Combining TF-GridNet And Mixture Encoder For Continuous Speech Separation For Meeting Transcription

IEEE Spoken Language Technology Workshop (SLT), pp. 155–162

Abstract

Many real-life applications of automatic speech recognition (ASR) require processing of overlapped speech. A common method involves first separating the speech into overlap-free streams on which ASR is performed. Recently, TF-GridNet has shown impressive performance in speech separation in real reverberant conditions. Furthermore, a mixture encoder was proposed that leverages the mixed speech to mitigate the effect of separation artifacts. In this work, we extended the mixture encoder from a static two-speaker scenario to a natural meeting context featuring an arbitrary number of speakers and varying degrees of overlap. We further demonstrate its limits by the integration with separators of varying strength including TF-GridNet. Our experiments result in a new state-of-the-art performance on LibriCSS using a single microphone. They show that TF-GridNet largely closes the gap between previous methods and oracle separation independent of mixture encoding. We further investigate the remaining potential for improvement.

Authors 6

1. Peter Vieting Aachen Machine Learning and Human Language Technology Group

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University,Machine Learning and Human Language Technology Group,Germany

2. Simon Berger Aachen Machine Learning and Human Language Technology Group

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University,Machine Learning and Human Language Technology Group,Germany

3. Thilo von Neumann

   Paderborn University

   Affiliation as printed

   Paderborn University,Germany

4. Christoph Boeddeker

   Paderborn University

   Affiliation as printed

   Paderborn University,Germany

5. Ralf Schlüter Aachen Machine Learning and Human Language Technology Group

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University,Machine Learning and Human Language Technology Group,Germany

6. Reinhold Haeb‐Umbach

   Paderborn University

   Affiliation as printed

   Paderborn University,Germany