SPPAS - the automatic annotation and analysis of speech (version 2.0) Brigitte Bigi To cite this version: Brigitte Bigi. SPPAS - the automatic annotation and analysis of speech (version 2.0). 2019. hal- 01414600v3 HAL Id: hal-01414600 https://hal.archives-ouvertes.fr/hal-01414600v3 Preprint submitted on 8 Jan 2019 (v3), last revised 9 Dec 2020 (v5) HAL is a multi-disciplinary open access L’archive ouverte pluridisciplinaire HAL, est archive for the deposit and dissemination of sci- destinée au dépôt et à la diffusion de documents entific research documents, whether they are pub- scientifiques de niveau recherche, publiés ou non, lished or not. The documents may come from émanant des établissements d’enseignement et de teaching and research institutions in France or recherche français ou étrangers, des laboratoires abroad, or from public or private research centers. publics ou privés. Copyright SPPASSPPASSPPASSPPAS thethethethe automaticautomaticautomaticautomatic annotationannotationannotationannotation andandandand analysisanalysisanalysisanalysis ofofofof speechspeechspeechspeech VersionVersion 2.0 2.0 BrigitteBrigitte BigiBigi [email protected]@sppas.org Copyright © 2011-2019 – Brigitte Bigi – Laboratoire Parole et Langage – France Permission is granted to copy, distribute and/or modify this document under the terms of the GNU Free Documentation License, Version 1.3 or any later version published by the Free Software Foundation; with no Invariant Sections, no Front-Cover Texts, and no Back-Cover Texts. A copy of the license is included in the section entitled "GNU Free Documentation License". Any and all constructive comments are welcome. version 2.0 ii Contents 1 Introduction 1 1.1 What is SPPAS? ...................................... 1 1.1.1 Overview ...................................... 1 1.1.2 User engagement .................................. 2 1.1.3 Need help ..................................... 2 1.1.4 About the author .................................. 2 1.1.5 Licenses ...................................... 3 1.1.6 Supports ...................................... 3 1.2 Getting and installing .................................... 4 1.2.1 Websites ...................................... 4 1.2.2 External programs ................................. 4 1.2.3 Download and install SPPAS ............................ 5 1.2.4 The package .................................... 5 1.2.5 Update ....................................... 6 1.3 Features .......................................... 6 1.3.1 How to use SPPAS? ................................ 6 1.3.2 What SPPAS can do? ............................... 7 1.4 Main and important recommendations ........................... 7 1.4.1 About files ..................................... 7 1.4.2 About automatic annotations ............................ 9 1.4.3 About linguistic resources ............................. 9 1.5 Interoperability and compatibility: convert files ....................... 9 1.6 About this documentation ................................. 11 iii Contents 2 User interfaces 13 2.1 The graphical user interface ................................ 13 2.1.1 Launch SPPAS ................................... 13 2.1.2 The tips ...................................... 14 2.1.3 The menu ..................................... 14 2.1.4 The file explorer .................................. 15 2.1.5 Settings ...................................... 18 2.1.6 About ....................................... 18 2.1.7 Help ........................................ 18 2.1.8 Plugins ....................................... 19 2.2 The command-line user interface .............................. 19 2.2.1 Usage ....................................... 20 2.2.2 Arguments for input/output ............................ 20 3 Automatic Annotations 23 3.1 Introduction ........................................ 23 3.1.1 About this chapter ................................. 23 3.1.2 Annotations methodology ............................. 23 3.1.3 File formats and tier names ............................. 25 3.1.4 Recorded speech .................................. 25 3.1.5 Automatic Annotations with GUI ......................... 25 3.1.6 Automatic Annotations with CLI .......................... 26 3.1.7 The procedure outcome report ........................... 28 3.2 New language support ................................... 32 3.3 Orthographic Transcription ................................. 32 3.4 Search for Inter-Pausal Units (IPUs) ............................ 33 3.4.1 Overview ...................................... 33 3.4.2 How does it work ................................. 33 3.4.3 Perform “Search for IPUs” with the GUI ...................... 34 3.4.4 Perform “Search for IPUs” with the CLI ...................... 