Publication Details
HyperConformer: Multi-head HyperMixer for Efficient Speech Recognition
Hypernetworks, HyperMixer, Efficient Auto- matic Speech Recognition, LibriSpeech, SpeechBrain
State-of-the-art ASR systems have achieved promising results by modeling local and global interactions separately. While the former can be computed efficiently, global interactions are usu- ally modeled via attention mechanisms, which are expensive for long input sequences. Here, we address this by extending Hy- perMixer, an efficient alternative to attention exhibiting linear complexity, to the Conformer architecture for speech recogni- tion, leading to HyperConformer. In particular, multi-head Hy- perConformer achieves comparable or higher recognition per- formance while being more efficient than Conformer in terms of inference speed, memory, parameter count, and available train- ing data. HyperConformer achieves a word error rate of 2.9% on LibriSpeech test-clean with less than 8M neural parameters and a peak memory during training of 5.7GB, hence trainable with accessible hardware. Encoder speed is between 38% on mid-length speech and 56% on long speech faster than an equiv- alent Conformer.1)
@inproceedings{BUT187786,
author="MAI, F. and ZULUAGA-GOMEZ, J. and PARCOLLET, T. and MOTLÍČEK, P.",
title="HyperConformer: Multi-head HyperMixer for Efficient Speech Recognition",
booktitle="Proceedings of the Annual Conference of International Speech Communication Association, INTERSPEECH",
year="2023",
journal="Proceedings of Interspeech",
volume="2023",
number="08",
pages="2213--2217",
publisher="International Speech Communication Association",
address="Dublin",
doi="10.21437/Interspeech.2023-1611",
issn="1990-9772",
url="https://www.isca-archive.org/interspeech_2023/mai23_interspeech.pdf"
}