# Gabor Gabor: E-Gaborformer, a Strictly Causal Speech Recognizer with Gabor-Dictionary Convolutions and Delta-Rule Memory

**Authors:** Nir Krakowski, Tamir Cohen, Ohad Zohar, Chen Zarfati  
**Published:** 5 Nov 2026  
**Links:** [arXiv](https://arxiv.org/abs/2611.08092) · [PDF](https://arxiv.org/pdf/2611.08092) · [This page](https://omen-bit.github.io/ai-paper-daily/paper/2611.08092.html)

## Key numbers

- **18%**: reaches a given accuracy up to 18% sooner
- **31%**: …Hebrew and English streaming transducer built on E-Gaborformer has 28 to 31% lower word error rate
- **20%**: and up to 20% lower Hebrew WER than our previous production system

## Abstract

Real-time voice agents need a speech recognizer that never waits for future audio and whose memory per call does not grow with the length of the call. We present E-Gaborformer, a strictly causal encoder that combines Gated DeltaNet-2 recurrent layers with sliding-window attention in a 3:1 ratio, and builds every temporal convolution from a fixed dictionary of causal Gabor atoms. Its streaming state is constant, about 19 MB per call at production scale including the prediction network, where a causal-attention encoder of the same size accumulates over 1 GB after ten minutes. In a controlled causal study on LibriSpeech, E-Gaborformer leaves the initial plateau earlier, reaches a given accuracy up to 18% sooner, and matches or beats an E-Branchformer trained with the identical front end and recipe. At production scale, a 0.6B-parameter Hebrew and English streaming transducer built on E-Gaborformer has 28 to 31% lower word error rate (WER) than NVIDIA's Nemotron 3.5 ASR Streaming, a model of the same size, on English voice-agent traffic, and up to 20% lower Hebrew WER than our previous production system. The same weights serve strictly causal and 480 ms-lookahead decoding with no loss in accuracy, and a two-class formulation of the RNN-T lattice trains the transducer 2.6x faster with exact loss and gradients.

---

Notes written by AI from the paper, numbers copied from the abstract. Check the paper before you rely on them. From AI Papers Daily.