Search Results for author:
Found 10 papers, 1 papers with code
Two-pass Endpoint Detection for Speech Recognition
Endpoint (EP) detection is a key component of far-field speech recognition systems that assist the user through voice commands.
Adaptive Endpointing with Deep Contextual Multi-armed Bandits
In this paper, we aim to provide a solution for adaptive endpointing by proposing an efficient method for choosing an optimal endpointing configuration given utterance-level audio features in an online setting, while avoiding hyperparameter grid-search.
Reducing Geographic Disparities in Automatic Speech Recognition via Elastic Weight Consolidation
A popular approach is to fine-tune the model with data from regions where the ASR model has a higher word error rate (WER).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
ImportantAug: a data augmentation agent for speech
We introduce ImportantAug, a technique to augment training data for speech classification and recognition models by adding noise to unimportant regions of the speech and not to important regions.
Ranked #1 on
Keyword Spotting
on Google Speech Commands
(Google Speech Command-Musan metric)
Unsupervised Speech Enhancement with speech recognition embedding and disentanglement losses
Our results show that the proposed function effectively improves the speech enhancement performance compared to a baseline trained in a supervised way on the noisy VoxCeleb dataset.
Enhancement of Spatial Clustering-Based Time-Frequency Masks using LSTM Neural Networks
By using LSTMs to enhance spatial clustering based time-frequency masks, we achieve both the signal modeling performance of multiple single-channel LSTM-DNN speech enhancers and the signal separation performance and generality of multi-channel spatial clustering.
Improved MVDR Beamforming Using LSTM Speech Models to Clean Spatial Clustering Masks
Spatial clustering techniques can achieve significant multi-channel noise reduction across relatively arbitrary microphone configurations, but have difficulty incorporating a detailed speech/noise model.
Combining Spatial Clustering with LSTM Speech Models for Multichannel Speech Enhancement
The system is compared to several baselines on the CHiME3 dataset in terms of speech quality predicted by the PESQ algorithm and word error rate of a recognizer trained on mis-matched conditions, in order to focus on generalization.
Large scale evaluation of importance maps in automatic speech recognition
In this paper, we propose a metric that we call the structured saliency benchmark (SSBM) to evaluate importance maps computed for automatic speech recognizers on individual utterances.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
