Related papers: SlimIPL: Language-Model-Free Iterative Pseudo-Labe…

Semi-supervised learning (SSL) is an active area of research which aims to utilize unlabelled data in order to improve the accuracy of speech recognition systems. The current study proposes a methodology for integration of two key ideas: 1)…

We address the problem of efficient acoustic-model refinement (continuous retraining) using semi-supervised and active learning for a low resource Indian language, wherein the low resource constraints are having i) a small labeled corpus…

Self-supervised learning (SSL) of speech has shown impressive results in speech-related tasks, particularly in automatic speech recognition (ASR). While most methods employ the output of intermediate layers of the SSL model as real-valued…

Scribble-supervised medical image segmentation tackles the limitation of sparse masks. Conventional approaches alternate between: labeling pseudo-masks and optimizing network parameters. However, such iterative two-stage paradigm is…

Learning representations for individual instances when only bag-level labels are available is a fundamental challenge in multiple instance learning (MIL). Recent works have shown promising results using contrastive self-supervised learning…

Active Learning (AL) and Semi-supervised Learning are two techniques that have been studied to reduce the high cost of deep learning by using a small amount of labeled data and a large amount of unlabeled data. To improve the accuracy of…

In the realms of computer vision, it is evident that deep neural networks perform better in a supervised setting with a large amount of labeled data. The representations learned with supervision are not only of high quality but also helps…

The cost of annotating transcriptions for large speech corpora becomes a bottleneck to maximally enjoy the potential capacity of deep neural network-based automatic speech recognition models. In this paper, we present a new training…

Partial label learning (PLL) aims to solve the problem where each training instance is associated with a set of candidate labels, one of which is the correct label. Most PLL algorithms try to disambiguate the candidate label set, by either…

This paper presents Conformer-1, an end-to-end Automatic Speech Recognition (ASR) model trained on an extensive dataset of 570k hours of speech audio data, 91% of which was acquired from publicly available sources. To achieve this, we…

Detecting medical conditions from speech acoustics is fundamentally a weakly-supervised learning problem: a single, often noisy, session-level label must be linked to nuanced patterns within a long, complex audio recording. This task is…

We propose a novel approach to semi-supervised automatic speech recognition (ASR). We first exploit a large amount of unlabeled audio data via representation learning, where we reconstruct a temporal slice of filterbank features from past…

In this work, we develop new self-learning techniques with an attention-based sequence-to-sequence (seq2seq) model for automatic speech recognition (ASR). For untranscribed speech data, the hypothesis from an ASR system must be used as a…

Despite rapid advances in speech recognition, current models remain brittle to superficial perturbations to their inputs. Small amounts of noise can destroy the performance of an otherwise state-of-the-art model. To harden models against…

The parallel advances in language modeling and speech representation learning have raised the prospect of learning language directly from speech without textual intermediates. This requires extracting semantic representations directly from…

We compare self-supervised representation learning algorithms which either explicitly quantize the audio data or learn representations without quantization. We find the former to be more accurate since it builds a good vocabulary of the…

Fine-tuning pretrained ASR models for specific domains is challenging for small organizations with limited labeled data and computational resources. Here, we explore different data selection pipelines and propose a robust approach that…

Semi-supervised learning, i.e. jointly learning from labeled and unlabeled samples, is an active research topic due to its key role on relaxing human supervision. In the context of image classification, recent advances to learn from…

Modern sensing systems generate large volumes of unlabeled multivariate time-series data. This abundance of unlabeled data makes self-supervised learning (SSL) a natural approach for learning transferable representations. However, most…

In this paper, we present a semi-supervised training technique using pseudo-labeling for end-to-end neural diarization (EEND). The EEND system has shown promising performance compared with traditional clustering-based methods, especially in…