Spoken Language Understanding

insight - Spoken Language Understanding

UniverSLU: A Versatile Spoken Language Understanding Model for Diverse Tasks with Natural Language Instructions

A single multi-task learning model "UniverSLU" can perform various speech classification and sequence generation tasks, often outperforming or matching state-of-the-art task-specific models. UniverSLU leverages natural language instructions as prompts to enhance user-friendliness and generalization.

Leveraging Large Language Models to Expand Spoken Language Understanding Systems Across Multiple Languages

A pipeline leveraging Large Language Models (LLMs) for machine translation of slot-annotated spoken language understanding (SLU) training data can effectively extend SLU systems to new languages, outperforming existing state-of-the-art methods.

Enhanced MEDIA Benchmark for French Spoken Language Understanding with Intent Annotations

This paper presents an enhanced version of the MEDIA benchmark dataset for French Spoken Language Understanding (SLU), with newly added intent annotations. It also provides baseline results for joint intent classification and slot-filling models on this enhanced dataset, using both manual transcriptions and automatic speech recognition outputs.

About

Products | Resources

Insights