no code implementations • CLTW (LREC) 2022 • Liam Lonergan, Mengjie Qian, Harald Berthelsen, Andy Murphy, Christoph Wendler, Neasa Ní Chiaráin, Christer Gobl, Ailbhe Ní Chasaide
This paper describes ÉIST, automatic speech recogniser for Irish, developed as part of the ongoing ABAIR initiative, combining (1) acoustic models, (2) pronunciation lexicons and (3) language models into a hybrid system.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 2 May 2024 • Liam Lonergan, Mengjie Qian, Neasa Ní Chiaráin, Christer Gobl, Ailbhe Ní Chasaide
This setting is then used to train a model with an E-branchformer encoder and the performance of both architectures are compared.
no code implementations • 9 Nov 2023 • Stefano Bannò, Rao Ma, Mengjie Qian, Kate M. Knill, Mark J. F. Gales
This foundation model can be used to replace the whole framework or part of it, e. g., ASR and disfluency removal.
no code implementations • 14 Sep 2023 • Mengjie Qian, Rao Ma, Adian Liusie, Erfan Loweimi, Kate M. Knill, Mark J. F. Gales
A key element for this process is highly rapid, flexible, search to support large archives, which in MVSE is facilitated by representing video attributes by embeddings.
no code implementations • 14 Jul 2023 • Liam Lonergan, Mengjie Qian, Neasa Ní Chiaráin, Christer Gobl, Ailbhe Ní Chasaide
Motivated by this, the present experiments investigate spoken dialect identification of Irish, with a view to incorporating such a system into the speech recognition pipeline.
no code implementations • 14 Jul 2023 • Liam Lonergan, Mengjie Qian, Neasa Ní Chiaráin, Christer Gobl, Ailbhe Ní Chasaide
ASR systems are generally built for the spoken 'standard', and their performance declines for non-standard dialects/varieties.
no code implementations • 13 Jul 2023 • Rao Ma, Mengjie Qian, Mark J. F. Gales, Kate M. Knill
Additionally, these models have a tendency to skip disfluencies and hesitations in the output.
no code implementations • 9 Jul 2023 • Rao Ma, Mengjie Qian, Potsawee Manakul, Mark Gales, Kate Knill
In this paper we investigate using ChatGPT, a generative LLM, for ASR error correction.
no code implementations • 1 Jun 2023 • Rao Ma, Mengjie Qian, Mark J. F. Gales, Kate M. Knill
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 having direct access to models themselves.
no code implementations • 1 Mar 2023 • Rao Ma, Mark J. F. Gales, Kate M. Knill, Mengjie Qian
Error correction models form an important part of Automatic Speech Recognition (ASR) post-processing to improve the readability and quality of transcriptions.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3