Search Results for author:
Found 9 papers, 0 papers with code
Continual Learning for End-to-End ASR by Averaging Domain Experts
Our experiments show that a simple linear interpolation of several models' parameters, each fine-tuned from the same generalist model, results in a single model that performs well on all tested data.
Improving Voice Trigger Detection with Metric Learning
A detector is typically trained on speech data independent of speaker information and used for the voice trigger detection task.
Device-Directed Speech Detection: Regularization via Distillation for Weakly-Supervised Models
We also show that the ensemble of the LatticeRNN and acoustic-distilled models brings further accuracy improvement of 20%.
Multi-task Learning with Cross Attention for Keyword Spotting
In this approach, an output of an acoustic model is split into two branches for the two tasks, one for phoneme transcription trained with the ASR data and one for keyword classification trained with the KWS data.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Streaming Transformer for Hardware Efficient Voice Trigger Detection and False Trigger Mitigation
We propose a streaming transformer (TF) encoder architecture, which progressively processes incoming audio chunks and maintains audio context to perform both VTD and FTM tasks using only acoustic features.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Dynamic curriculum learning via data parameters for noise robust keyword spotting
We propose dynamic curriculum learning via data parameters for noise robust keyword spotting.
Optimize what matters: Training DNN-HMM Keyword Spotting Model Using End Metric
The DNN, in prior methods, is trained independent of the HMM parameters to minimize the cross-entropy loss between the predicted and the ground-truth state probabilities.
Ranked #2 on
Keyword Spotting
on hey Siri
Hybrid Transformer/CTC Networks for Hardware Efficient Voice Triggering
Our baseline is an acoustic model(AM), with BiLSTM layers, trained by minimizing the CTC loss.
Unsupervised Style and Content Separation by Minimizing Mutual Information for Speech Synthesis
We present a method to generate speech from input text and a style vector that is extracted from a reference speech signal in an unsupervised manner, i. e., no style annotation, such as speaker information, is required.
