Search Results for author: Kazushige Ouchi

Found 7 papers, 3 papers with code

Syntactically Diverse Adversarial Network for Knowledge-Grounded Conversation Generation

no code implementations Findings (EMNLP) 2021 Fuwei Cui, Hui Di, Hongjie Ren, Kazushige Ouchi, Ze Liu, Jinan Xu

Generative conversation systems tend to produce meaningless and generic responses, which significantly reduce the user experience.

Informativeness

Compress Polyphone Pronunciation Prediction Model with Shared Labels

no code implementations CCL 2020 Pengfei Chen, Lina Wang, Hui Di, Kazushige Ouchi, Lvhong Wang

In contrast to existing quantization with low precision data format and projection layer, we propose a novel method based on shared labels, which focuses on compressing the fully-connected layer before Softmax for models with a huge number of labels in TTS polyphone selection.

Quantization

Semi-supervised Sound Event Detection with Local and Global Consistency Regularization

no code implementations15 Sep 2023 Yiming Li, Xiangdong Wang, Hong Liu, Rui Tao, Long Yan, Kazushige Ouchi

Then, the local consistency is adopted to encourage the model to leverage local features for frame-level predictions, and the global consistency is applied to force features to align with global prototypes through a specially designed contrastive loss.

Event Detection Sound Event Detection

Audio Generation with Multiple Conditional Diffusion Model

no code implementations23 Aug 2023 Zhifang Guo, Jianguo Mao, Rui Tao, Long Yan, Kazushige Ouchi, Hong Liu, Xiangdong Wang

To address this issue, we propose a novel model that enhances the controllability of existing pre-trained text-to-audio models by incorporating additional conditions including content (timestamp) and style (pitch contour and energy contour) as supplements to the text.

Audio Generation Language Modelling +1

Couple Learning for semi-supervised sound event detection

2 code implementations12 Oct 2021 Rui Tao, Long Yan, Kazushige Ouchi, Xiangdong Wang

The recently proposed Mean Teacher method, which exploits large-scale unlabeled data in a self-ensembling manner, has achieved state-of-the-art results in several semi-supervised learning benchmarks.

Event Detection Sound Event Detection

Sound Event Detection Transformer: An Event-based End-to-End Model for Sound Event Detection

1 code implementation5 Oct 2021 Zhirong Ye, Xiangdong Wang, Hong Liu, Yueliang Qian, Rui Tao, Long Yan, Kazushige Ouchi

A critical issue with the frame-based model is that it pursues the best frame-level prediction rather than the best event-level prediction.

Audio Tagging Boundary Detection +5

Cannot find the paper you are looking for? You can Submit a new open access paper.