Progress in Multilingual Speech Recognition for Low Resource Languages Kurmanji Kurdish, Cree and Inuktut

Vishwa Gupta, Gilles Boulianne


Abstract
This contribution presents our efforts to develop the automatic speech recognition (ASR) systems for three low resource languages: Kurmanji Kurdish, Cree and Inuktut. As a first step, we generate multilingual models from acoustic training data from 12 different languages in the hybrid DNN/HMM framework. We explore different strategies for combining the phones from different languages: either keep the phone labels separate for each language or merge the common phones. For Kurmanji Kurdish and Inuktut, keeping the phones separate gives much lower word error rate (WER), while merging phones gives lower WER for Cree. These WER are lower than training the acoustic models separately for each language. We also compare two different DNN architectures: factored time delay neural network (TDNN-F), and bidirectional long short-term memory (BLSTM) acoustic models. The TDNN-F acoustic models give significantly lower WER for Kurmanji Kurdish and Cree, while BLSTM acoustic models give significantly lower WER for Inuktut. We also show that for each language, training multilingual acoustic models by one more epoch with acoustic data from that language reduces the WER significantly. We also added 512-dimensional embedding features from cross-lingual pre-trained wav2vec2.0 XLSR-53 models, but they lead to only a small reduction in WER.
Anthology ID:
2022.lrec-1.689
Volume:
Proceedings of the Thirteenth Language Resources and Evaluation Conference
Month:
June
Year:
2022
Address:
Marseille, France
Venue:
LREC
SIG:
Publisher:
European Language Resources Association
Note:
Pages:
6420–6428
Language:
URL:
https://aclanthology.org/2022.lrec-1.689
DOI:
Bibkey:
Cite (ACL):
Vishwa Gupta and Gilles Boulianne. 2022. Progress in Multilingual Speech Recognition for Low Resource Languages Kurmanji Kurdish, Cree and Inuktut. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 6420–6428, Marseille, France. European Language Resources Association.
Cite (Informal):
Progress in Multilingual Speech Recognition for Low Resource Languages Kurmanji Kurdish, Cree and Inuktut (Gupta & Boulianne, LREC 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.lrec-1.689.pdf