Cross-Lingual Conversational Speech Summarization with Large Language Models
This addresses the lack of resources for cross-lingual speech summarization, but it is incremental as it builds on existing datasets and models.
The paper tackled cross-lingual conversational speech summarization by creating a dataset with GPT-4-generated summaries from translations and developed a system using Mistral-7B, which matched GPT-4's performance in handling transcription and translation errors.
Cross-lingual conversational speech summarization is an important problem, but suffers from a dearth of resources. While transcriptions exist for a number of languages, translated conversational speech is rare and datasets containing summaries are non-existent. We build upon the existing Fisher and Callhome Spanish-English Speech Translation corpus by supplementing the translations with summaries. The summaries are generated using GPT-4 from the reference translations and are treated as ground truth. The task is to generate similar summaries in the presence of transcription and translation errors. We build a baseline cascade-based system using open-source speech recognition and machine translation models. We test a range of LLMs for summarization and analyze the impact of transcription and translation errors. Adapting the Mistral-7B model for this task performs significantly better than off-the-shelf models and matches the performance of GPT-4.