Dear all,
I have a recorded of 134 singers (acoustic variables) and 40 judges (audio-perceptua is variable). The judges have judged the voices of singers. Is it possible to establish the relationship of acoustic variables (numerical variables) and audio-perceptual (nominal and ordinal variables) via ODA? If so, what papers of ODA journal do you recommended me to read ?.
Thank you very much,
Helena
Dear all,
Perhaps the answer would began by categorize the acoustic variable, and in that way we could aplly ODA.
But to do that, we need a theory in the music field that could explain me the correct way to define the cut points....
Who can help me, please?
Thank you
Helena
Hi!
Can you please clarify what you mean by ODA? I'm not sure what it stands for.
I'm guessing you are looking for acoustical cues that relate to a good singing timbre. If so, I should mention that singers work to develop the so-called "fifth formant", that is, the highest frequency resonance. Due to acoustic streaming, the very high frequency formant helps the listener to trace to the fundamental of the acoustic source. Moreover, this formant contributes to a round and free quality of sound which is aesthetically desirable.
My immediate thoughts are to the work of John Grey, Strawn, Moorer, and Chowning, who have attempted to create a (3 dimensional) vector space to relate timbres of various instruments along different perceptually-salient characteristics. I also recall some very nice sonograms of great tenors at the the end of Richard Miller's Training Tenor Voices.
Hope it's helpful!
Dear Jason,
ODA is a new paradigm of maximun accuracy developed by Paul Yarnold (RG).
is it possible to have acess to your paper, because it seems to me very very interesting.
Thank you very much for your wised answer.
Helena
The acoustics and the paralinguistic roles of breathy/whispery voice qualities are analyzed in spontaneous dialogue speech of several speakers. Analyses show that breathy/whispery voices carry a variety of emotion- or attitude-related paralinguistic information. Breathiness often appeared in emphasized words/phrases, having the effect of calling/catching the listener’s attention. It also rhythmically appeared in utterances expressing the speaker’s excitement. In backchannels, breathiness has the effect of expressing politeness or interest to the listener’s talk. When accompanied by a softer voice quality, breathiness is used to call/catch the listener’s attention, while expressing gentleness or tenderness. A more whispered and low-powered voice quality appears in confidential talking, embarrassment, or when the speaker is talking to oneself.
http://www.ieice.org/ken/paper/iaEk/eng/
Dear Helena,
Check this out:
Article Contributions to music semantic analysis and its acceleratio...
Dear beatrice,
I have read quicky that paper but it seems very interesting and useful. Thank you very much.
Have a nice time,
Helena
The same to you Dear Helena,
I also have problems with ODA.
I looked it up but it did not fit into music.
Article Using Music to Elicit Emotion in Robots
Article Features and classifiers for emotion recognition from speech...
Article P56 Recording voices. Why is oral history important in palli...
Article Post-operative pain management through audio-analgesia: Inve...
Article Acoustic analysis of children's voices: phonatory deviation ...
If you want we can test your dataset with my new data preprocessing method that improove a lot the classification results. (see Publication:"A Novel Machine Learning Data Preprocessing Method for Enhancing Classification Algorithms Performance)
Dear all,
Thank you very much for those very useful information.
I am very greatfull.
Helena
- Badges
- Science topic