Search Results for author:
Found 18 papers, 11 papers with code
Flashlight: Enabling Innovation in Tools for Machine Learning
As the computational requirements for machine learning systems and the size and complexity of machine learning frameworks increases, essential framework innovation has become challenging.
Pseudo-Labeling for Massively Multilingual Speech Recognition
Semi-supervised learning through pseudo-labeling has become a staple of state-of-the-art monolingual speech recognition systems.
Word Order Does Not Matter For Speech Recognition
In this paper, we study training of automatic speech recognition system in a weakly supervised setting where the order of words in transcript labels of the audio training data is not known.
Kaizen: Continuously improving teacher using Exponential Moving Average for semi-supervised speech recognition
In this paper, we introduce the Kaizen framework that uses a continuously improving teacher to generate pseudo-labels for semi-supervised speech recognition (ASR).
CAPE: Encoding Relative Positions with Continuous Augmented Positional Embeddings
Absolute or relative positional embeddings are the most popular ways to feed Transformer models with positional information.
Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training
On a large-scale competitive setup, we show that pre-training on unlabeled in-domain data reduces the gap between models trained on in-domain and out-of-domain labeled data by 66%-73%.
Joint Masked CPC and CTC Training for ASR
Self-supervised learning (SSL) has shown promise in learning representations of audio that are useful for automatic speech recognition (ASR).
SlimIPL: Language-Model-Free Iterative Pseudo-Labeling
We improve upon the IPL algorithm: as the model learns, we propose to iteratively re-generate transcriptions with hard labels (the most probable tokens), that is, without a language model.
Self-training and Pre-training are Complementary for Speech Recognition
Self-training and unsupervised pre-training have emerged as effective approaches to improve speech recognition systems using unlabeled data.
Ranked #1 on
Speech Recognition
on LibriSpeech train-clean-100 test-other
(using extra training data)
Rethinking Evaluation in ASR: Are Our Models Robust Enough?
Finally, we show that training a single acoustic model on the most widely-used datasets - combined - reaches competitive performance on both research and real-world benchmarks.
Iterative Pseudo-Labeling for Speech Recognition
In particular, IPL fine-tunes an existing model at each iteration using both labeled data and a subset of unlabeled data.
Ranked #9 on
Speech Recognition
on LibriSpeech test-other
(using extra training data)
Scaling Up Online Speech Recognition Using ConvNets
We design an online end-to-end speech recognition system based on Time-Depth Separable (TDS) convolutions and Connectionist Temporal Classification (CTC).
Libri-Light: A Benchmark for ASR with Limited or No Supervision
Additionally, we provide baseline systems and evaluation metrics working under three settings: (1) the zero resource/unsupervised setting (ABX), (2) the semi-supervised setting (PER, CER) and (3) the distant supervision setting (WER).
Ranked #1 on
Speech Recognition
on Libri-Light test-other
(ABX-across metric)
End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures
We study pseudo-labeling for the semi-supervised training of ResNet, Time-Depth Separable ConvNets, and Transformers for speech recognition, with either CTC or Seq2Seq loss functions.
Ranked #14 on
Speech Recognition
on LibriSpeech test-other
(using extra training data)
Who Needs Words? Lexicon-Free Speech Recognition
Lexicon-free speech recognition naturally deals with the problem of out-of-vocabulary (OOV) words.
InfiniteBoost: building infinite ensembles with gradient descent
In machine learning ensemble methods have demonstrated high accuracy for the variety of problems in different areas.
Inclusive Flavour Tagging Algorithm
The proposed inclusive flavour-tagging algorithm is applicable to tag the flavour of $B$ mesons in any proton-proton experiment.
Reproducible Experiment Platform
Data analysis in fundamental sciences nowadays is an essential process that pushes frontiers of our knowledge and leads to new discoveries.
Data Analysis, Statistics and Probability
