More Speaking or More Speakers?

• URL: http://arxiv.org/abs/2211.00854v1
• Date: Wed, 2 Nov 2022 03:50:40 GMT
• Title: More Speaking or More Speakers?
• Authors: Dan Berrebbi, Ronan Collobert, Navdeep Jaitly, Tatiana Likhomanenko
• Abstract summary: Self-training (ST) and self-supervised learning (SSL) methods have demonstrated strong improvements in automatic speech recognition (ASR) In this work we aim to analyse the effect of numbers of speakers in the training data on a recent SSL algorithm (wav2vec 2.0) and a recent ST algorithm (slimIPL) Our findings suggest that SSL requires a large amount of unlabeled data to produce high accuracy results, while ST requires a sufficient number of speakers in the labelled data, especially in the low-regime setting.
• Score: 17.143456510764576
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Self-training (ST) and self-supervised learning (SSL) methods have demonstrated strong improvements in automatic speech recognition (ASR). In spite of these advances, to the best of our knowledge, there is no analysis of how the composition of the labelled and unlabelled datasets used in these methods affects the results. In this work we aim to analyse the effect of numbers of speakers in the training data on a recent SSL algorithm (wav2vec 2.0), and a recent ST algorithm (slimIPL). 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. Our findings suggest that SSL requires a large amount of unlabeled data to produce high accuracy results, while ST requires a sufficient number of speakers in the labelled data, especially in the low-regime setting. In this manner these two approaches improve supervised learning in different regimes of dataset composition.

Related papers

• Semi-Supervised Cognitive State Classification from Speech with Multi-View Pseudo-Labeling [21.82879779173242]
  The lack of labeled data is a common challenge in speech classification tasks. We propose a Semi-Supervised Learning (SSL) framework, introducing a novel multi-view pseudo-labeling method. We evaluate our SSL framework on emotion recognition and dementia detection tasks.
  arXiv  Detail & Related papers  (2024-09-25T13:51:19Z)
• Performance Analysis of Speech Encoders for Low-Resource SLU and ASR in Tunisian Dialect [11.013934239276036]
  Speech encoders pretrained through self-supervised learning (SSL) have demonstrated remarkable performance in various downstream tasks. This paper contributes by comparing the effectiveness of SSL approaches in the context of the low-resource spoken Tunisian Arabic dialect.
  arXiv  Detail & Related papers  (2024-07-05T14:21:36Z)
• Co-training for Low Resource Scientific Natural Language Inference [65.37685198688538]
  We propose a novel co-training method that assigns weights based on the training dynamics of the classifiers to the distantly supervised labels. By assigning importance weights instead of filtering out examples based on an arbitrary threshold on the predicted confidence, we maximize the usage of automatically labeled data. The proposed method obtains an improvement of 1.5% in Macro F1 over the distant supervision baseline, and substantial improvements over several other strong SSL baselines.
  arXiv  Detail & Related papers  (2024-06-20T18:35:47Z)
• Rethinking Semi-supervised Learning with Language Models [33.70349754359132]
  Semi-supervised learning (SSL) is a popular setting aiming to effectively utilize unlabelled data to improve model performance. There are two popular approaches to make use of unlabelled data: Self-training (ST) and Task-adaptive pre-training (TAPT)
  arXiv  Detail & Related papers  (2023-05-22T13:07:35Z)
• Active Semi-Supervised Learning by Exploring Per-Sample Uncertainty and Consistency [30.94964727745347]
  We propose a method called Active Semi-supervised Learning (ASSL) to improve accuracy of models at a lower cost. ASSL involves more dynamic model updates than Active Learning (AL) due to the use of unlabeled data. ASSL achieved about 5.3 times higher computational efficiency than Semi-supervised Learning (SSL) while achieving the same performance.
  arXiv  Detail & Related papers  (2023-03-15T22:58:23Z)
• A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trends [82.64268080902742]
  Self-supervised learning (SSL) aims to learn discriminative features from unlabeled data without relying on human-annotated labels. SSL has garnered significant attention recently, leading to the development of numerous related algorithms. This paper presents a review of diverse SSL methods, encompassing algorithmic aspects, application domains, three key trends, and open research questions.
  arXiv  Detail & Related papers  (2023-01-13T14:41:05Z)
• Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentation [76.13334392868208]
  Direct speech-to-speech translation (S2ST) models suffer from data scarcity issues. In this work, we explore self-supervised pre-training with unlabeled speech data and data augmentation to tackle this issue.
  arXiv  Detail & Related papers  (2022-04-06T17:59:22Z)
• Augmented Contrastive Self-Supervised Learning for Audio Invariant Representations [28.511060004984895]
  We propose an augmented contrastive SSL framework to learn invariant representations from unlabeled data. Our method applies various perturbations to the unlabeled input data and utilizes contrastive learning to learn representations robust to such perturbations.
  arXiv  Detail & Related papers  (2021-12-21T02:50:53Z)
• UniSpeech-SAT: Universal Speech Representation Learning with Speaker Aware Pre-Training [72.004873454347]
  Two methods are introduced for enhancing the unsupervised speaker information extraction. Experiment results on SUPERB benchmark show that the proposed system achieves state-of-the-art performance. We scale up training dataset to 94 thousand hours public audio data and achieve further performance improvement.
  arXiv  Detail & Related papers  (2021-10-12T05:43:30Z)
• Self-supervised Learning is More Robust to Dataset Imbalance [65.84339596595383]
  We investigate self-supervised learning under dataset imbalance. Off-the-shelf self-supervised representations are already more robust to class imbalance than supervised representations. We devise a re-weighted regularization technique that consistently improves the SSL representation quality on imbalanced datasets.
  arXiv  Detail & Related papers  (2021-10-11T06:29:56Z)
• LeBenchmark: A Reproducible Framework for Assessing Self-Supervised Representation Learning from Speech [63.84741259993937]
  Self-Supervised Learning (SSL) using huge unlabeled data has been successfully explored for image and natural language processing. Recent works also investigated SSL from speech. We propose LeBenchmark: a reproducible framework for assessing SSL from speech.
  arXiv  Detail & Related papers  (2021-04-23T08:27:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.