Speaker extraction requires a sample speech from the target speaker as the reference. However, enrolling a speaker with a long speech is not practical. We propose a speaker extraction technique, that performs in multiple stages to take full advantage of short reference speech sample. The extracted speech in early stages is used as the reference speech for late stages. For the first time, we use frame-level sequential speech embedding as the reference for target speaker. This is a departure from the traditional utterance-based speaker embedding reference. In addition, a signal fusion scheme is proposed to combine the decoded signals in multiple scales with automatically learned weights. Experiments on WSJ0-2mix and its noisy versions (WHAM! and WHAMR!) show that SpEx++ consistently outperforms other state-of-the-art baselines.
翻译:发言者的抽调需要来自目标演讲者的抽样演讲作为参考。 但是, 注册使用长长的演讲者是不切实际的。 我们建议使用一个声音抽调技术, 在多个阶段进行, 以充分利用短的参考演讲样本。 早期抽调的演讲被用作后期阶段的参考演讲。 我们第一次使用框架级顺序演讲作为目标演讲者的参考。 这是与传统的发音型演讲者嵌入参考的偏离。 此外, 提议采用信号聚合计划, 将多尺度的解码信号与自动学习的重量结合起来。 WSJ0-2Mix 及其噪音版本( WHAM! 和 WHAMMR!) 实验显示 SpEx++ 一直比其他最新基线( WHAM! 和 WHAMMR! ) 。