Alert button
Picture for Chris Chinenye Emezue

Chris Chinenye Emezue

Alert button

AfriSpeech-200: Pan-African Accented Speech Dataset for Clinical and General Domain ASR

Sep 30, 2023
Tobi Olatunji, Tejumade Afonja, Aditya Yadavalli, Chris Chinenye Emezue, Sahib Singh, Bonaventure F. P. Dossou, Joanne Osuchukwu, Salomey Osei, Atnafu Lambebo Tonja, Naome Etori, Clinton Mbataku

Figure 1 for AfriSpeech-200: Pan-African Accented Speech Dataset for Clinical and General Domain ASR
Figure 2 for AfriSpeech-200: Pan-African Accented Speech Dataset for Clinical and General Domain ASR
Figure 3 for AfriSpeech-200: Pan-African Accented Speech Dataset for Clinical and General Domain ASR
Figure 4 for AfriSpeech-200: Pan-African Accented Speech Dataset for Clinical and General Domain ASR

Africa has a very low doctor-to-patient ratio. At very busy clinics, doctors could see 30+ patients per day -- a heavy patient burden compared with developed countries -- but productivity tools such as clinical automatic speech recognition (ASR) are lacking for these overworked clinicians. However, clinical ASR is mature, even ubiquitous, in developed nations, and clinician-reported performance of commercial clinical ASR systems is generally satisfactory. Furthermore, the recent performance of general domain ASR is approaching human accuracy. However, several gaps exist. Several publications have highlighted racial bias with speech-to-text algorithms and performance on minority accents lags significantly. To our knowledge, there is no publicly available research or benchmark on accented African clinical ASR, and speech data is non-existent for the majority of African accents. We release AfriSpeech, 200hrs of Pan-African English speech, 67,577 clips from 2,463 unique speakers across 120 indigenous accents from 13 countries for clinical and general domain ASR, a benchmark test set, with publicly available pre-trained models with SOTA performance on the AfriSpeech benchmark.

* Accepted to TACL 2023. This is a pre-MIT Press publication version 
Viaarxiv icon

Benchmarking Bayesian Causal Discovery Methods for Downstream Treatment Effect Estimation

Jul 30, 2023
Chris Chinenye Emezue, Alexandre Drouin, Tristan Deleu, Stefan Bauer, Yoshua Bengio

Figure 1 for Benchmarking Bayesian Causal Discovery Methods for Downstream Treatment Effect Estimation
Figure 2 for Benchmarking Bayesian Causal Discovery Methods for Downstream Treatment Effect Estimation
Figure 3 for Benchmarking Bayesian Causal Discovery Methods for Downstream Treatment Effect Estimation
Figure 4 for Benchmarking Bayesian Causal Discovery Methods for Downstream Treatment Effect Estimation

The practical utility of causality in decision-making is widespread and brought about by the intertwining of causal discovery and causal inference. Nevertheless, a notable gap exists in the evaluation of causal discovery methods, where insufficient emphasis is placed on downstream inference. To address this gap, we evaluate seven established baseline causal discovery methods including a newly proposed method based on GFlowNets, on the downstream task of treatment effect estimation. Through the implementation of a distribution-level evaluation, we offer valuable and unique insights into the efficacy of these causal discovery methods for treatment effect estimation, considering both synthetic and real-world scenarios, as well as low-data scenarios. The results of our study demonstrate that some of the algorithms studied are able to effectively capture a wide range of useful and diverse ATE modes, while some tend to learn many low-probability modes which impacts the (unrelaxed) recall and precision.

