End-to-End Spoken Language Understanding Without Full Transcripts

• URL: http://arxiv.org/abs/2009.14386v1
• Date: Wed, 30 Sep 2020 01:54:13 GMT
• Title: End-to-End Spoken Language Understanding Without Full Transcripts
• Authors: Hong-Kwang J. Kuo, Zolt\'an T\"uske, Samuel Thomas, Yinghui Huang, Kartik Audhkhasi, Brian Kingsbury, Gakuto Kurata, Zvi Kons, Ron Hoory, and Luis Lastras
• Abstract summary: We develop end-to-end (E2E) spoken language understanding systems that directly convert speech input to semantic entities. We create two types of such speech-to-entities models, a CTC model and an attention-based encoder-decoder model. For our speech-to-entities experiments on the ATIS corpus, both the CTC and attention models showed impressive ability to skip non-entity words.
• Score: 38.19173637496798
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: An essential component of spoken language understanding (SLU) is slot filling: representing the meaning of a spoken utterance using semantic entity labels. In this paper, we develop end-to-end (E2E) spoken language understanding systems that directly convert speech input to semantic entities and investigate if these E2E SLU models can be trained solely on semantic entity annotations without word-for-word transcripts. Training such models is very useful as they can drastically reduce the cost of data collection. We created two types of such speech-to-entities models, a CTC model and an attention-based encoder-decoder model, by adapting models trained originally for speech recognition. Given that our experiments involve speech input, these systems need to recognize both the entity label and words representing the entity value correctly. For our speech-to-entities experiments on the ATIS corpus, both the CTC and attention models showed impressive ability to skip non-entity words: there was little degradation when trained on just entities versus full transcripts. We also explored the scenario where the entities are in an order not necessarily related to spoken order in the utterance. With its ability to do re-ordering, the attention model did remarkably well, achieving only about 2% degradation in speech-to-bag-of-entities F1 score.

Related papers

• Introducing Semantics into Speech Encoders [91.37001512418111]
  We propose an unsupervised way of incorporating semantic information from large language models into self-supervised speech encoders without labeled audio transcriptions. Our approach achieves similar performance as supervised methods trained on over 100 hours of labeled audio transcripts.
  arXiv  Detail & Related papers  (2022-11-15T18:44:28Z)
• Bootstrapping meaning through listening: Unsupervised learning of spoken sentence embeddings [4.582129557845177]
  This study tackles the unsupervised learning of semantic representations for spoken utterances. We propose WavEmbed, a sequential autoencoder that predicts hidden units from a dense representation of speech. We also propose S-HuBERT to induce meaning through knowledge distillation.
  arXiv  Detail & Related papers  (2022-10-23T21:16:09Z)
• Wav2Seq: Pre-training Speech-to-Text Encoder-Decoder Models Using Pseudo Languages [58.43299730989809]
  We introduce Wav2Seq, the first self-supervised approach to pre-train both parts of encoder-decoder models for speech data. We induce a pseudo language as a compact discrete representation, and formulate a self-supervised pseudo speech recognition task. This process stands on its own, or can be applied as low-cost second-stage pre-training.
  arXiv  Detail & Related papers  (2022-05-02T17:59:02Z)
• Improving End-to-End Models for Set Prediction in Spoken Language Understanding [26.781489293420055]
  We propose a novel data augmentation technique along with an implicit attention based alignment method to infer the spoken order. F1 scores significantly increased by more than 11% for RNN-T and about 2% for attention based encoder-decoder SLU models, outperforming previously reported results.
  arXiv  Detail & Related papers  (2022-01-28T13:23:17Z)
• Towards Language Modelling in the Speech Domain Using Sub-word Linguistic Units [56.52704348773307]
  We propose a novel LSTM-based generative speech LM based on linguistic units including syllables and phonemes. With a limited dataset, orders of magnitude smaller than that required by contemporary generative models, our model closely approximates babbling speech. We show the effect of training with auxiliary text LMs, multitask learning objectives, and auxiliary articulatory features.
  arXiv  Detail & Related papers  (2021-10-31T22:48:30Z)
• Speech-language Pre-training for End-to-end Spoken Language Understanding [18.548949994603213]
  We propose to unify a well-optimized E2E ASR encoder (speech) and a pre-trained language model encoder (language) into a transformer decoder. The experimental results on two public corpora show that our approach to E2E SLU is superior to the conventional cascaded method.
  arXiv  Detail & Related papers  (2021-02-11T21:55:48Z)
• Towards Semi-Supervised Semantics Understanding from Speech [15.672850567147854]
  We propose a framework to learn semantics directly from speech with semi-supervision from transcribed speech to address these. Our framework is built upon pretrained end-to-end (E2E) ASR and self-supervised language models, such as BERT, and fine-tuned on a limited amount of target SLU corpus.
  arXiv  Detail & Related papers  (2020-11-11T01:48:09Z)
• Bridging the Modality Gap for Speech-to-Text Translation [57.47099674461832]
  End-to-end speech translation aims to translate speech in one language into text in another language via an end-to-end way. Most existing methods employ an encoder-decoder structure with a single encoder to learn acoustic representation and semantic information simultaneously. We propose a Speech-to-Text Adaptation for Speech Translation model which aims to improve the end-to-end model performance by bridging the modality gap between speech and text.
  arXiv  Detail & Related papers  (2020-10-28T12:33:04Z)
• Semi-Supervised Spoken Language Understanding via Self-Supervised Speech and Language Model Pretraining [64.35907499990455]
  We propose a framework to learn semantics directly from speech with semi-supervision from transcribed or untranscribed speech. Our framework is built upon pretrained end-to-end (E2E) ASR and self-supervised language models, such as BERT. In parallel, we identify two essential criteria for evaluating SLU models: environmental noise-robustness and E2E semantics evaluation.
  arXiv  Detail & Related papers  (2020-10-26T18:21:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.