Turning Speech Language Models into Multilingual Listeners

arXiv:2609.33204 · cs.CL · Submitted 2026-09-27 · Read on arXiv

cs.CL

Submitted: 2026-09-27

Updated: 2026-09-27

Comments: Interspeech 2026 Long

Code: https://github.com/quocanh34/Bud500

Project page: https://multispeech.github.io

License: http://creativecommons.org/licenses/by/4.0/

The gist: Speech Language Models (SLMs) that understand spoken language questions support only a few high-resource languages, limiting access to millions of people worldwide.

Terminology

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.

Sources

Related papers