paper-with-me

홈 › Papers

When can I Speak? Predicting initiation points for spoken dialogue agents

2022-08-07 · SIGDIAL (ACL) 2022 9 · Siyan Li, Ashwin Paranjape, Christopher D. Manning

Current spoken dialogue systems initiate their turns after a long period of silence (700-1000ms), which leads to little real-time feedback, sluggish responses, and an overall stilted conversational flow. Humans typically respond within 200ms and successfully predicting initiation points in advance would allow spoken dialogue agents to do the same. In this work, we predict the lead-time to initiation using prosodic features from a pre-trained speech representation model (wav2vec 1.0) operating on user audio and word features from a pre-trained language model (GPT-2) operating on incremental transcriptions. To evaluate errors, we propose two metrics w.r.t. predicted and true lead times. We train and evaluate the models on the Switchboard Corpus and find that our method outperforms features from prior work on both metrics and vastly outperforms the common approach of waiting for 700ms of silence.

📄 PDF Abstract BibTeX arXiv:2208.03812

Code (1)

siyan-sylvia-li/icarus_final 공식 구현 pytorch

Tasks

Language ModelingLanguage ModellingSpoken Dialogue Systems

Similar Papers 제목 키워드 기반

Improving End-of-turn Detection in Spoken Dialogues by Detecting Speaker Intentions as a Secondary Task

2018-05-09 · Zakaria Aldeneh, Dimitrios Dimitriadis, Emily Mower Provost

This work focuses on the use of acoustic cues for modeling turn-taking in dyadic spoken dialogues. Previous work has shown that speaker intentions (e.g., asking a question, uttering a backchannel, etc.) can influence tur…

Initiations and Interruptions in a Spoken Dialog System

2016-09-01 · WS 2016 9 · Leah Nicolich-Henkin, Carolyn Ros{\'e}, Alan W. black

Joint Modeling of Content and Discourse Relations in Dialogues

2017-05-14 · ACL 2017 7 · Kechen Qin, Lu Wang, Joseph Kim

We present a joint modeling approach to identify salient discussion points in spoken meetings as well as to label the discourse relations between speaker turns. A variation of our model is also discussed when discourse r…

Relation Prediction

Large Language Models Know What To Say But Not When To Speak

2024-10-21 · Muhammad Umair, Vasanth Sarathy, Jp de Ruiter

Turn-taking is a fundamental mechanism in human communication that ensures smooth and coherent verbal interactions. Recent advances in Large Language Models (LLMs) have motivated their use in improving the turn-taking ca…

Spoken Dialogue Systems

The importance of fillers for text representations of speech transcripts

2020-09-23 · EMNLP 2020 11 · Tanvi Dinkar, Pierre Colombo, Matthieu Labeau, Chloé Clavel

While being an essential component of spoken language, fillers (e.g."um" or "uh") often remain overlooked in Spoken Language Understanding (SLU) tasks. We explore the possibility of representing them with deep contextual…

Spoken Language Understanding