Evaluation of Automated Speech Recognition Systems for Conversational Speech: A Linguistic Perspective

TL;DR

This paper evaluates French speech recognition systems for conversational speech, focusing on linguistic challenges like homophone disambiguation, to understand their accuracy and error patterns in informal, real-world scenarios.

Contribution

It provides a linguistic analysis of ASR errors in French conversational speech, highlighting specific challenges and insights into system performance in natural language contexts.

Findings

Identification of common homophone disambiguation errors

Insights into transcription accuracy in conversational French

Analysis of error patterns in state-of-the-art ASR systems

Abstract

Automatic speech recognition (ASR) meets more informal and free-form input data as voice user interfaces and conversational agents such as the voice assistants such as Alexa, Google Home, etc., gain popularity. Conversational speech is both the most difficult and environmentally relevant sort of data for speech recognition. In this paper, we take a linguistic perspective, and take the French language as a case study toward disambiguation of the French homophones. Our contribution aims to provide more insight into human speech transcription accuracy in conditions to reproduce those of state-of-the-art ASR systems, although in a much focused situation. We investigate a case study involving the most common errors encountered in the automatic transcription of French language.