Search Results for author:
Found 8 papers, 6 papers with code
Separate and Reconstruct: Asymmetric Encoder-Decoder for Speech Separation
To achieve this, an asymmetric strategy is presented in which the encoder and decoder are partitioned to perform distinct processing in separation tasks.
Ranked #1 on
Speech Separation
on WSJ0-2mix
NeXt-TDNN: Modernizing Multi-Scale Temporal Convolution Backbone for Speaker Verification
Meanwhile, in vision tasks, ConvNet structures have been modernized by referring to Transformer, resulting in improved performance.
Statistical Beamformer Exploiting Non-stationarity and Sparsity with Spatially Constrained ICA for Robust Speech Recognition
In this paper, we present a statistical beamforming algorithm as a pre-processing step for robust automatic speech recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Unsupervised Speech Representation Pooling Using Vector Quantization
However, the pooling problem remains; the length of speech representations is inherently variable.
OLKAVS: An Open Large-Scale Korean Audio-Visual Speech Dataset
Inspired by humans comprehending speech in a multi-modal manner, various audio-visual datasets have been constructed.
Distilling a Pretrained Language Model to a Multilingual ASR Model
Hence, we are motivated to distill the rich knowledge embedded inside a well-trained teacher text model to the student speech model.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Unsupervised Speech Domain Adaptation Based on Disentangled Representation Learning for Robust Speech Recognition
The latent variables allow us to convert the domain of speech according to its context and domain representation.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+6
BREN: Body Reflection Essence-Neuter Model for Separation of Reflection Components
We propose a novel reflection color model consisting of body essence and (mixed) neuter, and present an effective method for separating dichromatic reflection components using a single image.
