Hand-crafted Attention is All You Need? A Study of Attention on Self-supervised Audio Transformer

In this paper, we seek to reduce the computation complexity of transformer-based models for speech representation learning. We evaluate 10 attention mechanisms; then, we pre-train the transformer-based model with those attentions in a self-supervised fashion and use them as feature extractors on downstream tasks, including phoneme classification and speaker classification. We find that the proposed approach, which only uses hand-crafted and learnable attentions, is comparable with the full self-attention.

VQVC+: One-Shot Voice Conversion by Vector Quantization and U-Net architecture

Voice conversion (VC) is a task that transforms the source speaker's timbre, accent, and tones in audio into another one's while preserving the linguistic content. It is still a challenging work, especially in a one-shot setting. Auto-encoder-based VC methods disentangle the speaker and the content in input speech without given the speaker's identity, so these methods can further generalize to unseen speakers. The disentangle capability is achieved by vector quantization (VQ), adversarial training, or instance normalization (IN). However, the imperfect disentanglement may harm the quality of output speech. In this work, to further improve audio quality, we use the U-Net architecture within an auto-encoder-based VC system. We find that to leverage the U-Net architecture, a strong information bottleneck is necessary. The VQ-based method, which quantizes the latent vectors, can serve the purpose. The objective and the subjective evaluations show that the proposed method performs well in both audio naturalness and speaker similarity.