UnMute

The Research

UnMute is a collaborative EPSRC-funded project between the University of Edinburgh, Swansea University, Translators Without Borders and Auris Tech, aiming to address the limitations of today's speech and voice-based interactions and open up intelligent interfaces to the currently digitally ‘unheard’.

While state-of-the-art natural language systems are beginning to address the needs of “conventional” users (i.e., those who speak a widely spoken and written language; and who have relatively high degrees of literacy, exposure to digital interactions and other resources), there are many hundreds millions of people who are being excluded globally. Paradoxically, these users who have resource constraints (such as low digital and textual literacy) could be the ones to most benefit from advances in speech-based interactive systems, opening up economic, social and educational possibilities that are currently unmet.

In advancing this area of research, we have produced a toolkit and blueprint that can be used by many other low or zero-resource language communities, worldwide.

Publications

• Cultivating Spoken Language Technologies for Unwritten Languages. Reitmaier, T. Raju, D. Klejch, O. Wallington, E. Markl, N. Pearson, J. Jones, M. Bell, P. Robinson. S., CHI 2024
• Speech Collage: Code-Switched Audio Generation by Collaging Monolingual Corpora. Hussein, A., Zeinali, D., Klejch, O., Wiesner, M., Yan, B., Chowdhury, S., Ali, A., Watanabe, S. & Khudanpur, S., ICASSP 2024.
• Comparing Self-Supervised Pre-Training and Semi-Supervised Training for Speech Recognition in Languages with Weak Language Models. Lam-Yee-Mui, L.-M., Ondel Yang, L. & Klejch, O., Interspeech 2023, pp. 87-91.
• Acoustic Word Embeddings for Untranscribed Target Languages with Continued Pretraining and Learned Pooling. Sanabria, R., Klejch, O., Tang, H. & Goldwater, S., Interspeech 2023, pp. 406-410.
• Automatic transcription and (de)standardisation. Markl, N., Wallington, E., Klejch, O., Reitmaier, T., Bailey, G., Pearson, J., Jones, M., Robinson, S. & Bell, P., SIGUL 2023.
• The Edinburgh International Accents of English Corpus: Towards the Democratization of English ASR. Sanabria, R., Bogoychev, N., Markl, M., Carmantini, A., Klejch, O. & Bell, P., ICASSP 2023.
• Towards Zero-Shot Code-Switched Speech Recognition. Yan, B., Wiesner, M., Klejch, O., Jyothi, P. & Watanabe, S., ICASSP 2023.
• Situating Automatic Speech Recognition Development within Communities of Under-heard Language Speakers. Reitmaier, T., Wallington, E., Raju, D. K., Klejch, O., Pearson, J., Jones, M., Bell, P. & Robinson, S., CHI 2023, Article 406.
• Deciphering Speech: a Zero-Resource Approach to Cross-Lingual Transfer in ASR. Klejch, O., Wallington, E. & Bell, P., Interspeech 2022, pp. 2888-2292.
• Opportunities and Challenges of Automatic Speech Recognition Systems for Low-Resource Language Speakers. Reitmaier, T., Wallington, E., Kalarikalayil Raju, D. K., Klejch, O., Pearson, J., Jones, M., Bell, P. & Robinson, S., CHI 2022, Article 299.
• Can’t Touch This: Rethinking Public Technology in a COVID-19 Era. Pearson, K., Bailey, G., Robinson, S., Jones, M., Owen, T., Reitmaier, T., Steer, C., Carter, A., Sahoo, D. R., Raju, D. K., CHI 2022, Article 401.
• The CSTR System for Multilingual and Code-Switching ASR Challenges for Low Resource Indian Languages. Klejch, O., Wallington, E. & Bell, P., Interspeech 2021, pp. 2881-2885.
• On the Learning Dynamics of Semi-Supervised Training for ASR. Wallington, E., Kershenbaum, B., Bell, P. & Klejch, O., Interspeech 2021, pp. 716-720