR

This paper introduces a method to create non-native English lexicons for bilingual TTS systems by mapping native lexicons using letter-to-phoneme alignment, improving speech intelligibility for non-native speakers.

Contribution

It proposes a novel rule-based approach to generate non-native English lexicons from native lexicons, enhancing bilingual TTS performance.

Findings

6% preference improvement in subjective evaluation

Effective mapping of native to non-native phoneme sequences

Enhanced speech intelligibility for non-native English speakers

Abstract

Bilingual English speakers speak English as one of their languages. Their English is of a non-native kind, and their conversations are of a code-mixed fashion. The intelligibility of a bilingual text-to-speech (TTS) system for such non-native English speakers depends on a lexicon that captures the phoneme sequence used by non-native speakers. However, due to the lack of non-native English lexicon, existing bilingual TTS systems employ native English lexicons that are widely available, in addition to their native language lexicon. Due to the inconsistency between the non-native English pronunciation in the audio and native English lexicon in the text, the intelligibility of synthesized speech in such TTS systems is significantly reduced. This paper is motivated by the knowledge that the native language of the speaker highly influences non-native English pronunciation. We propose a generic approach to obtain rules based on letter to phoneme alignment to map native English lexicon to their non-native version. The effectiveness of such mapping is studied by comparing bilingual (Indian English and Hindi) TTS systems trained with and without the proposed rules. The subjective evaluation shows that the bilingual TTS system trained with the proposed non-native English lexicon rules obtains a 6% absolute improvement in preference.