Search Results for author:
Found 8 papers, 2 papers with code
Optimized Tokenization for Transcribed Error Correction
The challenges facing speech recognition systems, such as variations in pronunciations, adverse audio conditions, and the scarcity of labeled data, emphasize the necessity for a post-processing step that corrects recurring errors.
Don't Be So Sure! Boosting ASR Decoding via Confidence Relaxation
One prominent speech recognition decoding heuristic is beam search, which seeks the transcript with the greatest likelihood computed using the predicted distribution.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Enhancing Speech Recognition Decoding via Layer Aggregation
Recently proposed speech recognition systems are designed to predict using representations generated by their top layers, employing greedy decoding which isolates each timestep from the rest of the sequence.
Single microphone speaker extraction using unified time-frequency Siamese-Unet
In this paper we present a unified time-frequency method for speaker extraction in clean and noisy conditions.
Speech enhancement with mixture-of-deep-experts with clean clustering pre-training
The experts estimate a mask from the noisy input and the final mask is then obtained as a weighted average of the experts' estimates, with the weights determined by the gating DNN.
Single channel voice separation for unknown number of speakers under reverberant and noisy settings
The proposed approach is composed of several separation heads optimized together with a speaker classification branch.
FCN Approach for Dynamically Locating Multiple Speakers
In this paper, we present a deep neural network-based online multi-speaker localisation algorithm.
Deep Clustering Based on a Mixture of Autoencoders
The optimal clustering is found by minimizing the reconstruction loss of the mixture of autoencoder network.
