View publication

This paper describes progress towards making a Neural Text-to-Speech (TTS) Frontend that works for many languages and can be easily extended to new languages. We take a Machine Translation (MT) inspired approach to constructing the frontend, and model both text normalization and pronunciation on a sentence level by building and using sequence-to-sequence (S2S) models. We experimented with training normalization and pronunciation as separate S2S models and with training a single S2S model combining both functions. For our language-independent approach to pronunciation we do not use a lexicon. Instead all pronunciations, including context-based pronunciations, are captured in the S2S model. We also present a language-independent chunking and splicing technique that allows us to process arbitrary-length sentences. Models for 18 languages were trained and evaluated. Many of the accuracy measurements are above 99%. We also evaluated the models in the context of end-to-end synthesis against our current production system.

Related readings and updates.

Class LM and Word Mapping for Contextual Biasing in End-to-End ASR

In recent years, all-neural, end-to-end (E2E) ASR systems gained rapid interest in the speech recognition community. They convert speech input to text units in a single trainable Neural Network model. In ASR, many utterances contain rich named entities. Such named entities may be user or location specific and they are not seen during training. A single model makes it inflexible to utilize dynamic contextual information during inference. In this…
See paper details


Apple sponsored the 45th International Conference on Acoustics, Speech, and Signal Processing (ICASSP) in May 2020. With a focus on signal processing and its applications, the conference took place virtually from May 4 - 8. Read Apple’s accepted papers below.

See event details