Prosodylab-aligner: A tool for forced alignment of laboratory speech

Abstract

The Penn Forced Aligner automates the alignment process using the Hidden Markov Model Toolkit (HTK). The core of Prosodylab-Aligner is align. py, a script which performs acoustic model training and alignment. This script automates calls to HTK and SoX, an open-source command-line tool which is capable of resampling audio. The included README file provides instructions for installing HTK and SoX on Linux and Mac OS X, and can also be run on Windows. During training, the model is initialized with flat-start monophones, which are then submitted to a single round of model estimation. Then, a tied-state 'small pause' model is inserted and used in a second round of estimation. The data is then aligned once to choose the most likely pronunciation of all homonyms. Web audio is downloaded from Ramp, a company which indexes radio and television programming, including NBC, PBS, Fox and CBS Radio, and processed using standard UNIX tools.