Search Results for author:
Found 14 papers, 2 papers with code
A Multimodal Approach to Device-Directed Speech Detection with Large Language Models
Interactions with virtual assistants typically start with a predefined trigger phrase followed by the user command.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Multimodal Data and Resource Efficient Device-Directed Speech Detection with Large Foundation Models
We compare the proposed system to unimodal baselines and show that the multimodal approach achieves lower equal-error-rates (EERs), while using only a fraction of the training 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.
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
Progressive Voice Trigger Detection: Accuracy vs Latency
We first demonstrate that by including more audio context after a detected trigger phrase, we can indeed get a more accurate decision.
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.
Multi-task Learning for Speaker Verification and Voice Trigger Detection
We train the network in a supervised multi-task learning setup, where the speech transcription branch of the network is trained to minimise a phonetic connectionist temporal classification (CTC) loss while the speaker recognition branch of the network is trained to label the input sequence with the correct label for the speaker.
Multi-task Learning for Voice Trigger Detection
Next, we collect a much smaller dataset of examples that are challenging for the baseline system.
Automatic Environmental Sound Recognition: Performance versus Computational Cost
In the context of the Internet of Things (IoT), sound sensing applications are required to run on embedded platforms where notions of product pricing and form factor impose hard constraints on the available computing power.
Unsupervised Feature Learning Based on Deep Models for Environmental Audio Tagging
For the unsupervised feature learning, we propose to use a symmetric or asymmetric deep de-noising auto-encoder (sDAE or aDAE) to generate new data-driven features from the Mel-Filter Banks (MFBs) features.
Learning to Generate Genotypes with Neural Networks
Neural networks and evolutionary computation have a rich intertwined history.
An End-to-End Neural Network for Polyphonic Piano Music Transcription
We compare performance of the neural network based acoustic models with two popular unsupervised acoustic models.
A Hybrid Recurrent Neural Network For Music Transcription
We investigate the problem of incorporating higher-level symbolic score-like information into Automatic Music Transcription (AMT) systems to improve their performance.
A Denoising Autoencoder that Guides Stochastic Search
An algorithm is described that adaptively learns a non-linear mutation distribution.
