{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/multi-head-state-space-model-for-speech","title":"Multi-Head State Space Model for Speech Recognition","arxiv_id":"2305.12498","date":"2023-05-21","proceeding":null,"authors":["Yassir Fathullah","Chunyang Wu","Yuan Shangguan","Junteng Jia","Wenhan Xiong","Jay Mahadeokar","Chunxi Liu","Yangyang Shi","Ozlem Kalinli","Mike Seltzer","Mark J. F. Gales"],"abstract":"State space models (SSMs) have recently shown promising results on small-scale sequence and language modelling tasks, rivalling and outperforming many attention-based approaches. In this paper, we propose a multi-head state space (MH-SSM) architecture equipped with special gating mechanisms, where parallel heads are taught to learn local and global temporal dynamics on sequence data. As a drop-in replacement for multi-head attention in transformer encoders, this new model significantly outperforms the transformer transducer on the LibriSpeech speech recognition corpus. Furthermore, we augment the transformer block with MH-SSMs layers, referred to as the Stateformer, achieving state-of-the-art performance on the LibriSpeech task, with word error rates of 1.76\\%/4.37\\% on the development and 1.91\\%/4.36\\% on the test sets without using an external language model.","url_abs":"https://arxiv.org/abs/2305.12498v2","url_pdf":"https://arxiv.org/pdf/2305.12498v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"state-space-models","task_name":"State Space Models"},{"task_slug":"model","task_name":"model"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-recognition-on-librispeech-test-clean","task":"Speech Recognition","dataset":"LibriSpeech test-clean","model":"Stateformer","rank_in_archive_order":11,"of":64,"metrics":{"Word Error Rate (WER)":"1.76"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.12498","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}