PaperScope
LIVE · 2026-09-29 05:40 UTC

Turning Speech Language Models into Multilingual Listeners

Tolúlopé Ògúnrèmí, Dan Jurafsky, Chris Manning, Ahmet Üstün, Martijn Bartelds

Latestcs.CLcs.LGcs.AIcs.CV
arXiv ID
2609.33204 v1
Category
Submitted
2026-09-27

Abstract

Speech Language Models (SLMs) that understand spoken language questions support only a few high-resource languages, limiting access to millions of people worldwide. This gap stems from the scarcity of multilingual speech instruction-tuning datasets. We present MULTISPEECHQA, a large-scale, synthetically generated and human-verified dataset comprising 9200 hours of 10.8 million spoken question-answer pairs in 23 typologically diverse languages. Using MULTISPEECHQA, we also introduce MULTISPEECH-BENCH, a multi-task benchmark for evaluating SLM performance on 23 languages. We compare the performance of a cascading system to open-weight and closed SLMs on MULTISPEECH-BENCH and find that the cascading system outperforms open-weight SLMs but not all closed SLMs. We use MULTISPEECHQA to finetune Qwen 2.5-Omni, which improves its performance on our benchmark. Our findings show that high-quality synthetic datasets offer a cheap solution to improving the multilingual capabilities of SLMs.

Comment: Interspeech 2026 Long

arXiv abs page · PDF · same-day batch