In this work, we present AfriHuBERT, an extension of mHuBERT-147, a compact self-supervised learning (SSL) model pretrained on 147 languages. While mHuBERT-147 covered 16 African languages, we expand this to 1,226 through continued pretraining on 10K+ hours of speech data from diverse sources, benefiting an African population of over 600M. We evaluate AfriHuBERT on two key speech tasks, Spoken Language Identification (SLID) and Automatic Speech Recognition (ASR), using the FLEURS benchmark. Our results show a +3.6% F1 score improvement for SLID and a -2.1% average Word Error Rate (WER) reduction for ASR over mHuBERT-147, and demonstrates competitiveness with larger SSL models such as MMS and XEUS. Further analysis shows that ASR models trained on AfriHuBERT exhibit improved cross-corpus generalization and are competitive in extremely low-resource ASR scenarios.
Benchmarking Automatic Speech Recognition Models for African Languages
Makerere University Centre for Artificial Intelligence(Makerere大学人工智能中心);Marconi Lab(Marconi实验室);Department of Information Systems(信息系统系);Department of Electrical Engineering(电气工程系);Department of Computer Science(计算机科学系)
Automatic Speech Recognition for African Low-Resource Languages: Challenges and Future Directions
Bayero University(贝耶罗大学);Kalinga University(卡林加大学);Debre Birhan University(德贝-比哈恩大学);Wollo University(沃尔洛大学);Northeastern University(东北大学);University of Pretoria(比勒陀利亚大学);University of Hamburg(汉堡大学);Imperial College London(伦敦帝国学院);EthioNLP(埃塞俄比亚NLP研究中心);HausaNLP(哈萨NLP研究中心)
本文分析非洲低资源语言 ASR 的数据、语言、算力、声学与伦理挑战,提出社区数据、自监督多语言学习、轻量隐私保护模型等路线。
Toward Responsible ASR for African American English Speakers: A Scoping Review of Bias and Equity in Speech Technology
DePaul University(德保罗大学);University of Washington(华盛顿大学);Carnegie Mellon University(卡内基梅隆大学);Cornell Tech University(康奈尔科技大学);University of Maryland(马里兰大学)
The NaijaVoices Dataset: Cultivating Large-Scale, High-Quality, Culturally-Rich Speech Data for African Languages
Lanfrica(兰非拉);NaijaVoices(尼日利亚之声);Mila - Quebec AI Institute(魁北克人工智能研究所);MLCollective(机器学习集体);The Ohio State University(俄亥俄州立大学);INRIA(法国国家信息与自动化技术研究院);Alex Ekwueme Federal University Ndufu Alike Ikwo(阿莱克斯·埃克韦梅联邦大学);Obafemi Awolowo University(奥巴费米·阿沃尔奥大学);Polytechnique Montreal(蒙特利尔理工学院);University of Montreal(蒙特利尔大学);McGill University(麦吉尔大学);Canada CIFAR AI Chair(加拿大CIFAR人工智能主席)
AfriSpeech-200: Pan-African Accented Speech Dataset for Clinical and General Domain ASR
Mila Quebec AI Institute(米拉魁北克人工智能研究所);Lanfrica;Lelapa AI;Instituto Politécnico Nacional(国立理工学院);Masakhane NLP(Masakhane自然语言处理组织);Intron Health(Intron健康公司);CISPA Helmholtz Center for Information Security(CISPA亥姆霍兹信息安全中心);AI Saturdays Lagos(拉各斯AI周六组织);Karya Inc(Karya公司);Ford Motor Company(福特汽车公司);McGill University(麦吉尔大学);University of Deutso(德乌措大学);University of Colorado Colorado Springs(科罗拉多大学科罗拉多斯普林斯分校);University of Minnesota(明尼苏达大学)
针对非洲口音临床与通用 ASR 数据及基准缺失问题,本文发布涵盖 13 国 120 种口音的 200 小时 AfriSpeech 数据集、测试基准及 SOTA 预训练模型。
Automatic Speech Recognition (ASR) for African Low-Resource Languages: A Systematic Literature Review
Northwest University Kano(北卡罗来纳大学肯诺分校);University of Gondar(贡达大学);Bayero University Kano(巴耶罗大学肯诺分校);University of Pretoria(比提利亚大学);Makerere University(Makerere大学);University of Hamburg(汉堡大学);Imperial College London(伦敦帝国理工学院)
