paper-with-me

Papers

The Peaking Phenomenon in Semi-supervised Learning

2016-10-17 · Jesse H. Krijthe, Marco Loog

For the supervised least squares classifier, when the number of training objects is smaller than the dimensionality of the data, adding more data to the training set may first increase the error rate before decreasing it. This, possibly counterintuitive, phenomenon is known as peaking. In this work, we observe that a similar but more pronounced version of this phenomenon also occurs in the semi-supervised setting, where instead of labeled objects, unlabeled objects are added to the training set. We explain why the learning curve has a more steep incline and a more gradual decline in this setting through simulation studies and by applying an approximation of the learning curve based on the work by Raudys & Duin.

📄 PDF Abstract BibTeX arXiv:1610.05160

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Science Fiction as a Worldwide Phenomenon: A Study of International Creation, Consumption and Dissemination

2013-08-06 · Elysia Wells

This paper examines the international nature of science fiction. The focus of this research is to determine whether science fiction is primarily English speaking and Western or global; being created and consumed by peopl…

Survey

Incremental Machine Speech Chain Towards Enabling Listening while Speaking in Real-time

2020-11-04 · Sashi Novitasari, Andros Tjandra, Tomoya Yanagita, Sakriani Sakti 외

Inspired by a human speech chain mechanism, a machine speech chain framework based on deep learning was recently proposed for the semi-supervised development of automatic speech recognition (ASR) and text-to-speech synth…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition+4

Semi-Supervised Generative Modeling for Controllable Speech Synthesis

2019-10-03 · ICLR 2020 1 · Raza Habib, Soroosh Mariooryad, Matt Shannon, Eric Battenberg 외

We present a novel generative model that combines state-of-the-art neural text-to-speech (TTS) with semi-supervised probabilistic latent variable models. By providing partial supervision to some of the latent variables, …

Speech Synthesistext-to-speechText to Speech

End-to-End Rich Transcription-Style Automatic Speech Recognition with Semi-Supervised Learning

2021-07-07 · Tomohiro Tanaka, Ryo Masumura, Mana Ihori, Akihiko Takashima 외

We propose a semi-supervised learning method for building end-to-end rich transcription-style automatic speech recognition (RT-ASR) systems from small-scale rich transcription-style and large-scale common transcription-s…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

A Semi-Automated Live Interlingual Communication Workflow Featuring Intralingual Respeaking: Evaluation and Benchmarking

2022-06-01 · LREC 2022 6 · Tomasz Korybski, Elena Davitti, Constantin Orasan, Sabine Braun

In this paper, we present a semi-automated workflow for live interlingual speech-to-text communication which seeks to reduce the shortcomings of existing ASR systems: a human respeaker works with a speaker-dependent spee…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)BenchmarkingMachine Translation+4