← Authors

Steve Renals

31 papers · 2006–2022 · 5 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🌍 Conference Polyglot (5) 🐝 Cross-Pollinator (13) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (12) 🌈 Renaissance Researcher (5) 🧭 Keyword Pioneer πŸƒ Academic Marathon (16) 🏠 Conference Loyalist (23) 🀝 Dynamic Duo (18) πŸ† Keyword Champion (4) πŸ‘₯ Mega-Team (46) 🧬 Topic Evolution πŸ”₯ Unstoppable (7) πŸ“ˆ Trend Setter πŸš€ Conference Pioneer ⚑ Prolific Year (5) πŸ’Ž Century Club (31) πŸ—ƒοΈ Keyword Collector (50)

Conferences

INTERSPEECH (23) EACL (3) NAACL (3) ACL (1) ICML (1)

Top co-authors

Peter Bell (18) Erfan Loweimi (6) Ahmed Ali (4) Joachim Fainberg (3) Manuel Sam Ribeiro (3) Korin Richmond (3) Ondrej Klejch (3) Zoran Cvetkovic (3) Aciel Eshky (3) Ulrich Germann (2)

Keywords

speech recognition (9) automatic speech recognition (7) word error rate (5) acoustic model (4) convolutional neural network (4) acoustic modeling (4) neural network (3) feature extraction (3) domain adaptation (3) recurrent neural network (3) ultrasound imaging (3) semi-supervised learning (2) speaker attribute (2) bottleneck feature (2) speech therapy (2) language model (2) speaker diarization (2) speaker recognition (2) word alignment (1) semantic parsing (1)

Papers

Investigating the contribution of speaker attributes to speaker separability using disentangled speaker representations INTERSPEECH 2022
Leveraging Speaker Attribute Information Using Multi Task Learning for Speaker Verification and Diarization INTERSPEECH 2021
Speech Acoustic Modelling Using Raw Source and Filter Components INTERSPEECH 2021
Stochastic Attention Head Removal: A Simple and Effective Method for Improving Transformer Based ASR Models INTERSPEECH 2021
European Language Grid: A Joint Platform for the European Language Technology Community EACL 2021
Silent versus Modal Multi-Speaker Speech Recognition from Ultrasound and Video INTERSPEECH 2021
Raw Sign and Magnitude Spectra for Multi-Head Acoustic Modelling INTERSPEECH 2020
Word Error Rate Estimation Without ASR Output: e-WER2 INTERSPEECH 2020
Deep Scattering Power Spectrum Features for Robust Speech Recognition INTERSPEECH 2020
A Deep 2D Convolutional Network for Waveform-Based Speech Recognition INTERSPEECH 2020
On the Robustness and Training Dynamics of Raw Waveform Models INTERSPEECH 2020
On Learning Interpretable CNNs with Parametric Modulated Kernel-Based Filters INTERSPEECH 2019
Ultrasound Tongue Imaging for Diarization and Alignment of Child Speech Therapy Sessions INTERSPEECH 2019
Untranscribed Web Audio for Low Resource Speech Recognition INTERSPEECH 2019
Trainable Dynamic Subsampling for End-to-End Speech Recognition INTERSPEECH 2019
Lattice-Based Lightly-Supervised Acoustic Model Training INTERSPEECH 2019
Synchronising Audio and Ultrasound by Learning Cross-Modal Embeddings INTERSPEECH 2019
Word Error Rate Estimation for Speech Recognition: e-WER ACL 2018
Dynamic Evaluation of Neural Sequence Models ICML 2018
Factorised Representations for Neural Network Adaptation to Diverse Acoustic Environments INTERSPEECH 2017
Hierarchical Recurrent Neural Network for Story Segmentation INTERSPEECH 2017
The SUMMA Platform Prototype EACL 2017
Improving Children’s Speech Recognition Through Out-of-Domain Data Augmentation INTERSPEECH 2016
Segmental Recurrent Neural Networks for End-to-End Speech Recognition INTERSPEECH 2016
Small-Footprint Deep Neural Networks with Highway Connections for Speech Recognition INTERSPEECH 2016
Automatic Dialect Detection in Arabic Broadcast Speech INTERSPEECH 2016
Unsupervised Adaptation of Recurrent Neural Network Language Models INTERSPEECH 2016
Invited Talk: Recognition and Understanding of Meetings NAACL 2010
Automatic Segmentation and Summarization of Meeting Speech NAACL 2007
Automatic Segmentation of Multiparty Dialogue EACL 2006
Incorporating Speaker and Discourse Features into Speech Summarization NAACL 2006