INTERSPEECH 2022

BEST STUDENT PAPER AWARDS

The ISCA best student paper awards go to

BEST STUDENT PAPER SHORTLIST

The following 12 papers are shortlisted for the ISCA Best Student Paper Award 2022.

• Tsiky Rakotomalala, Pierre Baraduc and Pascal Perrier: Trajectories predicted by optimal speech motor control using LSTM networks

  PaperID-10604, Speech Production, Mon-O-OS-2-2, In-Person

• Philipp Buech, Rachid Ridouane and Anne Hermes: Pharyngealization in Amazigh: Acoustic and articulatory marking over time

  PaperID-10831, Phonetics and Phonology, Wed-O-OS-7-3, In-Person

• Ambika Kirkland, Harm Lameris, Éva Székely and Joakim Gustafson: Where's the uh, hesitation? The interplay between filled pause location, speech rate and fundamental frequency in perception of confidence

  PaperID-10973, Emotional Speech Production and Perception, Thu-O-OS-10-3, In-Person

• Bei Liu, Zhengyang Chen and Yanmin Qian: Attentive Feature Fusion for Robust Speaker Verification

  PaperID-478, Embedding and Network Architecture for Speaker Recognition, Mon-P-VR-1-4, Virtual

• Katharine Patterson, Kevin Wilson, Scott Wisdom and John R. Hershey: Distance-Based Sound Separation

  PaperID-11100, Spatial Audio, Mon-P-VR-2-4, Virtual

• Vinay Kothapally and John H.L. Hansen: Complex-Valued Time-Frequency Self-Attention for Speech Dereverberation

  PaperID-11277, Dereverberation and Echo Cancellation, Tue-P-VR-5-4, Virtual

• Minchan Kim, Myeonghun Jeong, Byoung Jin Choi, Sunghwan Ahn, Joun Yeop Lee and Nam Soo Kim: Transfer Learning Framework for Low-Resource Text-to-Speech using a Large-Scale Unlabeled Speech Corpus

  PaperID-225, Speech Synthesis: Acoustic Modeling and Neural Waveform Generation I, Mon-P-OS-2-2, In-Person

• Guangzhi Sun, Chao Zhang and Phil Woodland: Tree-constrained Pointer Generator with Graph Neural Network Encodings for Contextual Speech Recognition

  PaperID-461, Neural Transducers Streaming ASR and Novel ASR Models, Tue-P-VR-4-4, Virtual

• Qu Yang, Qi Liu and Haizhou Li: Deep Residual Spiking Neural Network for Keyword Spotting in Low-Resource Settings

  PaperID-107, Resource-constrained ASR, Wed-P-OS-6-3, In-Person

• Bowen Shi, Wei-Ning Hsu and Abdelrahman Mohamed: Robust Self-Supervised Audio-Visual Speech Recognition

  PaperID-99, Zero Low-resource and Multi-Modal Speech Recognition II, Tue-P-VR-4-5, Virtual

• Sarenne Carrol Wallbridge, Catherine Lai and Peter Bell: Investigating perception of spoken dialogue acceptability through surprisal

  PaperID-10808, Spoken Dialogue Systems, Thu-O-OS-9-4, In-Person

• Hyeon-Kyeong Shin, Hyewon Han, Doyeon Kim, Soo-Whan Chung and Hong-Goo Kang: Learning Audio-Text Agreement for Open-vocabulary Keyword Spotting

  PaperID-580, Spoken Term Detection and Voice Search, Tue-O-OS-4-4, In-Person