# First-Pass Large Vocabulary Continuous Speech Recognition using Bi-Directional Recurrent DNNs

arXiv: https://arxiv.org/abs/1408.2873 · HTML: https://mlsanity.com/paper/1408.2873/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Aug 2014.

## Built on by (most cited first, 28 of 28)

- [End-to-End Speech Recognition: A Survey](https://mlsanity.com/paper/2303.03329/) (2023)
- [Directed Acyclic Transformer for Non-Autoregressive Machine Translation](https://mlsanity.com/paper/2205.07459/) (2022)
- [projUNN: efficient method for training deep networks with unitary matrices](https://mlsanity.com/paper/2203.05483/) (2022)
- [CTC Alignments Improve Autoregressive Translation](https://mlsanity.com/paper/2210.05200/) (2022)
- [Towards Zero-Shot Code-Switched Speech Recognition](https://mlsanity.com/paper/2211.01458/) (2022)
- [Non-autoregressive Text Editing with Copy-aware Latent Alignments](https://mlsanity.com/paper/2310.07821/) (2023)
- [4D ASR: Joint modeling of CTC, Attention, Transducer, and Mask-Predict decoders](https://mlsanity.com/paper/2212.10818/) (2022)
- [Text-To-Speech Data Augmentation for Low Resource Speech Recognition](https://mlsanity.com/paper/2204.00291/) (2022)
- [Better Intermediates Improve CTC Inference](https://mlsanity.com/paper/2204.00176/) (2022)
- [Speech Emotion: Investigating Model Representations, Multi-Task Learning and Knowledge Distillation](https://mlsanity.com/paper/2207.03334/) (2022)
- [Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition](https://mlsanity.com/paper/2501.09258/) (2025)
- [Sequence Transduction with Graph-based Supervision](https://mlsanity.com/paper/2111.01272/) (2021)
- [Improving Automatic Speech Recognition for Non-Native English with Transfer Learning and Language Model Decoding](https://mlsanity.com/paper/2202.05209/) (2022)
- [Can Visual Context Improve Automatic Speech Recognition for an Embodied Agent?](https://mlsanity.com/paper/2210.13189/) (2022)
- [Blank Collapse: Compressing CTC emission for the faster decoding](https://mlsanity.com/paper/2210.17017/) (2022)
- [Back from the future: bidirectional CTC decoding using future information in speech recognition](https://mlsanity.com/paper/2110.03326/) (2021)
- [Train your classifier first: Cascade Neural Networks Training from upper layers to lower layers](https://mlsanity.com/paper/2102.04697/) (2021)
- [Topic Model Robustness to Automatic Speech Recognition Errors in Podcast Transcripts](https://mlsanity.com/paper/2109.12306/) (2021)
- [Extended Graph Temporal Classification for Multi-Speaker End-to-End ASR](https://mlsanity.com/paper/2203.00232/) (2022)
- [Emphasizing Unseen Words: New Vocabulary Acquisition for End-to-End Speech Recognition](https://mlsanity.com/paper/2302.09723/) (2023)
- [Radio2Text: Streaming Speech Recognition Using mmWave Radio Signals](https://mlsanity.com/paper/2308.08125/) (2023)
- [Automated Mathematical Equation Structure Discovery for Visual Analysis](https://mlsanity.com/paper/2104.08633/) (2021)
- [An Investigation of Enhancing CTC Model for Triggered Attention-based Streaming ASR](https://mlsanity.com/paper/2110.10402/) (2021)
- [Enhancing the Unified Streaming and Non-streaming Model with Contrastive Learning](https://mlsanity.com/paper/2306.00755/) (2023)
- [Timestamped Embedding-Matching Acoustic-to-Word CTC ASR](https://mlsanity.com/paper/2306.11473/) (2023)
- [N-gram Boosting: Improving Contextual Biasing with Normalized N-gram Targets](https://mlsanity.com/paper/2308.02092/) (2023)
- [CANDLE: CTC-based Arabic Noisy-character Deduplication using a Lightweight Encoder](https://mlsanity.com/paper/2606.24758/) (2026)
- [O'ido: Open-Vocabulary Speech Recognition on a 5 Microcontroller without a Neural Accelerator](https://mlsanity.com/paper/2610.13447/) (2026)

## Abstract (arXiv)

We present a method to perform first-pass large vocabulary continuous speech recognition using only a neural network and language model. Deep neural network acoustic models are now commonplace in HMM-based speech recognition systems, but building such systems is a complex, domain-specific task. Recent work demonstrated the feasibility of discarding the HMM sequence modeling framework by directly predicting transcript text from audio. This paper extends this approach in two ways. First, we demonstrate that a straightforward recurrent neural network architecture can achieve a high level of accuracy. Second, we propose and evaluate a modified prefix-search decoding algorithm. This approach to decoding enables first-pass speech recognition with a language model, completely unaided by the cumbersome infrastructure of HMM-based systems. Experiments on the Wall Street Journal corpus demonstrate fairly competitive word error rates, and the importance of bi-directional network recurrence.