no code implementations • 10 Apr 2024 • Philip Anastassiou, Zhenyu Tang, Kainan Peng, Dongya Jia, Jiaxin Li, Ming Tu, Yuping Wang, Yuxuan Wang, Mingbo Ma
We present VoiceShop, a novel speech-to-speech framework that can modify multiple attributes of speech, such as age, gender, accent, and speech style, in a single forward pass while preserving the input speaker's timbre.
no code implementations • 12 Dec 2022 • Dongya Jia, Qiao Tian, Kainan Peng, Jiaxin Li, Yuanzhe Chen, Mingbo Ma, Yuping Wang, Yuxuan Wang
The goal of accent conversion (AC) is to convert the accent of speech into the target accent while preserving the content and speaker identity.
no code implementations • 27 Apr 2022 • Guangxu Xun, Mingbo Ma, Yuchen Bian, Xingyu Cai, Jiaji Huang, Renjie Zheng, Junkun Chen, Jiahong Yuan, Kenneth Church, Liang Huang
In simultaneous translation (SimulMT), the most widely used strategy is the wait-k policy thanks to its simplicity and effectiveness in balancing translation quality and latency.
2 code implementations • 18 Mar 2022 • He Bai, Renjie Zheng, Junkun Chen, Xintong Li, Mingbo Ma, Liang Huang
Recently, speech representation learning has improved many speech-related tasks such as speech recognition, speech classification, and speech-to-text translation.
no code implementations • Findings (ACL) 2021 • Junkun Chen, Mingbo Ma, Renjie Zheng, Liang Huang
Simultaneous speech-to-text translation is widely useful in many scenarios.
no code implementations • 10 Feb 2021 • Renjie Zheng, Junkun Chen, Mingbo Ma, Liang Huang
Recently, representation learning for text and speech has successfully improved many language related tasks.
no code implementations • EMNLP 2020 • Liang Huang, Colin Cherry, Mingbo Ma, Naveen Arivazhagan, Zhongjun He
Simultaneous translation, which performs translation concurrently with the source speech, is widely useful in many scenarios such as international conferences, negotiations, press releases, legal proceedings, and medicine.
no code implementations • 22 Oct 2020 • Junkun Chen, Mingbo Ma, Renjie Zheng, Liang Huang
End-to-end Speech-to-text Translation (E2E-ST), which directly translates source language speech to target language text, is widely useful in practice, but traditional cascaded approaches (ASR+MT) often suffer from error propagation in the pipeline.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +4
no code implementations • EMNLP 2021 • Junkun Chen, Renjie Zheng, Atsuhito Kita, Mingbo Ma, Liang Huang
Simultaneous translation is vastly different from full-sentence translation, in the sense that it starts translation before the source sentence ends, with only a few words delay.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Renjie Zheng, Mingbo Ma, Baigong Zheng, Kaibo Liu, Jiahong Yuan, Kenneth Church, Liang Huang
Simultaneous speech-to-speech translation is widely useful but extremely challenging, since it needs to generate target-language speech concurrently with the source-language speech, with only a few seconds delay.
no code implementations • ACL 2020 • Renjie Zheng, Mingbo Ma, Baigong Zheng, Kaibo Liu, Liang Huang
Simultaneous translation has many important application scenarios and attracts much attention from both academia and industry recently.
no code implementations • ACL 2020 • Baigong Zheng, Kaibo Liu, Renjie Zheng, Mingbo Ma, Hairong Liu, Liang Huang
Adaptive policies are better than fixed policies for simultaneous translation, since they can flexibly balance the tradeoff between translation quality and latency based on the current context information.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Mingbo Ma, Baigong Zheng, Kaibo Liu, Renjie Zheng, Hairong Liu, Kainan Peng, Kenneth Church, Liang Huang
Text-to-speech synthesis (TTS) has witnessed rapid progress in recent years, where neural methods became capable of producing audios with high naturalness.
