Praat, a system for doing phonetics by computer

By Paul P. G. Boersma. 2002

10,080 citations recorded by the source corpus.

How researchers see this paper

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

1. Xu Tan
2. Yi Ren
3. Tao Qin
4. Rongjie Huang
5. Zhou Zhao
6. Yoshua Bengio
7. Jinglin Liu
8. Yu Zhang

Citations in the corpus

• Deep Voice: Real-time Neural Text-to-Speech (2017, methodology): “The Praat batch script used to generate F0 is available at https://github.com/baidu-research/deep-voice/blob/master/scripts/f0-script.praat and can be run with praat --run f0-script.praat .”
• Comparison of Gender- and Speaker-adaptive Emotion Recognition (2014, methodology): “The speech signal features of the first set have been extracted from wave files using the Praat system (Boersma, 2002).”
• Gemination in Tashlhiyt Berber: an acoustic and articulatory study (2007, methodology): “Broad-band spectrograms of all utterances and visual displays of the corresponding waveforms were created and analysed using the Praat software package (Boersma 2001).”
• A Common Neural Substrate for Language Production and Verbal Working Memory (2011, unknown): “In order to avoid difficulties associated with voice keys in noisy environments, speaking times were manually scored by listening to subject responses and visually examining the speech spectrogram using Praat software (Boersma, 2001).”
• M4Singer: A Multi-Style, Multi-Singer and Musical Score Provided Mandarin Singing Corpus (2022, methodology): “Annotators leverage Praat [6] to make corrections on the rough annotation results, mainly concentrating on the following aspects: 1) Boundary correction: the annotators correct the boundaries of words and phonemes by listening to the audio and observing the spectrogram, which constitutes the main…”
• Automatic Prosodic Labeling with Conditional Random Fields and Rich Acoustic Features (2008, methodology): “Using Praat’s (Boersma, 2001) ”To pitch” and ”To intensity” functions and the phoneme, syllable, and word alignments provided in the corpus, we extract acoustic features for the region of interest.”