Oh, Jeez! or Uh-huh? A Listener-aware Backchannel Predictor on ASR Transcriptions

Ortega, Daniel, Li, Chia-Yu, Vu, Ngoc Thang

arXiv.org Artificial Intelligence 

This paper presents our latest investigation on modeling backchannel in conversations. Motivated by a proactive backchanneling theory, we aim at developing a system which acts as a proactive listener by inserting backchannels, such as continuers and assessment, to influence speakers. Our model takes into account not only lexical and acoustic cues, but also introduces the simple and novel idea of using listener embeddings to mimic different backchanneling behaviours. Our experimental results on the Switchboard benchmark dataset reveal that acoustic cues are more important than lexical cues in this task and their combination with listener embeddings works best on both, manual transcriptions and automatically generated transcriptions.

Duplicate Docs Excel Report

Title
None found

Similar Docs  Excel Report  more

TitleSimilaritySource
None found