Towards Unsupervised Speech Recognition Without Pronunciation Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916557533216768 |
|---|---|
| author | Ni, Junrui Wang, Liming Zhang, Yang Qian, Kaizhi Gao, Heting Hasegawa-Johnson, Mark Yoo, Chang D. |
| author_facet | Ni, Junrui Wang, Liming Zhang, Yang Qian, Kaizhi Gao, Heting Hasegawa-Johnson, Mark Yoo, Chang D. |
| contents | Recent advancements in supervised automatic speech recognition (ASR) have achieved remarkable performance, largely due to the growing availability of large transcribed speech corpora. However, most languages lack sufficient paired speech and text data to effectively train these systems. In this article, we tackle the challenge of developing ASR systems without paired speech and text corpora by proposing the removal of reliance on a phoneme lexicon. We explore a new research direction: word-level unsupervised ASR, and experimentally demonstrate that an unsupervised speech recognizer can emerge from joint speech-to-speech and text-to-text masked token-infilling. Using a curated speech corpus containing a fixed number of English words, our system iteratively refines the word segmentation structure and achieves a word error rate of between 20-23%, depending on the vocabulary size, without parallel transcripts, oracle word boundaries, or a pronunciation lexicon. This innovative model surpasses the performance of previous unsupervised ASR models under the lexicon-free setting. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_08380 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards Unsupervised Speech Recognition Without Pronunciation Models Ni, Junrui Wang, Liming Zhang, Yang Qian, Kaizhi Gao, Heting Hasegawa-Johnson, Mark Yoo, Chang D. Computation and Language Sound Audio and Speech Processing Recent advancements in supervised automatic speech recognition (ASR) have achieved remarkable performance, largely due to the growing availability of large transcribed speech corpora. However, most languages lack sufficient paired speech and text data to effectively train these systems. In this article, we tackle the challenge of developing ASR systems without paired speech and text corpora by proposing the removal of reliance on a phoneme lexicon. We explore a new research direction: word-level unsupervised ASR, and experimentally demonstrate that an unsupervised speech recognizer can emerge from joint speech-to-speech and text-to-text masked token-infilling. Using a curated speech corpus containing a fixed number of English words, our system iteratively refines the word segmentation structure and achieves a word error rate of between 20-23%, depending on the vocabulary size, without parallel transcripts, oracle word boundaries, or a pronunciation lexicon. This innovative model surpasses the performance of previous unsupervised ASR models under the lexicon-free setting. |
| title | Towards Unsupervised Speech Recognition Without Pronunciation Models |
| topic | Computation and Language Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2406.08380 |