Neufa: Neural Network Based End-to-End Forced Alignment with Bidirectional Attention Mechanism-Reference-Cited by-同舟云学术

Neufa: Neural Network Based End-to-End Forced Alignment with Bidirectional Attention Mechanism

Published:2022-05-23 Issue: Volume: Page:
ISSN:
Container-title:ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
language:
Short-container-title:

Author:

Li Jingbei¹,Meng Yi¹,Wu Zhiyong¹,Meng Helen²,Tian Qiao³,Wang Yuping³,Wang Yuxuan³

Affiliation:

1. Tsinghua University,Shenzhen International Graduate School,Shenzhen,China

2. The Chinese University of Hong Kong,China

3. ByteDance,Shanghai,China

Funder

National Natural Science Foundation of China

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/9745891/9746004/09747085.pdf?arnumber=9747085

Reference23 articles.

1. Conformer: Convolution-augmentedTransformerforSpeechRecognition;gulati,2020

2. Tacotron: Towards End-to-End Speech Synthesis;wang,2017

3. Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions;shen,2017

4. FastSpeech: fast, robust and controllable text to speech;ren;Proceedings of the 33rd International Conference on Neural Information Processing Systems,2019

5. Attention is All you Need;vaswani;Advances in Neural IInformation Processing Systems,2017

Cited by 6 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. Joint Multiscale Cross-Lingual Speaking Style Transfer With Bidirectional Attention Mechanism for Automatic Dubbing;IEEE/ACM Transactions on Audio, Speech, and Language Processing;2024

2. Bi-directional attention based RGB-D fusion for category-level object pose and shape estimation;Multimedia Tools and Applications;2023-11-11

3. Phoneme-to-Audio Forced Alignment with Basic Syllable Types and Broad Phonetic Classes;2023 6th International Conference on Information Communication and Signal Processing (ICICSP);2023-09-23

4. Speech-Text Based Multi-Modal Training with Bidirectional Attention for Improved Speech Recognition;ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2023-06-04

5. Achieving Timestamp Prediction While Recognizing with Non-autoregressive End-to-End ASR Model;Communications in Computer and Information Science;2023