Search Results for author:
Found 11 papers, 1 papers with code
On-Device Constrained Self-Supervised Speech Representation Learning for Keyword Spotting via Knowledge Distillation
Our approach used a teacher-student framework to transfer knowledge from a larger, more complex model to a smaller, light-weight model using dual-view cross-correlation distillation and the teacher's codebook as learning objectives.
Self-supervised speech representation learning for keyword-spotting with light-weight transformers
Self-supervised speech representation learning (S3RL) is revolutionizing the way we leverage the ever-growing availability of data.
Progressive Learning for Stabilizing Label Selection in Speech Separation with Mapping-based Method
We investigate the use of the mapping-based method in the time domain and show that it can perform better on a large training set than the masking-based method.
Recurrent Distillation based Crowd Counting
Besides, leveraging our density map generation method, we propose an iterative distillation algorithm to progressively enhance our model with identical network structures, without significantly sacrificing the dimension of the output density maps.
A Monaural Speech Enhancement Method for Robust Small-Footprint Keyword Spotting
To improve the robustness, a speech enhancement front-end is involved.
RHR-Net: A Residual Hourglass Recurrent Neural Network for Speech Enhancement
Most current speech enhancement models use spectrogram features that require an expensive transformation and result in phase information loss.
Hybrid Attention based Multimodal Network for Spoken Language Classification
The proposed hybrid attention architecture helps the system focus on learning informative representations for both modality-specific feature extraction and model fusion.
Multimodal Affective Analysis Using Hierarchical Attention Strategy with Word-Level Alignment
Multimodal affective computing, learning to recognize and interpret human affects and subjective information from multiple data sources, is still challenging because: (i) it is hard to extract informative features to represent human affects from heterogeneous inputs; (ii) current fusion strategies only fuse different modalities at abstract level, ignoring time-dependent interactions between modalities.
Deep Multimodal Learning for Emotion Recognition in Spoken Language
In this paper, we present a novel deep multimodal framework to predict human emotions based on sentence-level spoken language.
Generalizing GANs: A Turing Perspective
In this paper we examine how these algorithms relate to the Turing test, and derive what - from a Turing perspective - can be considered their defining features.
Progress Estimation and Phase Detection for Sequential Processes
For the Olympic swimming dataset, our system achieved an accuracy of 88%, an F1-score of 0. 58, a completeness estimation error of 6. 3% and a remaining-time estimation error of 2. 9 minutes.
