Search Results for author:
Found 16 papers, 7 papers with code
ChipSong: A Controllable Lyric Generation System for Chinese Popular Song
In this work, we take a further step towards satisfying practical demands in Chinese lyric generation from musical short-video creators, in respect of the challenges on songs’ format constraints, creating specific lyrics from open-ended inspiration inputs, and language rhyme grace.
Filter Pruning via Filters Similarity in Consecutive Layers
Filter pruning is widely adopted to compress and accelerate the Convolutional Neural Networks (CNNs), but most previous works ignore the relationship between filters and channels in different layers.
Improving Prosody for Cross-Speaker Style Transfer by Semi-Supervised Style Extractor and Hierarchical Modeling in Speech Synthesis
Cross-speaker style transfer in speech synthesis aims at transferring a style from source speaker to synthesized speech of a target speaker's timbre.
Style-Label-Free: Cross-Speaker Style Transfer by Quantized VAE and Speaker-wise Normalization in Speech Synthesis
In order to improve the style extraction ability of the reference encoder, a style invariant and contrastive data augmentation method is proposed.
Back-Translation-Style Data Augmentation for Mandarin Chinese Polyphone Disambiguation
In this paper we propose a simple back-translation-style data augmentation method for mandarin Chinese polyphone disambiguation, utilizing a large amount of unlabeled text data.
Parameter-Efficient Conformers via Sharing Sparsely-Gated Experts for End-to-End Speech Recognition
Experimental results show that the proposed model achieves competitive performance with 1/3 of the parameters of the encoder, compared with the full-parameter model.
An adaptive graph learning method for automated molecular interactions and properties predictions
In fact, the pursuit of high prediction performance on a limited number of datasets has crystallized their architectures and hyperparameters, making them lose advantage in repurposing to new data generated in drug discovery.
Ranked #1 on
Drug Discovery
on ToxCast (Toxicity Forecaster)
SpeechNAS: Towards Better Trade-off between Latency and Accuracy for Large-Scale Speaker Verification
Recently, x-vector has been a successful and popular approach for speaker verification, which employs a time delay neural network (TDNN) and statistics pooling to extract speaker characterizing embedding from variable-length utterances.
Ranked #1 on
Speaker Verification
on VoxCeleb1
RetroPrime: A Diverse, plausible and Transformer-based method for Single-Step retrosynthesis predictions
RetroPrime achieves the Top-1 accuracy of 64. 8% and 51. 4%, when the reaction type is known and unknown, respectively, in the USPTO-50 K dataset.
Ranked #12 on
Single-step retrosynthesis
on USPTO-50k
Dynamic Multi-scale Convolution for Dialect Identification
To address this issue, we propose a new architecture, named dynamic multi-scale convolution, which consists of dynamic kernel convolution, local multi-scale learning, and global multi-scale pooling.
Multi-Task Audio Source Separation
In detail, the proposed model follows a two-stage pipeline, which separates the three types of audio signals and then performs signal compensation separately.
Ranked #1 on
Multi-task Audio Source Seperation
on MTASS
Audio Source Separation
Multi-task Audio Source Seperation
+3
Gaussian Dynamic Convolution for Efficient Single-Image Segmentation
Furthermore, we also build a Gaussian dynamic pyramid Pooling to show its potential and generality in common semantic segmentation.
a novel cross-lingual voice cloning approach with a few text-free samples
In this paper, we present a cross-lingual voice cloning approach.
The Speechtransformer for Large-scale Mandarin Chinese Speech Recognition
Attention-based sequence-to-sequence architectures have made great progress in the speech recognition task.
Improving Gated Recurrent Unit Based Acoustic Modeling with Batch Normalization and Enlarged Context
The use of future contextual information is typically shown to be helpful for acoustic modeling.
Gated Recurrent Unit Based Acoustic Modeling with Future Context
The use of future contextual information is typically shown to be helpful for acoustic modeling.