* Peer-reviewed and Accepted to ICML 2023 Workshop on Structured Probabilistic Inference & Generative Modeling 
Viaarxiv icon

Adapting Pretrained ASR Models to Low-resource Clinical Speech using Epistemic Uncertainty-based Data Selection

Jun 03, 2023
Bonaventure F. P. Dossou, Atnafu Lambebo Tonja, Chris Chinenye Emezue, Tobi Olatunji, Naome A Etori, Salomey Osei, Tosin Adewumi, Sahib Singh

Figure 1 for Adapting Pretrained ASR Models to Low-resource Clinical Speech using Epistemic Uncertainty-based Data Selection
Figure 2 for Adapting Pretrained ASR Models to Low-resource Clinical Speech using Epistemic Uncertainty-based Data Selection
Figure 3 for Adapting Pretrained ASR Models to Low-resource Clinical Speech using Epistemic Uncertainty-based Data Selection
Figure 4 for Adapting Pretrained ASR Models to Low-resource Clinical Speech using Epistemic Uncertainty-based Data Selection

While there has been significant progress in ASR, African-accented clinical ASR has been understudied due to a lack of training datasets. Building robust ASR systems in this domain requires large amounts of annotated or labeled data, for a wide variety of linguistically and morphologically rich accents, which are expensive to create. Our study aims to address this problem by reducing annotation expenses through informative uncertainty-based data selection. We show that incorporating epistemic uncertainty into our adaptation rounds outperforms several baseline results, established using state-of-the-art (SOTA) ASR models, while reducing the required amount of labeled data, and hence reducing annotation costs. Our approach also improves out-of-distribution generalization for very low-resource accents, demonstrating the viability of our approach for building generalizable ASR models in the context of accented African clinical ASR, where training datasets are predominantly scarce.

Viaarxiv icon

AfriNames: Most ASR models "butcher" African Names

Jun 02, 2023
Tobi Olatunji, Tejumade Afonja, Bonaventure F. P. Dossou, Atnafu Lambebo Tonja, Chris Chinenye Emezue, Amina Mardiyyah Rufai, Sahib Singh

Figure 1 for AfriNames: Most ASR models "butcher" African Names
Figure 2 for AfriNames: Most ASR models "butcher" African Names
Figure 3 for AfriNames: Most ASR models "butcher" African Names
Figure 4 for AfriNames: Most ASR models "butcher" African Names

Useful conversational agents must accurately capture named entities to minimize error for downstream tasks, for example, asking a voice assistant to play a track from a certain artist, initiating navigation to a specific location, or documenting a laboratory result for a patient. However, where named entities such as ``Ukachukwu`` (Igbo), ``Lakicia`` (Swahili), or ``Ingabire`` (Rwandan) are spoken, automatic speech recognition (ASR) models' performance degrades significantly, propagating errors to downstream systems. We model this problem as a distribution shift and demonstrate that such model bias can be mitigated through multilingual pre-training, intelligent data augmentation strategies to increase the representation of African-named entities, and fine-tuning multilingual ASR models on multiple African accents. The resulting fine-tuned models show an 81.5\% relative WER improvement compared with the baseline on samples with African-named entities.

* Accepted at Interspeech 2023 (Main Conference) 
Viaarxiv icon

MasakhaPOS: Part-of-Speech Tagging for Typologically Diverse African Languages

May 23, 2023
Cheikh M. Bamba Dione, David Adelani, Peter Nabende, Jesujoba Alabi, Thapelo Sindane, Happy Buzaaba, Shamsuddeen Hassan Muhammad, Chris Chinenye Emezue, Perez Ogayo, Anuoluwapo Aremu, Catherine Gitau, Derguene Mbaye, Jonathan Mukiibi, Blessing Sibanda, Bonaventure F. P. Dossou, Andiswa Bukula, Rooweither Mabuya, Allahsera Auguste Tapo, Edwin Munkoh-Buabeng, victoire Memdjokam Koagne, Fatoumata Ouoba Kabore, Amelia Taylor, Godson Kalipe, Tebogo Macucwa, Vukosi Marivate, Tajuddeen Gwadabe, Mboning Tchiaze Elvis, Ikechukwu Onyenwe, Gratien Atindogbe, Tolulope Adelani, Idris Akinade, Olanrewaju Samuel, Marien Nahimana, Théogène Musabeyezu, Emile Niyomutabazi, Ester Chimhenga, Kudzai Gotosa, Patrick Mizha, Apelete Agbolo, Seydou Traore, Chinedu Uchechukwu, Aliyu Yusuf, Muhammad Abdullahi, Dietrich Klakow

