all AI news
Alternating Weak Triphone/BPE Alignment Supervision from Hybrid Model Improves End-to-End ASR
Feb. 27, 2024, 5:49 a.m. | Jintao Jiang, Yingbo Gao, Mohammad Zeineldeen, Zoltan Tuske
cs.CL updates on arXiv.org arxiv.org
Abstract: In this paper, alternating weak triphone/BPE alignment supervision is proposed to improve end-to-end model training. Towards this end, triphone and BPE alignments are extracted using a pre-existing hybrid ASR system. Then, regularization effect is obtained by cross-entropy based intermediate auxiliary losses computed on such alignments at a mid-layer representation of the encoder for triphone alignments and at the encoder for BPE alignments. Weak supervision is achieved through strong label smoothing with parameter of 0.5. Experimental …
abstract alignment arxiv asr cross-entropy cs.cl cs.sd eess.as entropy hybrid intermediate losses paper regularization supervision training type
More from arxiv.org / cs.CL updates on arXiv.org
Jobs in AI, ML, Big Data
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US