This section features software tools commonly used in interdisciplinary speech and voice research. They can be downloaded either directly from this website or from the developers’ websites, accessible through the links provided below.

Praat

Developed and maintained by Paul Boersma and David Weenink, Phonetic Sciences, University of Amsterdam.

Acoustic speech analysis software featuring a wide range of functions, including speech analysis and synthesis, labelling and segmentation, speech manipulation, machine learning algorithms, statistical analysis, data visualization, scripting, and cross-platform compatibility.

Free download link: https://www.fon.hum.uva.nl/praat/

Whisper

Deleveloped and maintained by OpenAI.

Open-acces automatic speech recognition (ASR) system. It can be accessed through the OpenAI website: https://replicate.com/openai/whisper

Users having Python installed on their computer can also install and run Whisper locally. The official GitHub repository provides detailed documentation on installation, available commands, and usage examples: https://github.com/openai/whisper

Sounds of Speech

Developed and maintanied by the University of Iowa.

The Sounds of Speech explains in detail the articulation of the sounds of Spanish, American English and German. This resource includes animations, videos and explanations of all the consonants and vowels of these languages.

https://soundsofspeech.uiowa.edu/

BioMet®Ling

Developed and maintained by NeuSpeLab® and Glottex® VAS SL

BioMetroLing is an AI-driven advanced neurolinguistic system architecture that performs non-invasive neuromotor and laryngeal clinical and forensic assessment by processing acoustic speech signals through Vocal Tract and Biomechanical Source Inversion, mapping extracted neuromechanical and physiological feature distributions directly connected to central Phono-Encephalography (phEG) cortical EEG bands (delta, theta, alpha, beta, gamma), providing multiple-feature multiple-sample evaluation and assessment by Information Theory and Decision Tree Classification.

A beta version of BioMet®Ling is available for download as a ZIP file via the link below. The package includes comprehensive installation and user instructions. If you experience any issues or require assistance, please feel free to contact us. To proceed with the download, kindly register by providing your name and email address.

UCL Division of Psychology and Language Sciences

Speech Hearing and Phonetic Sciences

UCL Speech Hearing and Phonetic Sciences (SHaPS) is internationally recognised for the excellence of its research into the perception and production of speech, hearing for speech and applied research in speech signal processing. It combines basic research into the normal mechanisms of speech and hearing with applied research into problems caused by hearing impairment or by atypical perceptual and cognitive development. Their methodologies include behavioural experimentation, neuro-imaging, computational modelling and acoustic analysis.

Software in Speech, Hearing and Phonetic Sciences

https://rdr.ucl.ac.uk/Division_of_Psychology_Language_Sciences