Detection of Overlapping Speech using a Convolutional Neural Network: First Experiments

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F18%3A43952729" target="_blank" >RIV/49777513:23520/18:43952729 - isvavai.cz</a>
Result on the web
<a href="http://hdl.handle.net/11025/29824" target="_blank" >http://hdl.handle.net/11025/29824</a>
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Detection of Overlapping Speech using a Convolutional Neural Network: First Experiments
Original language description
Many speech processing applications, such as speaker diarization and speech recognition, have problems with overlapping speech, i.e. intervals in which multiple speakers are talking simultaneously. This happens particularly often in spontaneous conversations, where speakers may regularly interrupt each other or interject short utterances while the original speaker keeps talking. Detecting such occurrences can help improve the performance of the impacted systems. However, this is still an actively researched task, which has not yet been fully solved. In this work, I describe my initial experiments in using a convolutional neural network (CNN) to detect overlapping speech in an artificial dataset created for the purpose.
Czech name
—
Czech description
—

Publication year
2018
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)