Abstract
For many languages in the world, not enough (annotated) speech data is available to train an ASR system. Recently, we proposed a cross-language method for training an ASR system using linguistic knowledge and semi-supervised training. Here, we apply this approach to the low-resource language Mboshi. Using an ASR system trained on Dutch, Mboshi acoustic units were first created using cross-language initialization of the phoneme vectors in the output layer. Subsequently, this adapted system was retrained using Mboshi self-labels. Two training methods were investigated: retraining of only the output layer and retraining the full deep neural network (DNN). The resulting Mboshi system was analyzed by investigating per phoneme accuracies, phoneme confusions, and by visualizing the hidden layers of the DNNs prior to and following retraining with the self-labels. Results showed a fairly similar performance for the two training methods but a better phoneme representation for the fully retrained DNN.
Original language | English |
---|---|
Title of host publication | Proceedings of the 6th Workshop on Spoken Language Technologies for Under-resourced Languages (SLTU) |
Subtitle of host publication | 29-31 August 2018, Gurugram, India |
Place of Publication | New Delhi, India |
Publisher | ISCA |
Pages | 167-171 |
Number of pages | 5 |
DOIs | |
Publication status | Published - 2018 |
Event | 6th Workshop on Spoken Language Technologies for Under-resourced Languages - New Delhi, India Duration: 29 Aug 2018 → 31 Aug 2018 |
Workshop
Workshop | 6th Workshop on Spoken Language Technologies for Under-resourced Languages |
---|---|
Abbreviated title | SLTU |
Country/Territory | India |
City | New Delhi |
Period | 29/08/18 → 31/08/18 |
Keywords
- Low-resource automatic speech recognition
- Cross-language adaptation
- n, Semi-supervised training