DeepAI AI Chat
Log In Sign Up

Separating Long-Form Speech with Group-Wise Permutation Invariant Training

by   Wangyou Zhang, et al.

Multi-talker conversational speech processing has drawn many interests for various applications such as meeting transcription. Speech separation is often required to handle overlapped speech that is commonly observed in conversation. Although the original utterancelevel permutation invariant training-based continuous speech separation approach has proven to be effective in various conditions, it lacks the ability to leverage the long-span relationship of utterances and is computationally inefficient due to the highly overlapped sliding windows. To overcome these drawbacks, we propose a novel training scheme named Group-PIT, which allows direct training of the speech separation models on the long-form speech with a low computational cost for label assignment. Two different speech separation approaches with Group-PIT are explored, including direct long-span speech separation and short-span speech separation with long-span tracking. The experiments on the simulated meeting-style data demonstrate the effectiveness of our proposed approaches, especially in dealing with a very long speech input.


Guided Training: A Simple Method for Single-channel Speaker Separation

Deep learning has shown a great potential for speech separation, especia...

Permutation Invariant Training of Deep Models for Speaker-Independent Multi-talker Speech Separation

We propose a novel deep learning model, which supports permutation invar...

Single-channel speech separation using Soft-minimum Permutation Invariant Training

The goal of speech separation is to extract multiple speech sources from...

Probabilistic Permutation Invariant Training for Speech Separation

Single-microphone, speaker-independent speech separation is normally per...

Interrupted and cascaded permutation invariant training for speech separation

Permutation Invariant Training (PIT) has long been a stepping stone meth...

Continuous Speech Separation with Recurrent Selective Attention Network

While permutation invariant training (PIT) based continuous speech separ...