E2E Spoken Entity Extraction for Virtual Agents
This addresses the challenge of spoken entity extraction for virtual agents, offering a more efficient solution.
The paper tackled the problem of extracting entities like names and addresses directly from speech without transcription, showing that a one-step approach outperforms the typical two-step method in virtual agent dialogues.
In human-computer conversations, extracting entities such as names, street addresses and email addresses from speech is a challenging task. In this paper, we study the impact of fine-tuning pre-trained speech encoders on extracting spoken entities in human-readable form directly from speech without the need for text transcription. We illustrate that such a direct approach optimizes the encoder to transcribe only the entity relevant portions of speech ignoring the superfluous portions such as carrier phrases, or spell name entities. In the context of dialog from an enterprise virtual agent, we demonstrate that the 1-step approach outperforms the typical 2-step approach which first generates lexical transcriptions followed by text-based entity extraction for identifying spoken entities.