Introducing Parselmouth: A Python interface to Praat

By Yannick Jadoul, Bill D. Thompson, Bart de Boer. J. Phonetics, 2018

602 citations recorded by the source corpus.

Abstract This paper introduces Parselmouth, an open-source Python library that facilitates access to core functionality of Praat in Python, in an efficient and programmer-friendly way. We introduce and motivate the package, and present simple usage examples. Specifically, we focus on applications in data visualisation, file manipulation, audio manipulation, statistical analysis, and integration of Parselmouth into a Python-based experimental design for automated, in-the-loop manipulation of acoustic data. Parselmouth is available at https://github.com/YannickJadoul/Parselmouth .

Subfields: Artificial Intelligence, Signal Processing

View Paper: https://www.semanticscholar.org/paper/095aa8f902cda5405757cb0017b94face4d0ebf9

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Signal Processing

Citations in the corpus

Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representations (2021, methodology): “[8] proposed to (3)We used Parselmouth for fs and pr [20].”
Paralinguistic Classification of Mask Wearing by Image Classifiers and Fusion (2020, methodology): “We have used the Parselmouth API [19] Python library for the Praat software [20], and also the Librosa toolkit [21] for Python.”
NANSY++: Unified Voice Synthesis with Neural Analysis and Synthesis (2022, methodology): “For the baseline models, we chose 4 popular F 0 estimators, that is, praat, rapt, pyin, and crepe (Boersma et al., 1993; Boersma & Van Heuven, 2001; Jadoul et al., 2018; Talkin & Kleijn, 1995; Mauch & Dixon, 2014; Kim et al., 2018).”
Context-Aware Prosody Correction for Text-Based Speech Editing (2021, positive): “Praat [22] implementation of TD-PSOLA via the Parselmouth [23] Python package.”
Alternate Endings: Improving Prosody for Incremental Neural TTS with Predicted Future Text Input (2021, methodology): “3) using Praat/Parselmouth [26, 27] and we compute the MAE in cents between the aligned f0 trajectories:”
The human auditory cortex concurrently tracks syllabic and phonemic timescales via acoustic spectral flux (2024, unknown): “The audio waveforms were linearly compressed or expanded using the PSOLA algorithm implemented in the Parselmouth Python package based on PRAAT ( 98 – 100 ), which modifies the duration of the audio stimulus without altering the original pitch contour.”