Figure 1 for MasakhaPOS: Part-of-Speech Tagging for Typologically Diverse African Languages
Figure 2 for MasakhaPOS: Part-of-Speech Tagging for Typologically Diverse African Languages
Figure 3 for MasakhaPOS: Part-of-Speech Tagging for Typologically Diverse African Languages
Figure 4 for MasakhaPOS: Part-of-Speech Tagging for Typologically Diverse African Languages

In this paper, we present MasakhaPOS, the largest part-of-speech (POS) dataset for 20 typologically diverse African languages. We discuss the challenges in annotating POS for these languages using the UD (universal dependencies) guidelines. We conducted extensive POS baseline experiments using conditional random field and several multilingual pre-trained language models. We applied various cross-lingual transfer models trained with data available in UD. Evaluating on the MasakhaPOS dataset, we show that choosing the best transfer language(s) in both single-source and multi-source setups greatly improves the POS tagging performance of the target languages, in particular when combined with cross-lingual parameter-efficient fine-tuning methods. Crucially, transferring knowledge from a language that matches the language family and morphosyntactic properties seems more effective for POS tagging in unseen languages.

* Accepted to ACL 2023 (Main conference) 
Viaarxiv icon

MasakhaNEWS: News Topic Classification for African languages

Apr 19, 2023
David Ifeoluwa Adelani, Marek Masiak, Israel Abebe Azime, Jesujoba Oluwadara Alabi, Atnafu Lambebo Tonja, Christine Mwase, Odunayo Ogundepo, Bonaventure F. P. Dossou, Akintunde Oladipo, Doreen Nixdorf, Chris Chinenye Emezue, Sana Sabah al-azzawi, Blessing K. Sibanda, Davis David, Lolwethu Ndolela, Jonathan Mukiibi, Tunde Oluwaseyi Ajayi, Tatiana Moteu Ngoli, Brian Odhiambo, Abraham Toluwase Owodunni, Nnaemeka C. Obiefuna, Shamsuddeen Hassan Muhammad, Saheed Salahudeen Abdullahi, Mesay Gemeda Yigezu, Tajuddeen Gwadabe, Idris Abdulmumin, Mahlet Taye Bame, Oluwabusayo Olufunke Awoyomi, Iyanuoluwa Shode, Tolulope Anu Adelani, Habiba Abdulganiy Kailani, Abdul-Hakeem Omotayo, Adetola Adeeko, Afolabi Abeeb, Anuoluwapo Aremu, Olanrewaju Samuel, Clemencia Siro, Wangari Kimotho, Onyekachi Raphael Ogbu, Chinedu E. Mbonu, Chiamaka I. Chukwuneke, Samuel Fanijo, Jessica Ojo, Oyinkansola F. Awosan, Tadesse Kebede Guge, Sakayo Toadoum Sari, Pamela Nyatsine, Freedmore Sidume, Oreen Yousuf, Mardiyyah Oduwole, Ussen Kimanuka, Kanda Patrick Tshinu, Thina Diko, Siyanda Nxakama, Abdulmejid Tuni Johar, Sinodos Gebre, Muhidin Mohamed, Shafie Abdi Mohamed, Fuad Mire Hassan, Moges Ahmed Mehamed, Evrard Ngabire, Pontus Stenetorp

Figure 1 for MasakhaNEWS: News Topic Classification for African languages
Figure 2 for MasakhaNEWS: News Topic Classification for African languages
Figure 3 for MasakhaNEWS: News Topic Classification for African languages
Figure 4 for MasakhaNEWS: News Topic Classification for African languages

African languages are severely under-represented in NLP research due to lack of datasets covering several NLP tasks. While there are individual language specific datasets that are being expanded to different tasks, only a handful of NLP tasks (e.g. named entity recognition and machine translation) have standardized benchmark datasets covering several geographical and typologically-diverse African languages. In this paper, we develop MasakhaNEWS -- a new benchmark dataset for news topic classification covering 16 languages widely spoken in Africa. We provide an evaluation of baseline models by training classical machine learning models and fine-tuning several language models. Furthermore, we explore several alternatives to full fine-tuning of language models that are better suited for zero-shot and few-shot learning such as cross-lingual parameter-efficient fine-tuning (like MAD-X), pattern exploiting training (PET), prompting language models (like ChatGPT), and prompt-free sentence transformer fine-tuning (SetFit and Cohere Embedding API). Our evaluation in zero-shot setting shows the potential of prompting ChatGPT for news topic classification in low-resource African languages, achieving an average performance of 70 F1 points without leveraging additional supervision like MAD-X. In few-shot setting, we show that with as little as 10 examples per label, we achieved more than 90\% (i.e. 86.0 F1 points) of the performance of full supervised training (92.6 F1 points) leveraging the PET approach.

