Auto-Landmark: Acoustic Landmark Dataset and Open-Source Toolkit for Landmark Extraction

TL;DR

This paper introduces Auto-Landmark, an annotated acoustic landmark dataset for TIMIT, along with an open-source toolkit and detection baselines, to advance research in speech analysis and recognition.

Contribution

It provides the first dataset with precise landmark timing annotations, an open-source extraction tool, and benchmark baselines for acoustic landmark detection.

Findings

Annotated TIMIT with acoustic landmarks

Developed an open-source landmark extraction toolkit

Established detection baselines for future research

Abstract

In the speech signal, acoustic landmarks identify times when the acoustic manifestations of the linguistically motivated distinctive features are most salient. Acoustic landmarks have been widely applied in various domains, including speech recognition, speech depression detection, clinical analysis of speech abnormalities, and the detection of disordered speech. However, there is currently no dataset available that provides precise timing information for landmarks, which has been proven to be crucial for downstream applications involving landmarks. In this paper, we selected the most useful acoustic landmarks based on previous research and annotated the TIMIT dataset with them, based on a combination of phoneme boundary information and manual inspection. Moreover, previous landmark extraction tools were not open source or benchmarked, so to address this, we developed an open source Python-based landmark extraction tool and established a series of landmark detection baselines. The first of their kinds, the dataset with landmark precise timing information, landmark extraction tool and baselines are designed to support a wide variety of future research.