@inproceedings{akera-etal-2026-real,
title = "Real-Time Spoken Instruction Following and Translation in Ugandan Languages",
author = "Akera, Benjamin and
Hu, Tim Wenjie and
Walukagga, Patrick and
Ouma, Evelyn Nafula and
Gilbert, Yiga and
Mwebaze, Ernest Tonny and
Quinn, John",
editor = "Chimoto, Everlyn Asiko and
Lignos, Constantine and
Muhammad, Shamsuddeen and
Abdulmumin, Idris and
Siro, Clemencia and
Adelani, David Ifeoluwa",
booktitle = "Proceedings of the 7th Workshop on {A}frican Natural Language Processing ({A}frica{NLP} 2026)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.africanlp-main.20/",
pages = "204--210",
ISBN = "979-8-89176-364-7",
abstract = "Many languages are predominantly spoken rather than written, and to bring the benefits of LLMs to speakers of these languages, it is essential that models cater to the voice modality. The typical approach is to cascade ASR, LLM and TTS models together, though this results in systems with high latency, making them unsuitable for natural, real-time interaction. We describe results on taking the encoder part of a Whisper-based model trained to recognise ten languages common in Uganda, and using the Ultravox architecture to project its output directly to the input embedding space of a text model based on Qwen 3 32B, also trained to have comprehension of those languages. The result is a speech LLM with high accuracy and very low latency. For most spoken prompts, we can begin streaming a text response within as low as 50 ms, and a speech audio response within around one second, making real-time spoken interaction with an LLM possible for the first time in these languages. The model is available open source onHugging Face."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="akera-etal-2026-real">
<titleInfo>
<title>Real-Time Spoken Instruction Following and Translation in Ugandan Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Akera</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="given">Wenjie</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Walukagga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Evelyn</namePart>
<namePart type="given">Nafula</namePart>
<namePart type="family">Ouma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiga</namePart>
<namePart type="family">Gilbert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ernest</namePart>
<namePart type="given">Tonny</namePart>
<namePart type="family">Mwebaze</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Quinn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 7th Workshop on African Natural Language Processing (AfricaNLP 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Everlyn</namePart>
<namePart type="given">Asiko</namePart>
<namePart type="family">Chimoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Constantine</namePart>
<namePart type="family">Lignos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shamsuddeen</namePart>
<namePart type="family">Muhammad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Idris</namePart>
<namePart type="family">Abdulmumin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Clemencia</namePart>
<namePart type="family">Siro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">Ifeoluwa</namePart>
<namePart type="family">Adelani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-364-7</identifier>
</relatedItem>
<abstract>Many languages are predominantly spoken rather than written, and to bring the benefits of LLMs to speakers of these languages, it is essential that models cater to the voice modality. The typical approach is to cascade ASR, LLM and TTS models together, though this results in systems with high latency, making them unsuitable for natural, real-time interaction. We describe results on taking the encoder part of a Whisper-based model trained to recognise ten languages common in Uganda, and using the Ultravox architecture to project its output directly to the input embedding space of a text model based on Qwen 3 32B, also trained to have comprehension of those languages. The result is a speech LLM with high accuracy and very low latency. For most spoken prompts, we can begin streaming a text response within as low as 50 ms, and a speech audio response within around one second, making real-time spoken interaction with an LLM possible for the first time in these languages. The model is available open source onHugging Face.</abstract>
<identifier type="citekey">akera-etal-2026-real</identifier>
<location>
<url>https://aclanthology.org/2026.africanlp-main.20/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>204</start>
<end>210</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Real-Time Spoken Instruction Following and Translation in Ugandan Languages
%A Akera, Benjamin
%A Hu, Tim Wenjie
%A Walukagga, Patrick
%A Ouma, Evelyn Nafula
%A Gilbert, Yiga
%A Mwebaze, Ernest Tonny
%A Quinn, John
%Y Chimoto, Everlyn Asiko
%Y Lignos, Constantine
%Y Muhammad, Shamsuddeen
%Y Abdulmumin, Idris
%Y Siro, Clemencia
%Y Adelani, David Ifeoluwa
%S Proceedings of the 7th Workshop on African Natural Language Processing (AfricaNLP 2026)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-364-7
%F akera-etal-2026-real
%X Many languages are predominantly spoken rather than written, and to bring the benefits of LLMs to speakers of these languages, it is essential that models cater to the voice modality. The typical approach is to cascade ASR, LLM and TTS models together, though this results in systems with high latency, making them unsuitable for natural, real-time interaction. We describe results on taking the encoder part of a Whisper-based model trained to recognise ten languages common in Uganda, and using the Ultravox architecture to project its output directly to the input embedding space of a text model based on Qwen 3 32B, also trained to have comprehension of those languages. The result is a speech LLM with high accuracy and very low latency. For most spoken prompts, we can begin streaming a text response within as low as 50 ms, and a speech audio response within around one second, making real-time spoken interaction with an LLM possible for the first time in these languages. The model is available open source onHugging Face.
%U https://aclanthology.org/2026.africanlp-main.20/
%P 204-210
Markdown (Informal)
[Real-Time Spoken Instruction Following and Translation in Ugandan Languages](https://aclanthology.org/2026.africanlp-main.20/) (Akera et al., AfricaNLP 2026)
ACL