* Accepted to AfricaNLP Workshop @ICLR 2023 (non-archival) 
Viaarxiv icon

AfroDigits: A Community-Driven Spoken Digit Dataset for African Languages

Apr 04, 2023
Chris Chinenye Emezue, Sanchit Gandhi, Lewis Tunstall, Abubakar Abid, Josh Meyer, Quentin Lhoest, Pete Allen, Patrick Von Platen, Douwe Kiela, Yacine Jernite, Julien Chaumond, Merve Noyan, Omar Sanseviero

Figure 1 for AfroDigits: A Community-Driven Spoken Digit Dataset for African Languages
Figure 2 for AfroDigits: A Community-Driven Spoken Digit Dataset for African Languages
Figure 3 for AfroDigits: A Community-Driven Spoken Digit Dataset for African Languages
Figure 4 for AfroDigits: A Community-Driven Spoken Digit Dataset for African Languages

The advancement of speech technologies has been remarkable, yet its integration with African languages remains limited due to the scarcity of African speech corpora. To address this issue, we present AfroDigits, a minimalist, community-driven dataset of spoken digits for African languages, currently covering 38 African languages. As a demonstration of the practical applications of AfroDigits, we conduct audio digit classification experiments on six African languages [Igbo (ibo), Yoruba (yor), Rundi (run), Oshiwambo (kua), Shona (sna), and Oromo (gax)] using the Wav2Vec2.0-Large and XLS-R models. Our experiments reveal a useful insight on the effect of mixing African speech corpora during finetuning. AfroDigits is the first published audio digit dataset for African languages and we believe it will, among other things, pave the way for Afro-centric speech applications such as the recognition of telephone numbers, and street numbers. We release the dataset and platform publicly at https://huggingface.co/datasets/chrisjay/crowd-speech-africa and https://huggingface.co/spaces/chrisjay/afro-speech respectively.

* Accepted to the AfricaNLP Workshop at ICLR 2023 
Viaarxiv icon

Adapting to the Low-Resource Double-Bind: Investigating Low-Compute Methods on Low-Resource African Languages

Mar 29, 2023
Colin Leong, Herumb Shandilya, Bonaventure F. P. Dossou, Atnafu Lambebo Tonja, Joel Mathew, Abdul-Hakeem Omotayo, Oreen Yousuf, Zainab Akinjobi, Chris Chinenye Emezue, Shamsudeen Muhammad, Steven Kolawole, Younwoo Choi, Tosin Adewumi

Figure 1 for Adapting to the Low-Resource Double-Bind: Investigating Low-Compute Methods on Low-Resource African Languages
Figure 2 for Adapting to the Low-Resource Double-Bind: Investigating Low-Compute Methods on Low-Resource African Languages

Many natural language processing (NLP) tasks make use of massively pre-trained language models, which are computationally expensive. However, access to high computational resources added to the issue of data scarcity of African languages constitutes a real barrier to research experiments on these languages. In this work, we explore the applicability of low-compute approaches such as language adapters in the context of this low-resource double-bind. We intend to answer the following question: do language adapters allow those who are doubly bound by data and compute to practically build useful models? Through fine-tuning experiments on African languages, we evaluate their effectiveness as cost-effective approaches to low-resource African NLP. Using solely free compute resources, our results show that language adapters achieve comparable performances to massive pre-trained language models which are heavy on computational resources. This opens the door to further experimentation and exploration on full-extent of language adapters capacities.

* Accepted to AfricaNLP workshop at ICLR2023 
Viaarxiv icon