mlsanityData to 14 Oct 2026

Fast and Accurate Recurrent Neural Network Acoustic Models for Speech Recognition

arXiv 1507.06947 ↗First posted 24 Jul 2015cs.CL cs.LG cs.NEcited by 26

Not on the map. Why?

Abstract (arXiv)

We have recently shown that deep Long Short-Term Memory (LSTM) recurrent neural networks (RNNs) outperform feed forward deep neural networks (DNNs) as acoustic models for speech recognition. More recently, we have shown that the performance of sequence trained context dependent (CD) hidden Markov model (HMM) acoustic models using such LSTM RNNs can be equaled by sequence trained phone models initialized with connectionist temporal classification (CTC). In this paper, we present techniques that further improve performance of LSTM RNN acoustic models for large vocabulary speech recognition. We show that frame stacking and reduced frame rate lead to more accurate models and faster decoding. CD phone modeling leads to further improvements. We also present initial results for LSTM RNN models outputting words directly.

Key facts. Cited by 26 papers in the map (data through 14 Oct 2026). First posted on arXiv 24 Jul 2015.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 10; 2022: 9; 2023: 5; 2024: 1; 2025: 1.

26 papers.

Sort:

By area:

  1. 2021BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognitioncited by 88
  2. 2021CTC-based Compression for Direct Speech Translationcited by 45
  3. 2022Self-Ensemble Adversarial Training for Improved Robustnesscited by 38
  4. 2021Why does CTC result in peaky behavior?cited by 33
  5. 2022Effect and Analysis of Large-scale Language Model Rescoring on Competitive ASR Systemscited by 23
  6. 2022Accelerating RNN-T Training and Inference Using CTC guidancecited by 17
  7. 2021Speechformer: Reducing Information Loss in Direct Speech Translationcited by 15
  8. 2022Reservoir Computing via Quantum Recurrent Neural Networkscited by 14
  9. 2023Generalist: Decoupling Natural and Robust Generalizationcited by 14
  10. 2024YOLOv1 to YOLOv10: A comprehensive review of YOLO variants and their application in the agricultural domaincited by 14
  11. 2021Alignment Knowledge Distillation for Online Streaming Attention-based Speech Recognitioncited by 13
  12. 2022Improving Adversarial Robustness via Mutual Information Estimationcited by 13
14 more
  1. 2021A Streaming End-to-End Framework For Spoken Language Understandingcited by 8
  2. 2022Delay-penalized transducer for low-latency streaming ASRcited by 7
  3. 2022TrimTail: Low-Latency Streaming ASR with Simple but Effective Spectrogram-Level Length Penaltycited by 6
  4. 2021Exploiting Large-scale Teacher-Student Training for On-device Acoustic Modelscited by 5
  5. 2021Flexi-Transducer: Optimizing Latency, Accuracy and Compute forMulti-Domain On-Device Scenarioscited by 3
  6. 2021Optimizing Latency for Online Video CaptioningUsing Audio-Visual Transformerscited by 3
  7. 2023Biomembrane-based Memcapacitive Reservoir Computing System for Energy Efficient Temporal Data Processingcited by 2
  8. 2022Towards Better Meta-Initialization with Task Augmentation for Kindergarten-aged Speech Recognitioncited by 1
  9. 2022Attacks as Defenses: Designing Robust Audio CAPTCHAs Using Attacks on Automatic Speech Recognition Systemscited by 1
  10. 2023Machine Learning based prediction of Glucose Levels in Type 1 Diabetes Patients with the use of Continuous Glucose Monitoring Datacited by 1
  11. 2025Parameter Interpolation Adversarial Training for Robust Image Classificationcited by 1
  12. 2021Oracle Teacher: Leveraging Target Information for Better Knowledge Distillation of CTC Modelscited by 0
  13. 2023Intelligent Multi-channel Meta-imagers for Accelerating Machine Visioncited by 0
  14. 2023ATWM: Defense against adversarial malware based on adversarial trainingcited by 0