Our Question

How can we better convey information from a target language in hopes of modulating the tension between translation and interpretation?

Our Solution

The solution we decided to pursue after our peers’ feedback was a speech translator that incorporates prosodic elements of speech (i.e: rhythm, loudness, stress, speed, pitch, and intonation) in order to clarify communication.


Firstly, it would be best to establish what prosody actually is. In general, prosody can be referred to as a set of elements that affect how a message is communicated and understood. Prosodic elements of speech include: rhythm, loudness, stress, speed, pitch, and intonation. Now that we defined prosody we can ask ourselves “does prosody really matter?” The simple answer is that yes it really does! Prosodic elements help process discourse structures, recognize a speaker’s emotional state, clarify communication, resolve ambiguities, and more! Since prosody is such a descriptive factor of spoken language, we believe it would help interactants derive and comprehend important information from translations.

Paper Prototype Description

Our group decided to model our “prosody translator” prototype after the current Google Translate app. Similar to the Google Translate app, the speaker will have the ability to input a dialogue that they wish to be translated from the native language (language A) to any language of their choosing (language B). Since our prototype is dependent on the speaker’s prosodic features, it is necessary for the input dialogue from language A to be spoken and not typed. From this, the prosody software will work with three basic components of soundwaves to compose a translation that accurately corresponds to the speaker’s emotional state. These three components include: timing (duration of pauses between words and sentences), pitch (the change of pitch within words and sentences) and volume (the change in wave amplitude that indicates emphasis). After the translation is generated, the speaker will have the option to listen to the translation in language B and read a typed version of the translation. From there, the speaker will have the ability to modify any part of the translation if necessary. It’s important to note that the prosody software will continue to learn from the speaker as new information is input into the translator.  

Mary, L. (1970, January 01). Significance of Prosody for Speaker, Language and Speech Recognition. Retrieved from https://link.springer.com/chapter/10.1007/978-1-4614-1159-8_1

Talbot, D. (2020, April 02). Prosody. Retrieved from https://www.technologyreview.com/2002/07/01/40873/prosody/