Search Results for author:
Found 31 papers, 4 papers with code
VoiceShop: A Unified Speech-to-Speech Framework for Identity-Preserving Zero-Shot Voice Editing
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.
Zero-Shot Accent Conversion using Pseudo Siamese Disentanglement Network
The goal of accent conversion (AC) is to convert the accent of speech into the target accent while preserving the content and speaker identity.
Data-Driven Adaptive Simultaneous Machine Translation
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.
A$^3$T: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and Editing
Recently, speech representation learning has improved many speech-related tasks such as speech recognition, speech classification, and speech-to-text translation.
Direct Simultaneous Speech-to-Text Translation Assisted by Synchronized Streaming ASR
Simultaneous speech-to-text translation is widely useful in many scenarios.
Fused Acoustic and Text Encoding for Multimodal Bilingual Pretraining and Speech Translation
Recently, representation learning for text and speech has successfully improved many language related tasks.
Simultaneous Translation
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.
MAM: Masked Acoustic Modeling for End-to-End Speech-to-Text Translation
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
Improving Simultaneous Translation by Incorporating Pseudo-References with Fewer Reorderings
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.
Fluent and Low-latency Simultaneous Speech-to-Speech Translation with Self-adaptive Training
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.
Opportunistic Decoding with Timely Correction for Simultaneous Translation
Simultaneous translation has many important application scenarios and attracts much attention from both academia and industry recently.
Simultaneous Translation Policies: From Fixed to Adaptive
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.
Incremental Text-to-Speech Synthesis with Prefix-to-Prefix Framework
Text-to-speech synthesis (TTS) has witnessed rapid progress in recent years, where neural methods became capable of producing audios with high naturalness.
Machine Translation in Pronunciation Space
The research in machine translation community focus on translation in text space.
Speculative Beam Search for Simultaneous Translation
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.
Robust Machine Translation with Domain Sensitive Pseudo-Sources: Baidu-OSU WMT19 MT Robustness Shared Task System Report
To make it worse, the amount of social media parallel corpora is extremely limited.
Simultaneous Translation with Flexible Policy via Restricted Imitation Learning
Simultaneous translation is widely useful but remains one of the most difficult tasks in NLP.
Learning to Stop in Structured Prediction for Neural Machine Translation
Beam search optimization resolves many issues in neural machine translation.
STACL: Simultaneous Translation with Implicit Anticipation and Controllable Latency using Prefix-to-Prefix Framework
Simultaneous translation, which translates sentences before they are finished, is useful in many scenarios but is notoriously difficult due to word-order differences.
Robust Neural Machine Translation with Joint Textual and Phonetic Embedding
Neural machine translation (NMT) is notoriously sensitive to noises, but noises are almost inevitable in practice.
When to Finish? Optimal Beam Search for Neural Text Generation (modulo beam size)
In neural text generation such as neural machine translation, summarization, and image captioning, beam search is widely used to improve the output text quality.
Ensemble Sequence Level Training for Multimodal MT: OSU-Baidu WMT18 Multimodal Machine Translation System Report
This paper describes multimodal machine translation systems developed jointly by Oregon State University and Baidu Research for WMT 2018 Shared Task on multimodal translation.
Breaking the Beam Search Curse: A Study of (Re-)Scoring Methods and Stopping Criteria for Neural Machine Translation
Beam search is widely used in neural machine translation, and usually improves translation quality compared to greedy search.
Multi-Reference Training with Pseudo-References for Neural Translation and Text Generation
Neural text generation, including neural machine translation, image captioning, and summarization, has been quite successful recently.
OSU Multimodal Machine Translation System Report
This paper describes Oregon State University's submissions to the shared WMT'17 task "multimodal translation task I".
Group Sparse CNNs for Question Classification with Answer Sets
Question classification is an important task with wide applications.
Jointly Trained Sequential Labeling and Classification by Sparse Attention Neural Networks
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.
Textual Entailment with Structured Attentions and Composition
We show that it is beneficial to extend the attention model to tree nodes between premise and hypothesis.
Classify or Select: Neural Architectures for Extractive Document Summarization
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.
Dependency-based Convolutional Neural Networks for Sentence Embedding
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.
