paper-with-me

Papers

Evaluating context-invariance in unsupervised speech representations

2022-10-27 · Mark Hallap, Emmanuel Dupoux, Ewan Dunbar

Unsupervised speech representations have taken off, with benchmarks (SUPERB, ZeroSpeech) demonstrating major progress on semi-supervised speech recognition, speech synthesis, and speech-only language modelling. Inspiration comes from the promise of ``discovering the phonemes'' of a language or a similar low-bitrate encoding. However, one of the critical properties of phoneme transcriptions is context-invariance: the phonetic context of a speech sound can have massive influence on the way it is pronounced, while the text remains stable. This is what allows tokens of the same word to have the same transcriptions -- key to language understanding. Current benchmarks do not measure context-invariance. We develop a new version of the ZeroSpeech ABX benchmark that measures context-invariance, and apply it to recent self-supervised representations. We demonstrate that the context-independence of representations is predictive of the stability of word-level representations. We suggest research concentrate on improving context-independence of self-supervised and unsupervised representations.

📄 PDF Abstract BibTeX arXiv:2210.15775

Code (1)

perceptimatic/context-invariance-paper 공식 구현

Tasks

Language Modellingspeech-recognitionSpeech RecognitionSpeech Synthesis

Similar Papers 제목 키워드 기반

Representation Learning With Hidden Unit Clustering For Low Resource Speech Applications

2023-07-14 · Varun Krishna, Tarun Sai, Sriram Ganapathy

The representation learning of speech, without textual resources, is an area of significant interest for many low resource speech applications. In this paper, we describe an approach to self-supervised representation lea…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)ClusteringRepresentation Learning+2

Understanding Self-Supervised Learning of Speech Representation via Invariance and Redundancy Reduction

2023-09-07 · Yusuf Brima, Ulf Krumnack, Simone Pika, Gunther Heidemann

Self-supervised learning (SSL) has emerged as a promising paradigm for learning flexible speech representations from unlabeled data. By designing pretext tasks that exploit statistical regularities, SSL models can captur…

Keyword SpottingSelf-Supervised LearningSpeaker Identification

Robust speaker recognition using unsupervised adversarial invariance

2019-11-03 · Raghuveer Peri, Monisankha Pal, Arindam Jati, Krishna Somandepalli 외

In this paper, we address the problem of speaker recognition in challenging acoustic conditions using a novel method to extract robust speaker-discriminative speech representations. We adopt a recently proposed unsupervi…

speaker-diarizationSpeaker DiarizationSpeaker RecognitionSpeaker Verification

Unspeech: Unsupervised Speech Context Embeddings

2018-04-18 · Benjamin Milde, Chris Biemann

We introduce "Unspeech" embeddings, which are based on unsupervised learning of context feature representations for spoken language. The embeddings were trained on up to 9500 hours of crawled English speech data without …

Clustering

Learning Robust and Multilingual Speech Representations

2020-01-29 · Findings of the Association for Computational Linguistics 2020 · Kazuya Kawakami, Luyu Wang, Chris Dyer, Phil Blunsom 외

Unsupervised speech representation learning has shown remarkable success at finding representations that correlate with phonetic structures and improve downstream speech recognition performance. However, most research ha…

Representation Learningspeech-recognitionSpeech RecognitionSpeech Representation Learning