# Scaling Up Online Speech Recognition Using ConvNets

arXiv: https://arxiv.org/abs/2001.09727 · HTML: https://mlsanity.com/paper/2001.09727/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jan 2020.

## Built on by (most cited first, 16 of 16)

- [Intermediate Loss Regularization for CTC-based Speech Recognition](https://mlsanity.com/paper/2102.03216/) (2021)
- [PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition](https://mlsanity.com/paper/2106.05933/) (2021)
- [Smart at what cost? Characterising Mobile Deep Neural Networks in the wild](https://mlsanity.com/paper/2109.13963/) (2021)
- [Dissecting User-Perceived Latency of On-Device E2E Speech Recognition](https://mlsanity.com/paper/2104.02207/) (2021)
- [emg2qwerty: A Large Dataset with Baselines for Touch Typing using Surface Electromyography](https://mlsanity.com/paper/2410.20081/) (2024)
- [Towards Online Continuous Sign Language Recognition and Translation](https://mlsanity.com/paper/2401.05336/) (2024)
- [Layer Pruning on Demand with Intermediate CTC](https://mlsanity.com/paper/2106.09216/) (2021)
- [Benchmarking of DL Libraries and Models on Mobile Devices](https://mlsanity.com/paper/2202.06512/) (2022)
- [Enabling Resource-efficient AIoT System with Cross-level Optimization: A survey](https://mlsanity.com/paper/2309.15467/) (2023)
- [NatiQ: An End-to-end Text-to-Speech System for Arabic](https://mlsanity.com/paper/2206.07373/) (2022)
- [Flexi-Transducer: Optimizing Latency, Accuracy and Compute forMulti-Domain On-Device Scenarios](https://mlsanity.com/paper/2104.02232/) (2021)
- [Application-Agnostic Language Modeling for On-Device ASR](https://mlsanity.com/paper/2305.09764/) (2023)
- [Align With Purpose: Optimize Desired Properties in CTC Models with a General Plug-and-Play Framework](https://mlsanity.com/paper/2307.01715/) (2023)
- [Audio Adversarial Examples: Attacks Using Vocal Masks](https://mlsanity.com/paper/2102.02417/) (2021)
- [Voice Quality and Pitch Features in Transformer-Based Speech Recognition](https://mlsanity.com/paper/2112.11391/) (2021)
- [Mixture-of-Rookies: Saving DNN Computations by Predicting ReLU Outputs](https://mlsanity.com/paper/2202.04990/) (2022)

## Abstract (arXiv)

We design an online end-to-end speech recognition system based on Time-Depth Separable (TDS) convolutions and Connectionist Temporal Classification (CTC). We improve the core TDS architecture in order to limit the future context and hence reduce latency while maintaining accuracy. The system has almost three times the throughput of a well tuned hybrid ASR baseline while also having lower latency and a better word error rate. Also important to the efficiency of the recognizer is our highly optimized beam search decoder. To show the impact of our design choices, we analyze throughput, latency, accuracy, and discuss how these metrics can be tuned based on the user requirements.