Search Results for author:
Found 12 papers, 2 papers with code
Context-aware Stand-alone Neural Spelling Correction
Existing natural language processing systems are vulnerable to noisy inputs resulting from misspellings.
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.
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.
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.
Exploring Neural Transducers for End-to-End Speech Recognition
In this work, we perform an empirical comparison among the CTC, RNN-Transducer, and attention-based Seq2Seq models for end-to-end speech recognition.
Reducing Bias in Production Speech Models
Replacing hand-engineered pipelines with end-to-end deep learning systems has enabled strong results in applications like speech and object recognition.
Gram-CTC: Automatic Unit Selection and Target Decomposition for Sequence Labelling
These methods suffer from two major drawbacks: 1) the set of basic units is fixed, such as the set of words, characters or phonemes in speech recognition, and 2) the decomposition of target sequences is fixed.
Active Learning for Speech Recognition: the Power of Gradients
For speech recognition, confidence scores and other likelihood-based active learning methods have been shown to be effective.
Robust Clustering as Ensembles of Affinity Relations
In this paper, we regard clustering as ensembles of k-ary affinity relations and clusters correspond to subsets of objects with maximal average affinity relations.