35 3.5 Fill in Inter-Pausal Units (IPUs) .............................. 36 3.5.1 Overview ...................................... 36 3.5.2 How does it work ................................. 37 3.5.3 Perform “Fill in IPUs” with the GUI ........................ 37 3.5.4 Perform “Fill in IPUs” with the CLI ........................ 37 version 2.0 iv Contents 3.6 Text normalization ..................................... 39 3.6.1 Overview ...................................... 39 3.6.2 Adapt Text normalization ............................. 39 3.6.3 Support of a new language ............................. 39 3.6.4 Perform Text Normalization with the GUI ..................... 40 3.6.5 Perform Text Normalization with the CLI ..................... 40 3.7 Phonetization ........................................ 42 3.7.1 Overview ...................................... 42 3.7.2 Adapt Phonetization ................................ 43 3.7.3 Support of a new language ............................. 43 3.7.4 Perform Phonetization with the GUI ........................ 43 3.7.5 Perform Phonetization with the CLI ........................ 44 3.8 Alignment ......................................... 46 3.8.1 Overview ...................................... 46 3.8.2 Adapt Alignment .................................. 46 3.8.3 Support of a new language ............................. 46 3.8.4 Perform Alignment with the GUI ......................... 47 3.8.5 Perform Alignment with the CLI .......................... 48 3.9 Syllabification ....................................... 49 3.9.1 Overview ...................................... 49 3.9.2 Adapt Syllabification ................................ 50 3.9.3 Support of a new language ............................. 50 3.9.4 Perform Syllabification with the GUI ........................ 51 3.9.5 Perform Syllabification with the CLI ........................ 51 3.10 TGA - Time Groups Analyzer ............................... 52 3.10.1 Overview ...................................... 52 3.10.2 Result of TGA into SPPAS ............................. 53 3.10.3 Perform TAG with the GUI ............................ 54 3.10.4 Perform TGA with the CLI ............................ 54 3.11 Self-Repetitions ...................................... 55 3.11.1 Overview ...................................... 55 3.11.2 Adapt to a new language .............................. 56 3.11.3 Perform Self-Repetitions with the GUI ....................... 56 3.11.4 Perform SelfRepetitions with the CLI ....................... 56 3.12 Other-Repetitions ..................................... 57 version 2.0 v Contents 3.12.1 Overview ...................................... 57 3.12.2 Adapt to a language and support of a new one ................... 57 3.12.3 Perform Other-Repetitions with the CLI ...................... 57 3.13 Momel and INTSINT ................................... 58 3.13.1 Momel (modelling melody) ............................ 58 3.13.2 Encoding of F0 target points using the “INTSINT” system ............. 59 3.13.3 Perform Momel and INTSINT with the GUI .................... 60 3.13.4 Perform Momel with the CLI ........................... 60 3.13.5 Perform INTSINT with the CLI .......................... 62 4 Resources for Automatic Annotations 65 4.1 Overview .......................................... 65 4.2 French ........................................... 66 4.2.1 List of phonemes .................................. 66 4.2.2 Pronunciation dictionary .............................. 67 4.2.3 Acoustic Model .................................. 68 4.2.4 Syllabification configuration file .......................... 68 4.3 Italian ........................................... 68 4.3.1 List of phonemes .................................. 68 4.3.2 Pronunciation dictionary .............................. 70 4.3.3 Acoustic Model .................................. 70 4.3.4 Syllabification configuration file .......................... 70 4.4 Spanish ........................................... 70 4.4.1 List of phonemes .................................. 70 4.4.2 Pronunciation Dictionary .............................. 72 4.4.3 Acoustic Model .................................. 72 4.5 Catalan ........................................... 72 4.5.1 List of phonemes .................................. 72 4.5.2 Pronunciation dictionary .............................. 74 4.5.3 Acoustic Model .................................. 74 4.6 English ........................................... 75 4.6.1 List of phonemes .................................. 75 4.6.2 Pronunciation dictionary .............................. 77 4.6.3 Acoustic Model .................................. 77 4.7 Polish ........................................... 77 version 2.0 vi Contents 4.7.1 List of phonemes