paper-with-me

홈 › Papers

Source and Target Bidirectional Knowledge Distillation for End-to-end Speech Translation

2021-04-13 · NAACL 2021 4 · Hirofumi Inaguma, Tatsuya Kawahara, Shinji Watanabe

A conventional approach to improving the performance of end-to-end speech translation (E2E-ST) models is to leverage the source transcription via pre-training and joint training with automatic speech recognition (ASR) and neural machine translation (NMT) tasks. However, since the input modalities are different, it is difficult to leverage source language text successfully. In this work, we focus on sequence-level knowledge distillation (SeqKD) from external text-based NMT models. To leverage the full potential of the source language information, we propose backward SeqKD, SeqKD from a target-to-source backward NMT model. To this end, we train a bilingual E2E-ST model to predict paraphrased transcriptions as an auxiliary task with a single decoder. The paraphrases are generated from the translations in bitext via back-translation. We further propose bidirectional SeqKD in which SeqKD from both forward and backward NMT models is combined. Experimental evaluations on both autoregressive and non-autoregressive models show that SeqKD in each direction consistently improves the translation performance, and the effectiveness is complementary regardless of the model capacity.

📄 PDF Abstract BibTeX arXiv:2104.06457

Code (0)

등록된 구현이 없습니다.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)DecoderKnowledge DistillationMachine TranslationNMTspeech-recognitionSpeech RecognitionTranslation

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

Knowledge Distillation from BERT Transformer to Speech Transformer for Intent Classification

2021-08-05 · Yidi Jiang, Bidisha Sharma, Maulik Madhavi, Haizhou Li

End-to-end intent classification using speech has numerous advantages compared to the conventional pipeline approach using automatic speech recognition (ASR), followed by natural language processing modules. It attempts …

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Classificationintent-classification+7

End-to-End Speech Translation with Knowledge Distillation

2019-04-17 · Yuchen Liu, Hao Xiong, Zhongjun He, Jiajun Zhang 외

End-to-end speech translation (ST), which directly translates from source language speech into target language text, has attracted intensive attentions in recent years. Compared to conventional pipeline systems, end-to-e…

Knowledge Distillationspeech-recognitionSpeech RecognitionTranslation

Comparison of Soft and Hard Target RNN-T Distillation for Large-scale ASR

2022-10-11 · Dongseong Hwang, Khe Chai Sim, Yu Zhang, Trevor Strohman

Knowledge distillation is an effective machine learning technique to transfer knowledge from a teacher model to a smaller student model, especially with unlabeled data. In this paper, we focus on knowledge distillation f…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Knowledge Distillationspeech-recognition+2

A Study of Non-autoregressive Model for Sequence Generation

2020-04-22 · ACL 2020 6 · Yi Ren, Jinglin Liu, Xu Tan, Zhou Zhao 외

Non-autoregressive (NAR) models generate all the tokens of a sequence in parallel, resulting in faster generation speed compared to their autoregressive (AR) counterparts but at the cost of lower accuracy. Different tech…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Knowledge DistillationMachine Translation+5

Low-resource Low-footprint Wake-word Detection using Knowledge Distillation

2022-07-06 · Arindam Ghosh, Mark Fuhs, Deblin Bagchi, Bahman Farahani 외

As virtual assistants have become more diverse and specialized, so has the demand for application or brand-specific wake words. However, the wake-word-specific datasets typically used to train wake-word detectors are cos…

Knowledge Distillationspeech-recognitionSpeech RecognitionTransfer Learning