CLSDASAug 29, 2022

Turn-Taking Prediction for Natural Conversational Speech

arXiv:2208.13321v126 citationsh-index: 69
Originality Incremental advance
AI Analysis

This addresses the challenge of enabling more natural interactions for voice assistants by accurately handling disfluencies and multiple queries in conversations.

The paper tackles the problem of predicting turn-taking in natural conversational speech, which involves disfluencies like hesitations and pauses, by presenting a system that jointly optimizes for speech recognition and turn detection, achieving over 97% recall and 85% precision with 100 ms latency.

While a streaming voice assistant system has been used in many applications, this system typically focuses on unnatural, one-shot interactions assuming input from a single voice query without hesitation or disfluency. However, a common conversational utterance often involves multiple queries with turn-taking, in addition to disfluencies. These disfluencies include pausing to think, hesitations, word lengthening, filled pauses and repeated phrases. This makes doing speech recognition with conversational speech, including one with multiple queries, a challenging task. To better model the conversational interaction, it is critical to discriminate disfluencies and end of query in order to allow the user to hold the floor for disfluencies while having the system respond as quickly as possible when the user has finished speaking. In this paper, we present a turntaking predictor built on top of the end-to-end (E2E) speech recognizer. Our best system is obtained by jointly optimizing for ASR task and detecting when the user is paused to think or finished speaking. The proposed approach demonstrates over 97% recall rate and 85% precision rate on predicting true turn-taking with only 100 ms latency on a test set designed with 4 types of disfluencies inserted in conversational utterances.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes