Automatic Speech Recognition and Topic Identification for Almost-Zero-Resource Languages
This addresses the challenge of enabling ASR for low-resource languages in humanitarian assistance and disaster relief settings, representing an incremental improvement over existing methods.
The paper tackles the problem of developing automatic speech recognition (ASR) systems for almost-zero-resource languages by adapting universal phone models with minimal transcribed speech, achieving results that significantly outperform competing approaches on the NIST LoReHLT 2017 Evaluation datasets.
Automatic speech recognition (ASR) systems often need to be developed for extremely low-resource languages to serve end-uses such as audio content categorization and search. While universal phone recognition is natural to consider when no transcribed speech is available to train an ASR system in a language, adapting universal phone models using very small amounts (minutes rather than hours) of transcribed speech also needs to be studied, particularly with state-of-the-art DNN-based acoustic models. The DARPA LORELEI program provides a framework for such very-low-resource ASR studies, and provides an extrinsic metric for evaluating ASR performance in a humanitarian assistance, disaster relief setting. This paper presents our Kaldi-based systems for the program, which employ a universal phone modeling approach to ASR, and describes recipes for very rapid adaptation of this universal ASR system. The results we obtain significantly outperform results obtained by many competing approaches on the NIST LoReHLT 2017 Evaluation datasets.