Exploring the Capability of Mamba in Speech Applications
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_ | 1866916298953326592 |
|---|---|
| author | Miyazaki, Koichi Masuyama, Yoshiki Murata, Masato |
| author_facet | Miyazaki, Koichi Masuyama, Yoshiki Murata, Masato |
| contents | This paper explores the capability of Mamba, a recently proposed architecture based on state space models (SSMs), as a competitive alternative to Transformer-based models. In the speech domain, well-designed Transformer-based models, such as the Conformer and E-Branchformer, have become the de facto standards. Extensive evaluations have demonstrated the effectiveness of these Transformer-based models across a wide range of speech tasks. In contrast, the evaluation of SSMs has been limited to a few tasks, such as automatic speech recognition (ASR) and speech synthesis. In this paper, we compared Mamba with state-of-the-art Transformer variants for various speech applications, including ASR, text-to-speech, spoken language understanding, and speech summarization. Experimental evaluations revealed that Mamba achieves comparable or better performance than Transformer-based models, and demonstrated its efficiency in long-form speech processing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_16808 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Exploring the Capability of Mamba in Speech Applications Miyazaki, Koichi Masuyama, Yoshiki Murata, Masato Sound Audio and Speech Processing This paper explores the capability of Mamba, a recently proposed architecture based on state space models (SSMs), as a competitive alternative to Transformer-based models. In the speech domain, well-designed Transformer-based models, such as the Conformer and E-Branchformer, have become the de facto standards. Extensive evaluations have demonstrated the effectiveness of these Transformer-based models across a wide range of speech tasks. In contrast, the evaluation of SSMs has been limited to a few tasks, such as automatic speech recognition (ASR) and speech synthesis. In this paper, we compared Mamba with state-of-the-art Transformer variants for various speech applications, including ASR, text-to-speech, spoken language understanding, and speech summarization. Experimental evaluations revealed that Mamba achieves comparable or better performance than Transformer-based models, and demonstrated its efficiency in long-form speech processing. |
| title | Exploring the Capability of Mamba in Speech Applications |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2406.16808 |