Most languages of the world are “oral”: they are not traditionally written and even if an alphabet exists, the community doesn’t usually use it. Hence, building NLP systems that can directly operate on speech input is paramount. At GMU NLP we work on speech transcription (ASR) and translation, as well as on building multilingual ASR systems for under-served langauges.
- BembaSpeech: A Speech Recognition Corpus for the Bemba Language
- Leveraging Translations for Speech Transcription in Low-resource Settings
- An Attentional Model for Speech Translation Without Transcription
- An Unsupervised Probability Model for Speech-to-Translation Alignment of Low-Resource Languages