Audio-to-Intent Using Acoustic-Textual Subword Representations from End-to-End ASR-Reference-Cited by-同舟云学术

登录注册会员服务联系我们

Audio-to-Intent Using Acoustic-Textual Subword Representations from End-to-End ASR

Published:2023-06-04 Issue: Volume: Page:
ISSN:
Container-title:ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
language:
Short-container-title:

Author:

Dighe Pranay¹,Nayak Prateeth¹,Rudovic Oggi¹,Marchi Erik¹,Niu Xiaochuan¹,Tewfik Ahmed¹

Affiliation:

1. Apple

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/10094559/10094560/10096510.pdf?arnumber=10096510

Reference26 articles.

1. Word Order does not Matter for Speech Recognition

2. Device-directed Utterance Detection

3. SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing

4. Efficient estimation of word representations in vector space;mikolov;Proceedings of Workshop at ICLR,2013

5. Complementary Language Model and Parallel Bi-LRNN for False Trigger Mitigation

Cited by 2 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. A Multimodal Approach to Device-Directed Speech Detection with Large Language Models;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

2. Exploring the Viability of Synthetic Audio Data for Audio-Based Dialogue State Tracking;2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU);2023-12-16

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线，采集、加工和组织学术论文而形成的新型学术文献查询和分析系统，可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容，当前同舟云学术共收录了国内外主流学术期刊6万余种，收集的期刊论文及会议论文总量共计约1.5亿篇，并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询！咨询电话：010-8811{复制后删除}0370

www.globalauthorid.com

TOP