Scalable language model adaptation for spoken dialogue systems

TL;DR

This paper presents a scalable method for adapting language models in spoken dialogue systems to new application intents by estimating n-gram counts from grammars and using constrained optimization, improving performance without degrading existing capabilities.

Contribution

It introduces a novel approach combining grammar-based n-gram estimation and constrained optimization for effective language model adaptation.

Findings

Improved word error rate by up to 15% on new application intents

Effective adaptation without additional data for new applications

Maintained performance on existing applications during adaptation

Abstract

Language models (LM) for interactive speech recognition systems are trained on large amounts of data and the model parameters are optimized on past user data. New application intents and interaction types are released for these systems over time, imposing challenges to adapt the LMs since the existing training data is no longer sufficient to model the future user interactions. It is unclear how to adapt LMs to new application intents without degrading the performance on existing applications. In this paper, we propose a solution to (a) estimate n-gram counts directly from the hand-written grammar for training LMs and (b) use constrained optimization to optimize the system parameters for future use cases, while not degrading the performance on past usage. We evaluated our approach on new applications intents for a personal assistant system and find that the adaptation improves the word error rate by up to 15% on new applications even when there is no adaptation data available for an application.