Search Results for author:
Found 15 papers, 3 papers with code
Weakly-supervised text-to-speech alignment confidence measure
This work proposes a new confidence measure for evaluating text-to-speech alignment systems outputs, which is a key component for many applications, such as semi-automatic corpus anonymization, lips syncing, film dubbing, corpus preparation for speech synthesis and speech recognition acoustic models training.
Do Convolutional Networks need to be Deep for Text Classification ?
We study in this work the importance of depth in convolutional models for text classification, either when character or word inputs are considered.
Multi-task dialog act and sentiment recognition on Mastodon
Both the annotated corpus and deep network are released with an open-source license.
Multi-lingual Dialogue Act Recognition with Deep Learning Methods
Two multi-lingual models are proposed for this task.
On unsupervised-supervised risk and one-class neural networks
Most unsupervised neural networks training methods concern generative models, deep clustering, pretraining or some form of representation learning.
Quality of syntactic implication of RL-based sentence summarization
Work on summarization has explored both reinforcement learning (RL) optimization using ROUGE as a reward and syntax-aware models, such as models those input is enriched with part-of-speech (POS)-tags and dependency information.
Cross-lingual Approaches for Task-specific Dialogue Act Recognition
In this paper we exploit cross-lingual models to enable dialogue act recognition for specific tasks with a small number of annotations.
On the Effects of Using word2vec Representations in Neural Networks for Dialogue Act Recognition
The performance of the proposed approach is consistent across these languages and it is comparable to the state-of-the-art results in English.
Learning representations with end-to-end models for improved remaining useful life prognostics
In this work, we propose an end-to-end deep learning model based on multi-layer perceptron and long short-term memory layers (LSTM) to predict the RUL.
AUTOMATED AUDIO CAPTIONING BY FINE-TUNING BART WITH AUDIOSET TAGS
utomated audio captioning is the multimodal task of describing environmental audio recordings with fluent natural language.
Ranked #7 on
Audio captioning
on AudioCaps
Distinguishing Fictional Voices: a Study of Authorship Verification Models for Quotation Attribution
Recent approaches to automatically detect the speaker of an utterance of direct speech often disregard general information about characters in favor of local information found in the context, such as surrounding mentions of entities.
Unsupervised multiple-choice question generation for out-of-domain Q&A fine-tuning
Pre-trained models have shown very good performances on a number of question answering benchmarks especially when fine-tuned on multiple question answering datasets at once.
