I am doing my final year project on "Classification of Tonal and Non-Tonal languages" using neural networks. The system takes pitch contour and energy as parameter Using only the pitch contour as a parameter yields an accuracy of 66%, whereas adding short term energy increases it to above 80%.
Many standard literatures also consider energy as a characteristic feature of the language, but provides no explanation.
I have studied the relationship between the pitch and energy contour in my PhD and summarized some of the work in the follow publication. Whilst it is not directly related to tonal languages there is a comprehensive analysis and discussion about the relationship between the two measurements.
The Relationship between Prosody and Breathing in Spontaneous Discourse
Hird, Kathryn ; Kirsner, Kim
Brain and Language, 2002, Vol.80(3), pp.536-555 [Peer Reviewed Journal]
Digital Thesis available from UWA
Are cognitive processes involved in the control of declination in spontaneous speech?
Kathryn Marie Hird University of Western Australia. Dept. of Psychology. 1994
Available at Reid Library Store (Thesis 1994 HIR)
Do not take my answer as an expert comment because it is only inference based on the understanding of languages.
Tone is (primarily) a feature of syllable, which is dominated by the vowel. In the languages where tone does not affect meaning (non-tonal languages), vowels in real speech can have less duration and less amplitude (and energy), whereas in tonal languages, vowels with a specific tonal pattern have to be clear enough to be distinguished with those of different tonal pattern. This, perhaps, should be the reason for the tonal languages having more energy in speech.
Dear Biplav,
I wish you lots of luck with your new research and I believe your adding of the second parameter was a very right thing to do. I would like to refer you to an expert named Mathew Gordon for more details on the issue and here is his e mail: [email protected]
I hope you'll find the referral useful.
Best regards,
R. Biria
The opposite to tonal languages occurs when voiceless segments evaluated as such by the ears appear on the praat screen with a blue line indicating some voicing action by the vocal cords. This fact is explained with the very low intensity: the perception of voicing is neutralized by the very low intensity. I have found this phenomenon in Spanish in particular.
This is a most interesting topic. If I correctly understand your point, the energy used when speaking may vary from one language to another and may influence... Well, frankly I have no idea what may happen. As a professor, I do know that, if speaking for a long time, my voice may become hoarse and begin to feel a slight pain in the throat, obviously I spoke too much. What result may there be if speaking the same time span in a language requiring more energy per second? Or less energy?
Interesting topic indeed. I am no expert in this field, but have become most interested. Perhaps you may send me a draft, to be fairly quoted of course, for the conference in phonetics to be held in Riga, Latvia, on 14–15 May.
I have studied the relationship between the pitch and energy contour in my PhD and summarized some of the work in the follow publication. Whilst it is not directly related to tonal languages there is a comprehensive analysis and discussion about the relationship between the two measurements.
The Relationship between Prosody and Breathing in Spontaneous Discourse
Hird, Kathryn ; Kirsner, Kim
Brain and Language, 2002, Vol.80(3), pp.536-555 [Peer Reviewed Journal]
Digital Thesis available from UWA
Are cognitive processes involved in the control of declination in spontaneous speech?
Kathryn Marie Hird University of Western Australia. Dept. of Psychology. 1994
Available at Reid Library Store (Thesis 1994 HIR)
- Badges
- Science topic
- Similar topics
- Linguistics