Layer-wise Probing of wav2vec 2.0 and Whisper for Consonant Cluster Reduction in African American English
Department of English Language and Linguistics, Institute of English and American Studies, Faculty of Arts and Humanities, Heinrich Heine University Düsseldorf, Germany(海因里希·海涅大学杜塞尔多夫分校,人文与艺术学院,英美研究学院,英语语言与语言学系);Department of Linguistics, University of Florida, United States of America(佛罗里达大学语言学系)
Performant ASR Models for Medical Entities in Accented Speech
CISPA Helmholtz Center for Information Security(CISPA亥姆霍兹信息安全中心);Intron Health;Université de Lorraine(洛林大学);CNRS(法国国家科学研究中心);Inria(法国国家信息与自动化研究所);LORIA(洛林计算机科学与应用实验室);University of Minnesota - Twin Cities(明尼苏达大学双城分校);African Masters of Machine Intelligence(非洲机器智能硕士项目);AIMS/AMMI(非洲数学科学研究所/非洲机器智能硕士项目);AI Saturdays Lagos(拉各斯AI周六);Masakhane NLP(Masakhane自然语言处理项目)
AfriNames: Most ASR models "butcher" African Names
Intron Health Inc(Intron健康公司);Georgia Institute of Technology(佐治亚理工学院);AI Saturdays Lagos(拉各斯AI星期六组织);CISPA Helmholtz Center for Information Security(亥姆霍兹信息安全中心(CISPA));McGill University(麦吉尔大学);Mila Quebec AI Institute(米拉魁北克人工智能研究所);Lelapa AI(莱拉帕人工智能公司);Lanfrica(Lanfrica公司);Instituto Politécnico Nacional(国立理工学院);Technical University of Munich(慕尼黑工业大学);Idiap Research Institute(Idiap研究所);Ford Motor Company(福特汽车公司);Masakhane NLP(Masakhane自然语言处理组织)
该研究将 ASR 对非洲姓名的识别失败建模为分布偏移,并通过多语言预训练、数据增强和非洲口音微调,使相对 WER 改善 81.5%。
CAFE A Novel Code switching Dataset for Algerian Dialect French and English
University of Bouira(布维拉大学);German Research Center for Artificial Intelligence (DFKI)(德国人工智能研究中心(DFKI));Qatar Computing and Research Institute (HBKU)(卡塔尔计算与研究所(HBKU))
Université de Lorraine(洛林大学);CNRS(法国国家科学研究中心);Inria(法国国家信息与自动化研究所);LORIA(洛林计算机科学与应用实验室);Intron Health(Intron健康公司);Amazethu Research(Amazethu研究所);CISPA Helmholtz Center for Information Security(CISPA亥姆霍兹信息安全中心);AI Saturdays Lagos(拉各斯AI周六组织);University of Pretoria(比勒陀利亚大学);University of Minnesota - Twin Cities(明尼苏达大学双城分校);Luleå University of Technology(吕勒奥理工大学);Masakhane NLP(马萨卡内自然语言处理组织)
Automatic Dialect Detection in Arabic Broadcast Speech
Qatar Computing Research Institute, HBKU(哈马德·本·哈利法大学卡塔尔计算研究所);MIT Computer Science and Artificial Intelligence Laboratory (CSAIL)(麻省理工学院计算机科学与人工智能实验室);JHU Center for Language and Speech Processing (CLSP)(约翰斯·霍普金斯大学语言与语音处理中心);University of Edinburgh(爱丁堡大学)
BibleTTS: a large, high-fidelity, multilingual, and uniquely African speech corpus
Masakhane NLP(Masakhane自然语言处理社区);Coqui(Coqui公司);Saarland University(萨尔大学);CLEAR Global(全球清晰语言组织);Col·lectivaT(Col·lectivaT机构);SIL International(国际暑期语言学院);Leibniz Universität Hannover(汉诺威莱布尼茨大学);Johns Hopkins University(约翰斯·霍普金斯大学);Niger-Volta LTI(尼日尔-沃尔特语言技术倡议);Carnegie Mellon University(卡内基梅隆大学);Technical University of Munich(慕尼黑工业大学);Makerere University(马凯雷雷大学);Ewegbe Akademi(埃韦格贝学院);Kwame Nkrumah University of Science and Technology(夸梅·恩克鲁玛科技大学)
Speech to Speech Translation with Translatotron: A State of the Art Review
International University of Grand-Bassam(大巴萨姆国际大学);Covenant University(圣约大学);HRA, Institute for Systems Science, Durban University of Technology(德班理工大学系统科学研究所HRA中心);Walter Sisulu University(沃尔特·西苏鲁大学);Summit University(萨米特大学)
本文综述语音到语音翻译技术,重点梳理 Google 的 Translatotron 1、2、3 如何由概念验证发展到在部分方面超越级联模型,并指出其弥合非洲语言与成熟语言差距的潜力。