← Authors

Peter Bell

42 papers · 2012–2026 · 4 conferences · across top CS/AI conferences

Achievements

πŸƒ Academic Marathon (13) 🌍 Conference Polyglot (4) 🐝 Cross-Pollinator (6) 🐣 Hot Topic Early Bird 🌈 Renaissance Researcher (8) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (13) 🧭 Keyword Pioneer 🏠 Conference Loyalist (32) 🀝 Dynamic Duo (18) πŸ”¬ Deep Specialist (10) πŸ‘₯ Mega-Team (46) πŸ† Keyword Champion (8) πŸ”₯ Unstoppable (10) ❓ The Questioner πŸš€ Conference Pioneer ⚑ Prolific Year (8) πŸ’Ž Century Club (41) πŸ—ƒοΈ Keyword Collector (53)

Conferences

INTERSPEECH (32) EACL (6) COLING (3) EMNLP (1)

Top co-authors

Steve Renals (18) Ondrej Klejch (10) Catherine Lai (7) Erfan Loweimi (6) Electra Wallington (5) Jie Chi (5) Joachim Fainberg (5) Sarenne Wallbridge (4) Zoran Cvetkovic (3) Shucong Zhang (2)

Keywords

automatic speech recognition (14) speech recognition (10) acoustic model (8) word error rate (5) language model (4) semi-supervised learning (3) convolutional neural network (3) semi-supervised training (3) spoken dialogue (2) machine translation (2) speech perception (2) recurrent neural network (2) data augmentation (2) dialogue system (2) feature extraction (2) low-resource language (2) domain adaptation (2) cross-lingual transfer (2) acoustic modeling (2) speaker recognition (2)

Papers

Analysing the role of lexical and temporal information in turn-taking through predictability EACL 2026
Spoken Document Retrieval for an Unwritten Language: A Case Study on Gormati EMNLP 2025
LLM-Personalize: Aligning LLM Planners with Human Preferences via Reinforced Self-Training for Housekeeping Robots COLING 2025
Synthesising a Corpus of Gaelic Traditional Narrative with Cross-Lingual Text Expansion COLING 2025
Characterizing code-switching: Applying Linguistic Principles for Metric Assessment and Development INTERSPEECH 2024
Analyzing the Role of Part-of-Speech in Code-Switching: A Corpus-Based Study EACL 2024
Evaluating and reducing the distance between synthetic and real speech distributions INTERSPEECH 2023
Unsupervised Code-switched Text Generation from Parallel Text INTERSPEECH 2023
ASR and Emotional Speech: A Word-Level Investigation of the Mutual Impact of Speech and Emotion Recognition INTERSPEECH 2023
Capturing Formality in Speech Across Domains and Languages INTERSPEECH 2023
Do dialogue representations align with perception? An empirical study EACL 2023
Transfer Learning for Personality Perception via Speech Emotion Recognition INTERSPEECH 2023
Regarding Topology and Variant Frame Rates for Differentiable WFST-based End-to-End ASR INTERSPEECH 2023
Quantifying the perceptual value of lexical and non-lexical channels in speech INTERSPEECH 2023
Deciphering Speech: a Zero-Resource Approach to Cross-Lingual Transfer in ASR INTERSPEECH 2022
Improving Code-switched ASR with Linguistic Information COLING 2022
Investigating perception of spoken dialogue acceptability through surprisal INTERSPEECH 2022
Investigating the contribution of speaker attributes to speaker separability using disentangled speaker representations INTERSPEECH 2022
Segmenting Subtitles for Correcting ASR Segmentation Errors EACL 2021
Speech Acoustic Modelling Using Raw Source and Filter Components INTERSPEECH 2021
Leveraging Speaker Attribute Information Using Multi Task Learning for Speaker Verification and Diarization INTERSPEECH 2021
On the Learning Dynamics of Semi-Supervised Training for ASR INTERSPEECH 2021
It’s Not What You Said, it’s How You Said it: Discriminative Perception of Speech as a Multichannel Communication System INTERSPEECH 2021
Stochastic Attention Head Removal: A Simple and Effective Method for Improving Transformer Based ASR Models INTERSPEECH 2021
The CSTR System for Multilingual and Code-Switching ASR Challenges for Low Resource Indian Languages INTERSPEECH 2021
A Deep 2D Convolutional Network for Waveform-Based Speech Recognition INTERSPEECH 2020
Deep Scattering Power Spectrum Features for Robust Speech Recognition INTERSPEECH 2020
On the Robustness and Training Dynamics of Raw Waveform Models INTERSPEECH 2020
Raw Sign and Magnitude Spectra for Multi-Head Acoustic Modelling INTERSPEECH 2020
Lattice-Based Lightly-Supervised Acoustic Model Training INTERSPEECH 2019
Trainable Dynamic Subsampling for End-to-End Speech Recognition INTERSPEECH 2019
On Learning Interpretable CNNs with Parametric Modulated Kernel-Based Filters INTERSPEECH 2019
Untranscribed Web Audio for Low Resource Speech Recognition INTERSPEECH 2019
Learning to Adapt: A Meta-learning Approach for Speaker Adaptation INTERSPEECH 2018
Factorised Representations for Neural Network Adaptation to Diverse Acoustic Environments INTERSPEECH 2017
The SUMMA Platform Prototype EACL 2017
Hierarchical Recurrent Neural Network for Story Segmentation INTERSPEECH 2017
A System for Real Time Collaborative Transcription Correction INTERSPEECH 2017
Improving Children’s Speech Recognition Through Out-of-Domain Data Augmentation INTERSPEECH 2016
Unsupervised Adaptation of Recurrent Neural Network Language Models INTERSPEECH 2016
Automatic Dialect Detection in Arabic Broadcast Speech INTERSPEECH 2016
Evaluating language understanding accuracy with respect to objective outcomes in a dialogue system EACL 2012