MR-RawNet: Speaker verification system with multiple temporal resolutions for variable duration utterances using raw waveforms
This work addresses performance degradation in speaker verification for short utterances, which is a domain-specific problem, but it appears incremental as it builds on existing raw waveform methods.
The paper tackles the challenge of speaker verification with short utterances by proposing MR-RawNet, a system that uses raw waveforms and multiple temporal resolutions to handle variable duration utterances, showing superior performance on the VoxCeleb1 dataset compared to other raw waveform-based systems.
In speaker verification systems, the utilization of short utterances presents a persistent challenge, leading to performance degradation primarily due to insufficient phonetic information to characterize the speakers. To overcome this obstacle, we propose a novel structure, MR-RawNet, designed to enhance the robustness of speaker verification systems against variable duration utterances using raw waveforms. The MR-RawNet extracts time-frequency representations from raw waveforms via a multi-resolution feature extractor that optimally adjusts both temporal and spectral resolutions simultaneously. Furthermore, we apply a multi-resolution attention block that focuses on diverse and extensive temporal contexts, ensuring robustness against changes in utterance length. The experimental results, conducted on VoxCeleb1 dataset, demonstrate that the MR-RawNet exhibits superior performance in handling utterances of variable duration compared to other raw waveform-based systems.