Hi there,
There are recordings from different English talkers (i.e., language: English; recordings: sentences). For each recording, there are multiple sentences with pauses between sentences. We have already transcribed the recordings to text scripts accordingly. We would like to do segmentations for these recordings next.
Is there a method to automatically label consonants and vowels of each sentence using Praat?
PS. That is fine if the boundaries are not accurate. We can adjust them manually.
Thanks,
Yanping
Dear Yanping Li
Praat is primarily designed for phonetic analysis and speech-related tasks, and it may not be the most suitable tool for automatic English sentence segmentation. However, if you are looking to work with text and sentence segmentation, explore other tools or programming languages that are better suited for natural language processing (NLP) tasks.
You may check out these references at any time:
Article Effective Semi-Supervised Learning Strategies for Automatic ...
https://acikerisim.isikun.edu.tr/xmlui/handle/11729/1317
https://www.esat.kuleuven.be/psi/spraak/cgi-bin/get_file.cgi?/dseppi/aisv11/aisv11.pdf&auto&ds:aisv11
https://repositori.upf.edu/handle/10230/28063
I hope it helps in getting started.....
Regards,
Shafik
Dear Wasswa Shafik
Thanks for your comments. The paper looks cool.
My gut feeling for this task is to use Praat scripts to label boundaries. It seems that there are better methods than running Praat scripts. I am not sure whether it is possible to extract acoustic parameters after using NLP..... Will read the paper for details. Thanks.
Cheers,
Yanping
- Badges
- Science topic
- Similar topics
- Biological Science
- Molecular Biology
- Biomolecules
- Nucleic Acids
- RNA