Search Results for author:
Found 21 papers, 12 papers with code
USM RNN-T model weights binarization
Large-scale universal speech models (USM) are already used in production.
Audio-visual fine-tuning of audio-only ASR models
Audio-visual automatic speech recognition (AV-ASR) models are very effective at reducing word error rates on noisy speech, but require large amounts of transcribed AV training data.
On Robustness to Missing Video for Audiovisual Speech Recognition
Multi-modal models need to be robust: missing video frames should not degrade the performance of an audiovisual model to be worse than that of a single-modality audio-only model.
Conformers are All You Need for Visual Speech Recognition
We achieve a new state-of-the-art of 12. 8% WER for visual speech recognition on the TED LRS3 dataset, which rivals the performance of audio-only models from just four years ago.
Ranked #1 on
Lipreading
on LRS3-TED
(using extra training data)
Transformer-Based Video Front-Ends for Audio-Visual Speech Recognition for Single and Multi-Person Video
We achieve the state of the art performance of the audio-visual recognition on the LRS3-TED after fine-tuning our model (1. 6% WER).
Audio-Visual Speech Recognition
Automatic Speech Recognition
+4
Audio-Visual Speech Recognition is Worth 32$\times$32$\times$8 Voxels
In this work, we propose to replace the 3D convolutional visual front-end with a video transformer front-end.
Audio-Visual Speech Recognition
Automatic Speech Recognition
+5
Accounting for Variance in Machine Learning Benchmarks
Strong empirical evidence that one machine-learning algorithm A outperforms another one B ideally calls for multiple trials optimizing the learning pipeline over sources of variation such as data sampling, data augmentation, parameter initialization, and hyperparameters choices.
Multi-Class Few Shot Learning Task and Controllable Environment
In this paper, we address the task of classifying multiple objects by seeing only a few samples from each category.
Unsupervised adversarial domain adaptation for acoustic scene classification
A general problem in acoustic scene classification task is the mismatched conditions between training and testing data, which significantly reduces the performance of the developed methods on classification accuracy.
Twin Regularization for online speech recognition
Online speech recognition is crucial for developing natural human-machine interfaces.
Fortified Networks: Improving the Robustness of Deep Networks by Modeling the Manifold of Hidden Representations
Deep networks have achieved impressive results across a variety of important tasks.
Towards end-to-end spoken language understanding
Spoken language understanding system is traditionally designed as a pipeline of a number of components.
Natural Language Understanding
Spoken Language Understanding
MaD TwinNet: Masker-Denoiser Architecture with Twin Networks for Monaural Sound Source Separation
Current state of the art (SOTA) results in monaural singing voice separation are obtained with deep learning based methods.
Sound Audio and Speech Processing
Twin Networks: Matching the Future for Sequence Generation
We propose a simple technique for encouraging generative RNNs to plan ahead.
Deep Complex Networks
Despite their attractive properties and potential for opening up entirely new neural architectures, complex-valued deep neural networks have been marginalized due to the absence of the building blocks required to design such models.
Ranked #3 on
Music Transcription
on MusicNet
Invariant Representations for Noisy Speech Recognition
Ensuring such robustness to variability is a challenge in modern day neural network-based ASR systems, especially when all types of variability are not seen during training.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Theano: A Python framework for fast computation of mathematical expressions
Since its introduction, it has been one of the most used CPU and GPU mathematical compilers - especially in the machine learning community - and has shown steady performance improvements.
Task Loss Estimation for Sequence Prediction
Our idea is that this score can be interpreted as an estimate of the task loss, and that the estimation error may be used as a consistent surrogate loss.
End-to-End Attention-based Large Vocabulary Speech Recognition
Many of the current state-of-the-art Large Vocabulary Continuous Speech Recognition Systems (LVCSR) are hybrids of neural networks and Hidden Markov Models (HMMs).
Attention-Based Models for Speech Recognition
Recurrent sequence generators conditioned on input data through an attention mechanism have recently shown very good performance on a range of tasks in- cluding machine translation, handwriting synthesis and image caption gen- eration.
Ranked #17 on
Speech Recognition
on TIMIT
Blocks and Fuel: Frameworks for deep learning
We introduce two Python frameworks to train neural networks on large datasets: Blocks and Fuel.
