Search Results for author:
Found 15 papers, 9 papers with code
A Generalized Bandsplit Neural Network for Cinematic Audio Source Separation
Cinematic audio source separation is a relatively new subtask of audio source separation, with the aim of extracting the dialogue, music, and effects stems from their mixture.
ÌròyìnSpeech: A multi-purpose Yorùbá Speech Corpus
To encourage a participatory approach to data creation, we provide 5000 curated sentences to the Mozilla Common Voice platform to crowd-source the recording and validation of Yor\`{u}b\'{a} speech data.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Looking Similar, Sounding Different: Leveraging Counterfactual Cross-Modal Pairs for Audiovisual Representation Learning
We additionally compare this approach to a strong baseline where we remove speech before pretraining, and find that dub-augmented training is more effective, including for paralinguistic and audiovisual tasks where speech removal leads to worse performance.
BibleTTS: a large, high-fidelity, multilingual, and uniquely African speech corpus
BibleTTS is a large, high-quality, open speech dataset for ten languages spoken in Sub-Saharan Africa.
Learning Nigerian accent embeddings from speech: preliminary results based on SautiDB-Naija corpus
We describe how the corpus was created and curated as well as preliminary experiments with accent classification and learning Nigerian accent embeddings.
AVASpeech-SMAD: A Strongly Labelled Speech and Music Activity Detection Dataset with Label Co-Occurrence
We propose a dataset, AVASpeech-SMAD, to assist speech and music activity detection research.
MasakhaNER: Named Entity Recognition for African Languages
We take a step towards addressing the under-representation of the African continent in NLP research by creating the first large publicly available high-quality dataset for named entity recognition (NER) in ten African languages, bringing together a variety of stakeholders.
Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets
With the success of large-scale pre-training and multilingual modeling in Natural Language Processing (NLP), recent years have seen a proliferation of large, web-mined text datasets covering hundreds of languages.
Participatory Research for Low-resourced Machine Translation: A Case Study in African Languages
Research in NLP lacks geographic diversity, and the question of how NLP can be scaled to low-resourced languages has not yet been adequately solved.
Towards Neural Machine Translation for Edoid Languages
Many Nigerian languages have relinquished their previous prestige and purpose in modern society to English and Nigerian Pidgin.
Improving Yorùbá Diacritic Restoration
Yor\`ub\'a is a widely spoken West African language with a writing system rich in orthographic and tonal diacritics.
The Marchex 2018 English Conversational Telephone Speech Recognition System
In this paper, we describe recent performance improvements to the production Marchex speech recognition system for our spontaneous customer-to-business telephone conversations.
Attentive Sequence-to-Sequence Learning for Diacritic Restoration of Yorùbá Language Text
Yor\`ub\'a is a widely spoken West African language with a writing system rich in tonal and orthographic diacritics.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Semi-Supervised Model Training for Unbounded Conversational Speech Recognition
For conversational large-vocabulary continuous speech recognition (LVCSR) tasks, up to about two thousand hours of audio is commonly used to train state of the art models.