no code implementations • 3 Nov 2019 • Hairong Liu, Mingbo Ma, Liang Huang
The research in machine translation community focus on translation in text space.
no code implementations • IJCNLP 2019 • Renjie Zheng, Mingbo Ma, Baigong Zheng, Liang Huang
Beam search is universally used in full-sentence translation but its application to simultaneous translation remains non-trivial, where output words are committed on the fly.
no code implementations • IJCNLP 2019 • Baigong Zheng, Renjie Zheng, Mingbo Ma, Liang Huang
Simultaneous translation is widely useful but remains challenging.
no code implementations • WS 2019 • Renjie Zheng, Hairong Liu, Mingbo Ma, Baigong Zheng, Liang Huang
To make it worse, the amount of social media parallel corpora is extremely limited.
no code implementations • ACL 2019 • Baigong Zheng, Renjie Zheng, Mingbo Ma, Liang Huang
Simultaneous translation is widely useful but remains one of the most difficult tasks in NLP.
no code implementations • NAACL 2019 • Mingbo Ma, Renjie Zheng, Liang Huang
Beam search optimization resolves many issues in neural machine translation.
3 code implementations • ACL 2019 • Mingbo Ma, Liang Huang, Hao Xiong, Renjie Zheng, Kaibo Liu, Baigong Zheng, Chuanqiang Zhang, Zhongjun He, Hairong Liu, Xing Li, Hua Wu, Haifeng Wang
Simultaneous translation, which translates sentences before they are finished, is useful in many scenarios but is notoriously difficult due to word-order differences.
no code implementations • ACL 2019 • Hairong Liu, Mingbo Ma, Liang Huang, Hao Xiong, Zhongjun He
Neural machine translation (NMT) is notoriously sensitive to noises, but noises are almost inevitable in practice.
no code implementations • EMNLP 2017 • Liang Huang, Kai Zhao, Mingbo Ma
In neural text generation such as neural machine translation, summarization, and image captioning, beam search is widely used to improve the output text quality.
no code implementations • WS 2018 • Renjie Zheng, Yilin Yang, Mingbo Ma, Liang Huang
This paper describes multimodal machine translation systems developed jointly by Oregon State University and Baidu Research for WMT 2018 Shared Task on multimodal translation.
no code implementations • EMNLP 2018 • Yilin Yang, Liang Huang, Mingbo Ma
Beam search is widely used in neural machine translation, and usually improves translation quality compared to greedy search.
no code implementations • EMNLP 2018 • Renjie Zheng, Mingbo Ma, Liang Huang
Neural text generation, including neural machine translation, image captioning, and summarization, has been quite successful recently.
no code implementations • WS 2017 • Mingbo Ma, Dapeng Li, Kai Zhao, Liang Huang
This paper describes Oregon State University's submissions to the shared WMT'17 task "multimodal translation task I".
no code implementations • ACL 2017 • Mingbo Ma, Liang Huang, Bing Xiang, Bo-Wen Zhou
Question classification is an important task with wide applications.
no code implementations • 28 Sep 2017 • Mingbo Ma, Kai Zhao, Liang Huang, Bing Xiang, Bo-Wen Zhou
In order to utilize the potential benefits from their correlations, we propose a jointly trained model for learning the two tasks simultaneously via Long Short-Term Memory (LSTM) networks.
1 code implementation • COLING 2016 • Kai Zhao, Liang Huang, Mingbo Ma
We show that it is beneficial to extend the attention model to tree nodes between premise and hypothesis.
no code implementations • 14 Nov 2016 • Ramesh Nallapati, Bo-Wen Zhou, Mingbo Ma
The Selector architecture, on the other hand, is free to pick one sentence at a time in any arbitrary order to piece together the summary.
1 code implementation • IJCNLP 2015 • Mingbo Ma, Liang Huang, Bing Xiang, Bo-Wen Zhou
In sentence modeling and classification, convolutional neural network approaches have recently achieved state-of-the-art results, but all such efforts process word vectors sequentially and neglect long-distance dependencies.