More Like this

1. Count and separate: incorporating speaker counting for continuous speaker separation

   https://doi.org/10.1109/ICASSP39728.2021.9414677  

   Wang, Z.-Q.; Wang, D.L. (January 2021, Proceedings of the IEEE International Conference on Acoustics Speech and Signal Processing)

   null (Ed.)
2. DyViSE: Dynamic Vision-Guided Speaker Embedding for Audio-Visual Speaker Diarization

   https://doi.org/10.1109/MMSP55362.2022.9948860  

   Wuerkaixi, Abudukelimu; Yan, Kunda; Zhang, You; Duan, Zhiyao; Zhang, Changshui (September 2022, 2022 IEEE 24th International Workshop on Multimedia Signal Processing (MMSP))
3. An investigation of domain adaptation in speaker embedding space for speaker recognition

   https://doi.org/10.1016/j.specom.2021.01.001  

   Bahmaninezhad, Fahimeh; Zhang, Chunlei; Hansen, John H.L. (May 2021, Speech Communication)

   null (Ed.)
4. Smart Speaker Command Dataset

   https://doi.org/10.60593/ur.d.26417548.v1  

   DiPassio, Tre; Heilemann, Michael; Rutowski, Jenna; Sedlacek, Paula; Thompson, Benjamin; Wen, Yutong (January 2024, University of Rochester)

   This dataset contains a collection of voice commands for a smart speaker, each beginning with the common wake-word "Hey Alexa". The commands cover a range of tasks such as music control, smart home management, information requests, reminders, shopping, entertainment, and communication. The dataset reflects natural language usage from a diverse group of speakers, capturing various phrasings, inflections, and contexts. It includes contributions from both male and female voices and features speakers with different native languages.If you plan to download this dataset, we would appreciate it very much if you could fill out the Google form at https://forms.gle/dixQ4mkZ4xbXtXRDA. This will help us understand the usage and impacts of this dataset. Your feedback will also help us improve any future extensions of this work. 

   more » « less
5. Speaker Conditioning of Acoustic Models Using Affine Transformation for Multi-Speaker Speech Recognition

   https://doi.org/10.1109/ASRU51503.2021.9688231  

   Yousefi, Midia; Hansen, John H.L. (December 2021, IEEE ASRU-2021: Automatic Speech Recognition & Understanding Workshop)

   This study addresses the problem of single-channel Automatic Speech Recognition of a target speaker within an overlap speech scenario. In the proposed method, the hidden representations in the acoustic model are modulated by speaker auxiliary information to recognize only the desired speaker. Affine transformation layers are inserted into the acoustic model network to integrate speaker information with the acoustic features. The speaker conditioning process allows the acoustic model to perform computation in the context of target-speaker auxiliary information. The proposed speaker conditioning method is a general approach and can be applied to any acoustic model architecture. Here, we employ speaker conditioning on a ResNet acoustic model. Experiments on the WSJ corpus show that the proposed speaker conditioning method is an effective solution to fuse speaker auxiliary information with acoustic features for multi-speaker speech recognition, achieving +9% and +20% relative WER reduction for clean and overlap speech scenarios, respectively, compared to the original ResNet acoustic model baseline. 

   more » « less