SiamCTC: Learning Speech Representations through Monotonic Temporal Alignment
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916074663968768 |
|---|---|
| author | Eom, SooHwan Hasegawa-Johnson, Mark Yoo, ad Chang D. |
| author_facet | Eom, SooHwan Hasegawa-Johnson, Mark Yoo, ad Chang D. |
| contents | Self-supervised speech representation learning has made significant progress through Siamese networks, which leverage different views of the same input. However, existing methods often require frame-wise alignment between these views, overlooking the broader linguistic context invariance across different speaking styles. We introduce SiamCTC, a framework that integrates Siamese networks with Connectionist Temporal Classification (CTC) to learn speech representations without strict frame-level correspondence. By employing CTC loss to establish flexible, monotonic alignments between differing temporal realizations of the same content, SiamCTC accommodates speed perturbations and other temporal augmentations. This design relaxes frame-wise constraints while preserving temporal coherence and enhancing robustness to speaking-rate variations in downstream tasks. Our experiments demonstrate that SiamCTC leads to more adaptable speech representations, particularly at diverse speaking rates. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2606_02220 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SiamCTC: Learning Speech Representations through Monotonic Temporal Alignment Eom, SooHwan Hasegawa-Johnson, Mark Yoo, ad Chang D. Audio and Speech Processing Self-supervised speech representation learning has made significant progress through Siamese networks, which leverage different views of the same input. However, existing methods often require frame-wise alignment between these views, overlooking the broader linguistic context invariance across different speaking styles. We introduce SiamCTC, a framework that integrates Siamese networks with Connectionist Temporal Classification (CTC) to learn speech representations without strict frame-level correspondence. By employing CTC loss to establish flexible, monotonic alignments between differing temporal realizations of the same content, SiamCTC accommodates speed perturbations and other temporal augmentations. This design relaxes frame-wise constraints while preserving temporal coherence and enhancing robustness to speaking-rate variations in downstream tasks. Our experiments demonstrate that SiamCTC leads to more adaptable speech representations, particularly at diverse speaking rates. |
| title | SiamCTC: Learning Speech Representations through Monotonic Temporal Alignment |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2606.02220 |