mlsanityData to 7 Oct 2026

Exploring Teacher-Student Learning Approach for Multi-lingual Speech-to-Intent Classification

arXiv 2109.13486 ↗First posted 28 Sep 2021cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

End-to-end speech-to-intent classification has shown its advantage in harvesting information from both text and speech. In this paper, we study a technique to develop such an end-to-end system that supports multiple languages. To overcome the scarcity of multi-lingual speech corpus, we exploit knowledge from a pre-trained multi-lingual natural language processing model. Multi-lingual bidirectional encoder representations from transformers (mBERT) models are trained on multiple languages and hence expected to perform well in the multi-lingual scenario. In this work, we employ a teacher-student learning approach to sufficiently extract information from an mBERT model to train a multi-lingual speech model. In particular, we use synthesized speech generated from an English-Mandarin text corpus for analysis and training of a multi-lingual intent classification model. We also demonstrate that the teacher-student learning approach obtains an improved performance (91.02%) over the traditional end-to-end (89.40%) intent classification approach in a practical multi-lingual scenario.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 24 of its 35 references that are in the map. First posted on arXiv 28 Sep 2021.

Builds on

24 of 35 references.

References · 24

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  4. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 800
  5. 2019How multilingual is Multilingual BERT?cited by 642
  6. 2019LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speechcited by 639
  7. 2019Unified Vision-Language Pre-Training for Image Captioning and VQAcited by 494
  8. 2019Speech Model Pre-training for End-to-End Spoken Language Understandingcited by 191
  9. 2018Towards end-to-end spoken language understandingcited by 92
  10. 2018From Audio to Semantics: Approaches to end-to-end spoken language understandingcited by 63
  11. 2017Efficiently Trainable Text-to-Speech System Based on Deep Convolutional Networks with Guided Attentioncited by 57
  12. 2015THCHS-30 : A Free Chinese Speech Corpuscited by 43
12 more
  1. 2020End-to-End Neural Transformer Based Spoken Language Understandingcited by 31
  2. 2017Large-Scale Domain Adaptation via Teacher-Student Learningcited by 28
  3. 2021Speech-language Pre-training for End-to-end Spoken Language Understandingcited by 27
  4. 2019Multi-lingual Intent Detection and Slot Filling in a Joint BERT-based Modelcited by 24
  5. 2019Using Speech Synthesis to Train End-to-End Spoken Language Understanding Modelscited by 24
  6. 2020Pretrained Semantic Speech Embeddings for End-to-End Spoken Language Understanding via Cross-Modal Teacher-Student Learningcited by 14
  7. 2021Knowledge Distillation from BERT Transformer to Speech Transformer for Intent Classificationcited by 14
  8. 2018Capsule Networks for Low Resource Spoken Language Understandingcited by 11
  9. 2021Leveraging Acoustic and Linguistic Embeddings from Pretrained speech and language Models for Intent Classificationcited by 11
  10. 2019Building a mixed-lingual neural TTS system with only monolingual datacited by 9
  11. 2019Leveraging Acoustic Cues and Paralinguistic Embeddings to Detect Expression from Voicecited by 7
  12. 2020Multitask Learning with Capsule Networks for Speech-to-Intent Applicationscited by 4

Built on by

Not cited yet.