Search Results for author:
Found 60 papers, 23 papers with code
No Need to Talk: Asynchronous Mixture of Language Models
We introduce SmallTalk LM, an innovative method for training a mixture of language models in an almost asynchronous manner.
Denoising LM: Pushing the Limits of Error Correction Models for Speech Recognition
Language models (LMs) have long been used to improve results of automatic speech recognition (ASR) systems, but they are unaware of the errors that ASR systems make.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
AV-CPL: Continuous Pseudo-Labeling for Audio-Visual Speech Recognition
Audio-visual speech contains synchronized audio and visual information that provides cross-modal supervision to learn representations for both automatic speech recognition (ASR) and visual speech recognition (VSR).
Audio-Visual Speech Recognition
Automatic Speech Recognition
+4
Unsupervised ASR via Cross-Lingual Pseudo-Labeling
Here, "unsupervised" means no labeled audio is available for the $\textit{target}$ language.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Continuous Soft Pseudo-Labeling in ASR
Continuous pseudo-labeling (PL) algorithms such as slimIPL have recently emerged as a powerful strategy for semi-supervised learning in speech recognition.
More Speaking or More Speakers?
We perform a systematic analysis on both labeled and unlabeled data by varying the number of speakers while keeping the number of hours fixed and vice versa.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Continuous Pseudo-Labeling from the Start
Nevertheless, these approaches still rely on bootstrapping the ST using an initial supervised learning phase where the model is trained on labeled data alone.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Flashlight: Enabling Innovation in Tools for Machine Learning
This is in part due to the difficulties involved in prototyping new computational paradigms with existing frameworks.
Star Temporal Classification: Sequence Classification with Partially Labeled Data
These experiments show that STC can recover most of the performance of supervised baseline when up to 70% of the labels are missing.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
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.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
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%.
MLS: A Large-Scale Multilingual Dataset for Speech Research
This paper introduces Multilingual LibriSpeech (MLS) dataset, a large multilingual corpus suitable for speech research.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
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).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
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.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
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.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
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)
Massively Multilingual ASR: 50 Languages, 1 Model, 1 Billion Parameters
We study training a single acoustic model for multiple languages with the aim of improving automatic speech recognition (ASR) performance on low-resource languages, and over-all simplifying deployment of ASR systems that support diverse languages.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Unsupervised Cross-lingual Representation Learning for Speech Recognition
This paper presents XLSR which learns cross-lingual speech representations by pretraining a single model from the raw waveform of speech in multiple languages.
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 #13 on
Speech Recognition
on LibriSpeech test-other
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Multi-scale Transformer Language Models
We investigate multi-scale transformer language models that learn representations of text at multiple scales, and present three different architectures that have an inductive bias to handle the hierarchical nature of language.
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-within 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 #19 on
Speech Recognition
on LibriSpeech test-other
(using extra training data)
Word-level Speech Recognition with a Letter to Word Encoder
We propose a direct-to-word sequence model which uses a word network to learn word embeddings from letters.
wav2vec: Unsupervised Pre-training for Speech Recognition
Our experiments on WSJ reduce WER of a strong character-based log-mel filterbank baseline by up to 36% when only a few hours of transcribed data is available.
Ranked #5 on
Speech Recognition
on TIMIT
(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.
Sequence-to-Sequence Speech Recognition with Time-Depth Separable Convolutions
Coupled with a convolutional language model, our time-depth separable convolution architecture improves by more than 22% relative WER over the best previously reported sequence-to-sequence results on the noisy LibriSpeech test set.
A Fully Differentiable Beam Search Decoder
We demonstrate our approach scales by applying it to speech recognition, jointly training acoustic and word-level language models.
wav2letter++: The Fastest Open-source Speech Recognition System
This paper introduces wav2letter++, the fastest open-source deep learning speech recognition framework.
Fully Convolutional Speech Recognition
In this paper we present an alternative approach based solely on convolutional neural networks, leveraging recent advances in acoustic models from the raw waveform and language modeling.
Ranked #3 on
Speech Recognition
on WSJ eval93
To Reverse the Gradient or Not: An Empirical Comparison of Adversarial and Multi-task Learning in Speech Recognition
In multi-task learning, the goal is speaker prediction; we expect a performance improvement with this joint training if the two tasks of speech recognition and speaker recognition share a common set of underlying features.
