RNN Approaches to Text Normalization: A Challenge

by   Richard Sproat, et al.

This paper presents a challenge to the community: given a large corpus of written text aligned to its normalized spoken form, train an RNN to learn the correct normalization function. We present a data set of general text where the normalizations were generated using an existing text normalization component of a text-to-speech system. This data set will be released open-source in the near future. We also present our own experiments with this data set with a variety of different RNN architectures. While some of the architectures do in fact produce very good results when measured in terms of overall accuracy, the errors that are produced are problematic, since they would convey completely the wrong message if such a system were deployed in a speech application. On the other hand, we show that a simple FST-based filter can mitigate those errors, and achieve a level of accuracy not achievable by the RNN alone. Though our conclusions are largely negative on this point, we are actually not arguing that the text normalization problem is intractable using an pure RNN approach, merely that it is not going to be something that can be solved merely by having huge amounts of annotated text data and feeding that to a general RNN model. And when we open-source our data, we will be providing a novel data set for sequence-to-sequence modeling in the hopes that the the community can find better solutions. The data used in this work have been released and are available at: https://github.com/rwsproat/text-normalization-data


DeepNorm-A Deep Learning Approach to Text Normalization

This paper presents an simple yet sophisticated approach to the challeng...

Transformer-based Models of Text Normalization for Speech Applications

Text normalization, or the process of transforming text into a consisten...

Proteno: Text Normalization with Limited Data for Fast Deployment in Text to Speech Systems

Developing Text Normalization (TN) systems for Text-to-Speech (TTS) on n...

ESPnet-ST-v2: Multipurpose Spoken Language Translation Toolkit

ESPnet-ST-v2 is a revamp of the open-source ESPnet-ST toolkit necessitat...

Text Normalization using Memory Augmented Neural Networks

We propose a memory augmented neural network to perform text normalizati...

A big data approach towards sarcasm detection in Russian

We present a set of deterministic algorithms for Russian inflection and ...

AMR Normalization for Fairer Evaluation

Meaning Representation (AMR; Banarescu et al., 2013) encodes the meaning...

Please sign up or login with your details

Forgot password? Click here to reset