Disfluency Detection using a Noisy Channel Model and a Deep Neural Language Model

TL;DR

This paper introduces an LSTM Noisy Channel Model that combines a noisy channel approach with a deep neural language model to improve disfluency detection in spontaneous speech transcripts.

Contribution

It presents a novel integration of an LSTM language model with a noisy channel framework for enhanced disfluency detection accuracy.

Findings

Improved state-of-the-art disfluency detection performance.

Effective use of LSTM language models in reranking analyses.

Demonstrated the benefit of deep neural models in speech transcript processing.

Abstract

This paper presents a model for disfluency detection in spontaneous speech transcripts called LSTM Noisy Channel Model. The model uses a Noisy Channel Model (NCM) to generate n-best candidate disfluency analyses and a Long Short-Term Memory (LSTM) language model to score the underlying fluent sentences of each analysis. The LSTM language model scores, along with other features, are used in a MaxEnt reranker to identify the most plausible analysis. We show that using an LSTM language model in the reranking process of noisy channel disfluency model improves the state-of-the-art in disfluency detection.