End-to-End Speech Recognition From the Raw Waveform
In this paper, we study end-to-end systems trained directly from the raw waveform, building on two alternatives for trainable replacements of mel-filterbanks that use a convolutional architecture.
Gated ConvNets for Letter-Based ASR
In this paper we introduce a new speech recognition system, leveraging a simple letter-based ConvNet acoustic model.
Letter-Based Speech Recognition with Gated ConvNets
In the recent literature, "end-to-end" speech systems often refer to letter-based acoustic models trained in a sequence-to-sequence manner, either via a recurrent model or via a structured output learning approach (such as CTC).
Ranked #55 on
Speech Recognition
on LibriSpeech test-clean
Wav2Letter: an End-to-End ConvNet-based Speech Recognition System
This paper presents a simple end-to-end model for speech recognition, combining a convolutional network based acoustic model and a graph decoding.
Neural Network-based Word Alignment through Score Aggregation
We present a simple neural network for word alignment that builds source and target word window representations to compute alignment scores for sentence pairs.
Learning to Refine Object Segments
In this work we propose to augment feedforward nets for object segmentation with a novel top-down refinement approach.
Ranked #4 on
Region Proposal
on COCO test-dev
ProNet: Learning to Propose Object-specific Boxes for Cascaded Neural Networks
This paper aims to classify and locate objects accurately and efficiently, without using bounding box annotations.
Ranked #5 on
Weakly Supervised Object Detection
on MS COCO
Learning to Segment Object Candidates
Recent object detection systems rely on two critical steps: (1) a set of object proposals is predicted as efficiently as possible, and (2) this set of candidate proposals is then passed to an object classifier.
"The Sum of Its Parts": Joint Learning of Word and Phrase Representations with Autoencoders
We evaluate the quality of the word representations on several classical word evaluation tasks, and we introduce a novel task to evaluate the quality of the phrase representations.
Phrase-based Image Captioning
Generating a novel textual description of an image is an interesting problem that connects computer vision and natural language processing.
Simple Image Description Generator via a Linear Phrase-Based Approach
Generating a novel textual description of an image is an interesting problem that connects computer vision and natural language processing.
Learning linearly separable features for speech recognition using convolutional neural networks
This system was shown to yield similar or better performance than HMM/ANN based system on phoneme recognition task and on large scale continuous speech recognition task, using less parameters.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Joint RNN-Based Greedy Parsing and Word Composition
This paper introduces a greedy parser based on neural networks, which leverages a new compositional sub-tree representation.
Video (language) modeling: a baseline for generative models of natural videos
We propose a strong baseline model for unsupervised feature learning using video data.
N-gram-Based Low-Dimensional Representation for Document Classification
The number of features is therefore dramatically reduced and documents can be represented as bag of semantic concepts.
Rehabilitation of Count-based Models for Word Vector Representations
We present a systematic study of the use of the Hellinger distance to extract semantic representations from the word co-occurence statistics of large text corpora.
From Image-level to Pixel-level Labeling with Convolutional Networks
We are interested in inferring object segmentation by leveraging only object class information, and by considering only minimal priors on the object segmentation task.
Word Emdeddings through Hellinger PCA
Word embeddings resulting from neural language models have been shown to be successful for a large variety of NLP tasks.
End-to-end Phoneme Sequence Recognition using Convolutional Neural Networks
Most phoneme recognition state-of-the-art systems rely on a classical neural network classifiers, fed with highly tuned features, such as MFCC or PLP features.
Recurrent Convolutional Neural Networks for Scene Parsing
Scene parsing is a technique that consist on giving a label to all pixels in an image according to the class they belong to.
Estimating Phoneme Class Conditional Probabilities from Raw Speech Signal using Convolutional Neural Networks
Motivated from these studies, in the framework of convolutional neural networks (CNNs), this paper investigates a novel approach, where the input to the ANN is raw speech signal and the output is phoneme class conditional probability estimates.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Natural Language Processing (almost) from Scratch
We propose a unified neural network architecture and learning algorithm that can be applied to various natural language processing tasks including: part-of-speech tagging, chunking, named entity recognition, and semantic role labeling.
Polynomial Semantic Indexing
We present a class of nonlinear (polynomial) models that are discriminatively trained to directly map from the word content in a query-document or document-document pair to a ranking score.
