English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Utterance-level permutation invariant training (uPIT) has achieved promisingprogress on single-channel multi-talker speech separation task. Long short-termmemory (LSTM) and bidirectional LSTM (BLSTM) are widely used as the separationnetworks of uPIT, i.e. uPIT-LSTM and uPIT-BLSTM. uPIT-LSTM has lower latencybut worse performance, while uPIT-BLSTM has better performance but higherlatency. In this paper, we propose using latency-controlled BLSTM (LC-BLSTM)during inference to fulfill low-latency and good-performance speech separation.To find a better training strategy for BLSTM-based separation network,chunk-level PIT (cPIT) and uPIT are compared. The experimental results showthat uPIT outperforms cPIT when LC-BLSTM is used during inference. It is alsofound that the inter-chunk speaker tracing (ST) can further improve theseparation performance of uPIT-LC-BLSTM. Evaluated on the WSJ0 two-talkermixed-speech separation task, the absolute gap of signal-to-distortion ratio(SDR) between uPIT-BLSTM and uPIT-LC-BLSTM is reduced to within 0.7 dB.

Utterance-level Permutation Invariant Training with Latency-controlled BLSTM for Single-channel Multi-talker Speech Separation