paper-with-me

Papers

Improving End-to-End Models for Set Prediction in Spoken Language Understanding

2022-01-28 · Hong-Kwang J. Kuo, Zoltan Tuske, Samuel Thomas, Brian Kingsbury, George Saon

The goal of spoken language understanding (SLU) systems is to determine the meaning of the input speech signal, unlike speech recognition which aims to produce verbatim transcripts. Advances in end-to-end (E2E) speech modeling have made it possible to train solely on semantic entities, which are far cheaper to collect than verbatim transcripts. We focus on this set prediction problem, where entity order is unspecified. Using two classes of E2E models, RNN transducers and attention based encoder-decoders, we show that these models work best when the training entity sequence is arranged in spoken order. To improve E2E SLU models when entity spoken order is unknown, 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.

📄 PDF Abstract BibTeX arXiv:2201.12105

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationDecoderspeech-recognitionSpeech RecognitionSpoken Language Understanding

Similar Papers 제목 키워드 기반

What BERT Based Language Models Learn in Spoken Transcripts: An Empirical Study

2021-09-19 · Ayush Kumar, Mukuntha Narayanan Sundararaman, Jithendra Vepa

Language Models (LMs) have been ubiquitously leveraged in various tasks including spoken language understanding (SLU). Spoken language requires careful understanding of speaker interactions, dialog states and speech indu…

Spoken Language Understanding

What BERT Based Language Model Learns in Spoken Transcripts: An Empirical Study

2021-11-01 · EMNLP (BlackboxNLP) 2021 11 · Ayush Kumar, Mukuntha Narayanan Sundararaman, Jithendra Vepa

Language Models (LMs) have been ubiquitously leveraged in various tasks including spoken language understanding (SLU). Spoken language requires careful understanding of speaker interactions, dialog states and speech indu…

Language ModelingLanguage ModellingSpoken Language Understanding

Bidirectional Representations for Low Resource Spoken Language Understanding

2022-11-24 · Quentin Meeus, Marie-Francine Moens, Hugo Van hamme

Most spoken language understanding systems use a pipeline approach composed of an automatic speech recognition interface and a natural language understanding module. This approach forces hard decisions when converting co…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Language ModellingNatural Language Understanding+3

I$^2$KD-SLU: An Intra-Inter Knowledge Distillation Framework for Zero-Shot Cross-Lingual Spoken Language Understanding

2023-10-04 · Tianjun Mao, Chenghong Zhang

Spoken language understanding (SLU) typically includes two subtasks: intent detection and slot filling. Currently, it has achieved great success in high-resource languages, but it still remains challenging in low-resourc…

Intent DetectionKnowledge Distillationslot-fillingSlot Filling+1

A Hierarchical Decoding Model For Spoken Language Understanding From Unaligned Data

2019-04-09 · Zijian Zhao, Su Zhu, Kai Yu

Spoken language understanding (SLU) systems can be trained on two types of labelled data: aligned or unaligned. Unaligned data do not require word by word annotation and is easier to be obtained. In the paper, we focus o…

Spoken Language Understanding