28 citations · 93 across the 11 of their papers we have counts for
12 papers
CIViC: Evidence Gates for Audio-Conditioned Visual Prediction on Proxy Tasks
Mengzhe Geng, Max W. Y. Lam, Yuewen Cao +4
Removing audio can shift a visual predictor's output without showing whether the task uses the intended audio information. We introduce Conditional Input and Visual Interpretation…
Efficient Neural Music Generation
Max W. Y. Lam, Qiao Tian, Tang Li +10
Recent progress in music generation has been remarkably advanced by the state-of-the-art MusicLM, which comprises a hierarchy of three LMs, respectively, for semantic, coarse acous…
Diverse and Expressive Speech Prosody Prediction with Denoising Diffusion Probabilistic Model
Xiang Li, Songxiang Liu, Max W. Y. Lam +3
Expressive human speech generally abounds with rich and flexible speech prosody variations. The speech prosody predictors in existing expressive speech synthesis methods mostly pro…
FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesis
Rongjie Huang, Max W. Y. Lam, Jun Wang +4
Denoising diffusion probabilistic models (DDPMs) have recently achieved leading performances in many generative tasks. However, the inherited iterative sampling process costs hinde…
BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech Synthesis
Max W. Y. Lam, Jun Wang, Dan Su +1
Diffusion probabilistic models (DPMs) and their extensions have emerged as competitive generative models yet confront challenges of efficient sampling. We propose a new bilateral d…
Bilateral Denoising Diffusion Models
Max W. Y. Lam, Jun Wang, Rongjie Huang +2
Denoising diffusion probabilistic models (DDPMs) have emerged as competitive generative models yet brought challenges to efficient sampling. In this paper, we propose novel bilater…
Raw Waveform Encoder with Multi-Scale Globally Attentive Locally Recurrent Networks for End-to-End Speech Recognition
Max W. Y. Lam, Jun Wang, Chao Weng +2
End-to-end speech recognition generally uses hand-engineered acoustic features as input and excludes the feature extraction module from its joint optimization. To extract learnable…
Sandglasset: A Light Multi-Granularity Self-attentive Network For Time-Domain Speech Separation
Max W. Y. Lam, Jun Wang, Dan Su +1
One of the leading single-channel speech separation (SS) models is based on a TasNet with a dual-path segmentation technique, where the size of each segment remains unchanged throu…
Tune-In: Training Under Negative Environments with Interference for Attention Networks Simulating Cocktail Party Effect
Jun Wang, Max W. Y. Lam, Dan Su +1
We study the cocktail party problem and propose a novel attention network called Tune-In, abbreviated for training under negative environments with interference. It firstly learns…
Contrastive Separative Coding for Self-supervised Representation Learning
Jun Wang, Max W. Y. Lam, Dan Su +1
To extract robust deep representations from long sequential modeling of speech data, we propose a self-supervised learning approach, namely Contrastive Separative Coding (CSC). Our…
Effective Low-Cost Time-Domain Audio Separation Using Globally Attentive Locally Recurrent Networks
Max W. Y. Lam, Jun Wang, Dan Su +1
Recent research on the time-domain audio separation networks (TasNets) has brought great success to speech separation. Nevertheless, conventional TasNets struggle to satisfy the me…
Mixup-breakdown: a consistency training method for improving generalization of speech separation models
Max W. Y. Lam, Jun Wang, Dan Su +1
Deep-learning based speech separation models confront poor generalization problem that even the state-of-the-art models could abruptly fail when evaluating them in mismatch conditi…