paper-with-me

Papers

Self-supervised Semantic-driven Phoneme Discovery for Zero-resource Speech Recognition

2022-05-01 · ACL 2022 5 · Liming Wang, Siyuan Feng, Mark Hasegawa-Johnson, Chang Yoo

Phonemes are defined by their relationship to words: changing a phoneme changes the word. Learning a phoneme inventory with little supervision has been a longstanding challenge with important applications to under-resourced speech technology. In this paper, we bridge the gap between the linguistic and statistical definition of phonemes and propose a novel neural discrete representation learning model for self-supervised learning of phoneme inventory with raw speech and word labels. Under mild assumptions, we prove that the phoneme inventory learned by our approach converges to the true one with an exponentially low error rate. Moreover, in experiments on TIMIT and Mboshi benchmarks, our approach consistently learns a better phoneme-level representation and achieves a lower error rate in a zero-resource phoneme recognition task than previous state-of-the-art self-supervised representation learning algorithms.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Phoneme RecognitionRepresentation LearningSelf-Supervised Learningspeech-recognitionSpeech Recognition

Similar Papers 제목 키워드 기반

Self-supervised Semantic-driven Phoneme Discovery for Zero-resource Speech Recognition

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Phonemes are defined by their relationship to words: changing a phoneme changes the word. Learning a phoneme inventory with little supervision has been a longstanding challenge with important applications to under-resour…

Phoneme RecognitionRepresentation LearningSelf-Supervised Learningspeech-recognition+1

SD-HuBERT: Sentence-Level Self-Distillation Induces Syllabic Organization in HuBERT

2023-10-16 · Cheol Jun Cho, Abdelrahman Mohamed, Shang-Wen Li, Alan W Black 외

Data-driven unit discovery in self-supervised learning (SSL) of speech has embarked on a new era of spoken language processing. Yet, the discovered units often remain in phonetic space and the units beyond phonemes are l…

Language ModelingLanguage ModellingSelf-Supervised LearningSentence

Do speech foundation models really learn words?

2026-09-09 · Robin Huo, Ewan Dunbar arxiv

Self-supervised speech foundation models are now used in a wide array of downstream applications, including traditional speech recognition and as the basis for tokens in speech-aware language models. Attempts to understa…

Speech Recognition

Data-driven grapheme-to-phoneme representations for a lexicon-free text-to-speech

2024-01-19 · Abhinav Garg, Jiyeon Kim, Sushil Khyalia, Chanwoo Kim 외

Grapheme-to-Phoneme (G2P) is an essential first step in any modern, high-quality Text-to-Speech (TTS) system. Most of the current G2P systems rely on carefully hand-crafted lexicons developed by experts. This poses a two…

Self-Supervised Learningtext-to-speechText to Speech

DiscoPhon: Benchmarking the Unsupervised Discovery of Phoneme Inventories With Discrete Speech Units

2026-03-19 · Maxime Poli, Manel Khentout, Angelo Ortiz Tandazo, Ewan Dunbar 외 arxiv

We introduce DiscoPhon, a multilingual benchmark for evaluating unsupervised phoneme discovery from discrete speech units. DiscoPhon covers 6 dev and 6 test languages, chosen to span a wide range of phonemic contrasts. G…