27 citations · 57 across the 16 of their papers we have counts for
17 papers
Training Articulatory Inversion Models for Interspeaker Consistency
Charles McGhee, Mark J. F. Gales, Kate M. Knill
Acoustic-to-Articulatory Inversion (AAI) attempts to model the inverse mapping from speech to articulation. Exact articulatory prediction from speech alone may be impossible, as sp…
Assessment of L2 Oral Proficiency using Speech Large Language Models
Rao Ma, Mengjie Qian, Siyuan Tang +3
The growing population of L2 English speakers has increased the demand for developing automatic graders for spoken language assessment (SLA). Historically, statistical models, text…
Scaling and Prompting for Improved End-to-End Spoken Grammatical Error Correction
Mengjie Qian, Rao Ma, Stefano Bannò +2
Spoken Grammatical Error Correction (SGEC) and Feedback (SGECF) are crucial for second language learners, teachers and test takers. Traditional SGEC systems rely on a cascaded pipe…
Speak & Improve Corpus 2025: an L2 English Speech Corpus for Language Assessment and Feedback
Kate Knill, Diane Nicholls, Mark J. F. Gales +2
We introduce the Speak & Improve Corpus 2025, a dataset of L2 learner English data with holistic scores and language error annotation, collected from open (spontaneous) speaking te…
Speak & Improve Challenge 2025: Tasks and Baseline Systems
Mengjie Qian, Kate Knill, Stefano Banno +4
This paper presents the "Speak & Improve Challenge 2025: Spoken Language Assessment and Feedback" -- a challenge associated with the ISCA SLaTE 2025 Workshop. The goal of the chall…
Grammatical Error Feedback: An Implicit Evaluation Approach
Stefano Bannò, Kate Knill, Mark J. F. Gales
Grammatical feedback is crucial for consolidating second language (L2) learning. Most research in computer-assisted language learning has focused on feedback through grammatical er…
Learn and Don't Forget: Adding a New Language to ASR Foundation Models
Mengjie Qian, Siyuan Tang, Rao Ma +2
Foundation ASR models often support many languages, e.g. 100 languages in Whisper. However, there has been limited work on integrating an additional, typically low-resource, langua…
Can GPT-4 do L2 analytic assessment?
Stefano Bannò, Hari Krishna Vydana, Kate M. Knill +1
Automated essay scoring (AES) to evaluate second language (L2) proficiency has been a firmly established technology used in educational contexts for decades. Although holistic scor…
Investigating the Emergent Audio Classification Ability of ASR Foundation Models
Rao Ma, Adian Liusie, Mark J. F. Gales +1
Text and vision foundation models can perform many tasks in a zero-shot setting, a desirable property that enables these systems to be applied in general and low-resource settings.…
Towards End-to-End Spoken Grammatical Error Correction
Stefano Bannò, Rao Ma, Mengjie Qian +2
Grammatical feedback is crucial for L2 learners, teachers, and testers. Spoken grammatical error correction (GEC) aims to supply feedback to L2 learners on their use of grammar whe…
Zero-shot Audio Topic Reranking using Large Language Models
Mengjie Qian, Rao Ma, Adian Liusie +3
Multimodal Video Search by Examples (MVSE) investigates using video clips as the query term for information retrieval, rather than the more traditional text query. This enables far…
Adapting an ASR Foundation Model for Spoken Language Assessment
Rao Ma, Mengjie Qian, Mark J. F. Gales +1
A crucial part of an accurate and reliable spoken language assessment system is the underlying ASR model. Recently, large-scale pre-trained ASR foundation models such as Whisper ha…
Can Generative Large Language Models Perform ASR Error Correction?
Rao Ma, Mengjie Qian, Potsawee Manakul +2
ASR error correction is an interesting option for post processing speech recognition system outputs. These error correction models are usually trained in a supervised fashion using…
Analysis of the Cambridge Multiple-Choice Questions Reading Dataset with a Focus on Candidate Response Distribution
Adian Liusie, Vatsal Raina, Andrew Mullooly +2
Multiple choice exams are widely used to assess candidates across a diverse range of domains and tasks. To moderate question quality, newly proposed questions often pass through pr…
Adapting an Unadaptable ASR System
Rao Ma, Mengjie Qian, Mark J. F. Gales +1
As speech recognition model sizes and training data requirements grow, it is increasingly common for systems to only be available via APIs from online service providers rather than…
N-best T5: Robust ASR Error Correction using Multiple Input Hypotheses and Constrained Decoding Space
Rao Ma, Mark J. F. Gales, Kate M. Knill +1
Error correction models form an important part of Automatic Speech Recognition (ASR) post-processing to improve the readability and quality of transcriptions. Most prior works use…
L2 proficiency assessment using self-supervised speech representations
Stefano Bannò, Kate M. Knill, Marco Matassoni +2
There has been a growing demand for automated spoken language assessment systems in recent years. A standard pipeline for this process is to start with a speech recognition system…