3 papers
cs.SD2024
Mamba-based Decoder-Only Approach with Bidirectional Speech Modeling for Speech Recognition
Yoshiki Masuyama, Koichi Miyazaki, Masato Murata
Selective state space models (SSMs) represented by Mamba have demonstrated their computational efficiency and promising outcomes in various tasks, including automatic speech recogn…
cs.SD2024
An Attribute Interpolation Method in Speech Synthesis by Model Merging
Masato Murata, Koichi Miyazaki, Tomoki Koriyama
With the development of speech synthesis, recent research has focused on challenging tasks, such as speaker generation and emotion intensity control. Attribute interpolation is a c…
cs.SD2024
Exploring the Capability of Mamba in Speech Applications
Koichi Miyazaki, Yoshiki Masuyama, Masato Murata
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 s…