CONF Kumar_ICASSP2024_2024/IDIAP Multitask Speech Recognition and Speaker Change Detection for Unknown Number of Speakers Kumar, Shashi Madikeri, Srikanth Iuliia, Nigmatulina Villatoro-Tello, Esaú Motlicek, Petr S, Karthik Pandia D Dubagunta, S. Pavankumar Ganapathiraju, Aravind F1 score multitask learning Speaker change detection speaker turn detection speech recognition Proceedings of the 49th IEEE International Conference on Acoustics, Speech, & Signal Processing (ICASSP) 2024 Seoul, Republic of Korea 2024 IEEE 12592-12596 2379-190X 979-8-3503-4485-1 https://ieeexplore.ieee.org/document/10446130 URL https://doi.org/10.1109/ICASSP48485.2024.10446130 doi Traditionally, automatic speech recognition (ASR) and speaker change detection (SCD) systems have been independently trained to generate comprehensive transcripts accompanied by speaker turns. Recently, joint training of ASR and SCD systems, by inserting speaker turn tokens in the ASR training text, has been shown to be successful. In this work, we present a multitask alternative to the joint training approach. Results obtained on the mix-headset audios of AMI corpus show that the proposed multitask training yields an absolute improvement of 1.8% in coverage and purity based F1 score on SCD task without ASR degradation. We also examine the trade-offs between the ASR and SCD performance when trained using multitask criteria. Additionally, we validate the speaker change information in the embedding spaces obtained after different transformer layers of a self-supervised pre-trained model, such as XLSR-53, by integrating an SCD classifier at the output of specific transformer layers. Results reveal that the use of different embedding spaces from XLSR-53 model for multitask ASR and SCD is advantageous.