Attention-based E2E network outperforms CTC-based E2E for LID on Hindi-English code-switching corpus and uses attention weights to locate switch boundaries.
Towards End-to-End Code-Switching Speech Recognition
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
abstract
Code-switching speech recognition has attracted an increasing interest recently, but the need for expert linguistic knowledge has always been a big issue. End-to-end automatic speech recognition (ASR) simplifies the building of ASR systems considerably by predicting graphemes or characters directly from acoustic input. In the mean time, the need of expert linguistic knowledge is also eliminated, which makes it an attractive choice for code-switching ASR. This paper presents a hybrid CTC-Attention based end-to-end Mandarin-English code-switching (CS) speech recognition system and studies the effect of hybrid CTC-Attention based models, different modeling units, the inclusion of language identification and different decoding strategies on the task of code-switching ASR. On the SEAME corpus, our system achieves a mixed error rate (MER) of 34.24%.
representative citing papers
Iterative pseudo-labeling on 22.4k hours of unlabeled code-switching audio reduces Mix Error Rate on SEAME devman to 12.88% and devsge to 18.89%.
End-to-end ASR for code-switched Hindi-English with <50 hours of data shows gains from multi-task learning and corpus balancing but underperforms cascaded baselines.
citing papers explorer
-
Joint Language Identification of Code-Switching Speech using Attention based E2E Network
Attention-based E2E network outperforms CTC-based E2E for LID on Hindi-English code-switching corpus and uses attention weights to locate switch boundaries.
-
Progressive Refinement: An Iterative Pseudo-Labeling Approach for Mandarin-English Code-Switching ASR
Iterative pseudo-labeling on 22.4k hours of unlabeled code-switching audio reduces Mix Error Rate on SEAME devman to 12.88% and devsge to 18.89%.
-
End-to-End ASR for Code-switched Hindi-English Speech
End-to-end ASR for code-switched Hindi-English with <50 hours of data shows gains from multi-task learning and corpus balancing but underperforms cascaded baselines.