Joint On-line Learning Of A Zero-shot Spoken Semantic Parser And A Reinforcement Learning Dialogue Manager
2018 · Matthieu Riou, Bassam Jabaian, Stéphane Huet, et al.
Abstract
Despite many recent advances for the design of dialogue systems, a true bottleneck remains the acquisition of data required to train its components. Unlike many other language processing applications, dialogue systems require interactions with users, therefore it is complex to develop them with pre-recorded data. Building on previous works, on-line learning is pursued here as a most convenient way to address the issue. Data collection, annotation and use in learning algorithms are performed in a single process. The main difficulties are then: to bootstrap an initial basic system, and to control the level of additional cost on the user side. Considering that well-performing solutions can be used directly off the shelf for speech recognition and synthesis, the study is focused on learning the spoken language understanding and dialogue management modules only. Several variants of joint learning are investigated and tested with user trials to confirm that the overall on-line learning can b
Authors
(none)
Tags
Stats
Related papers
- Nearly Zero-shot Learning For Semantic Decoding In Spoken Dialogue Systems (2018)0.00
- Exploration Of End-to-end Synthesisers Forzero Resource Speech Challenge 2020 (2020)4.52
- An Adversarial Learning Based Multi-step Spoken Language Understanding System Through Human-computer Interaction (2021)0.00
- Joint Online Spoken Language Understanding And Language Modeling With Recurrent Neural Networks (2016)13.28
- Speaker Diarization As A Fully Online Learning Problem In Minivox (2020)0.00
- Self-supervised Language Learning From Raw Audio: Lessons From The Zero Resource Speech Challenge (2022)10.07
- Speechdialoguefactory: Generating High-quality Speech Dialogue Data To Accelerate Your Speech-llm Development (2025)0.00
- Dialogueagents: A Hybrid Agent-based Speech Synthesis Framework For Multi-party Dialogue (2025)1.69