Data to 7 Oct 2026

Transformer-based Acoustic Modeling for Hybrid Speech Recognition

arXiv 1910.09799 ↗First posted 22 Oct 2019cs.CL eess.AScited by 86

Not on the map. Why?

Abstract (arXiv)

We propose and evaluate transformer-based acoustic models (AMs) for hybrid speech recognition. Several modeling choices are discussed in this work, including various positional embedding methods and an iterated loss to enable training deep transformers. We also present a preliminary study of using limited right context in transformer models, which makes it possible for streaming applications. We demonstrate that on the widely used Librispeech benchmark, our transformer-based AM outperforms the best published hybrid result by 19% to 26% relative when the standard n-gram language model (LM) is used. Combined with neural network LM for rescoring, our proposed approach achieves state-of-the-art results on Librispeech. Our findings are also confirmed on a much larger internal dataset.

Key facts. Cited by 86 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 37; 2022: 17; 2023: 19; 2024: 10; 2025: 3.

86 papers.

Sort:

2021TransVG: End-to-End Visual Grounding with Transformerscited by 269
2023End-to-End Speech Recognition: A Surveycited by 127
2023Zipformer: A faster and better encoder for automatic speech recognitioncited by 77
2021Linear algebra with transformerscited by 62
2022Squeezeformer: An Efficient Transformer for Automatic Speech Recognitioncited by 50
2024Automatic Speech Recognition using Advanced Deep Learning Approaches: A surveycited by 50
2021MobTCast: Leveraging Auxiliary Trajectory Forecasting for Human Mobility Predictioncited by 48
2021CAPE: Encoding Relative Positions with Continuous Augmented Positional Embeddingscited by 47
2022Learning to Estimate Shapley Values with Vision Transformerscited by 44
2021Transformer Based Deliberation for Two-Pass Speech Recognitioncited by 29
2021Kaizen: Continuously improving teacher using Exponential Moving Average for semi-supervised speech recognitioncited by 21
2021Improved Language Identification Through Cross-Lingual Self-Supervised Learningcited by 20

38 more

2022Speaker Adaptation Using Spectro-Temporal Deep Features for Dysarthric and Elderly Speech Recognitioncited by 19
2021Personalized Speech Enhancement: New Models and Comprehensive Evaluationcited by 18
2021End-to-End Multi-Channel Transformer for Speech Recognitioncited by 17
2022Personalized Adversarial Data Augmentation for Dysarthric and Elderly Speech Recognitioncited by 16
2023SpeechFormer++: A Hierarchical Efficient Framework for Paralinguistic Speech Processingcited by 16
2021Conformer-based Hybrid ASR System for Switchboard Datasetcited by 15
2021Scaling ASR Improves Zero and Few Shot Learningcited by 15
2022SepTr: Separable Transformer for Audio Spectrogram Processingcited by 15
2021Perspectives and Prospects on Transformer Architecture for Cross-Modal Tasks with Language and Visioncited by 14
2022Efficient Training of Neural Transducer for Speech Recognitioncited by 14
2023Multi-Head State Space Model for Speech Recognitioncited by 14
2023Lexical Speaker Error Correction: Leveraging Language Models for Speaker Diarization Error Correctioncited by 14
2022Spectro-Temporal Deep Features for Disordered Speech Assessment and Recognitioncited by 13
2022Revisiting Checkpoint Averaging for Neural Machine Translationcited by 13
2021Arabic Speech Recognition by End-to-End, Modular Systems and Humancited by 12
2024HiQuE: Hierarchical Question Embedding Network for Multimodal Depression Detectioncited by 12
2021Contrastive Semi-supervised Learning for ASRcited by 11
2021XLST: Cross-lingual Self-training to Learn Multilingual Representation for Low Resource Speech Recognitioncited by 11
2023SALSA PICANTE: a machine learning attack on LWE with binary secretscited by 11
2021Understanding Medical Conversations: Rich Transcription, Confidence Scores & Information Extractioncited by 10
2022TraHGR: Transformer for Hand Gesture Recognition via ElectroMyographycited by 10
2021Speech Technology for Everyone: Automatic Speech Recognition for Non-Native English with Transfer Learningcited by 9
2021Correcting Automated and Manual Speech Transcription Errors using Warped Language Modelscited by 8
2021An Improved Single Step Non-autoregressive Transformer for Automatic Speech Recognitioncited by 8
2021Multi-Channel Transformer Transducer for Speech Recognitioncited by 8
2022Data Augmentation for Low-Resource Quechua ASR Improvementcited by 8
2023Angel-PTM: A Scalable and Economical Large-scale Pre-training System in Tencentcited by 8
2024Dynamic Transformer Architecture for Continual Learning of Multimodal Taskscited by 8
2021TEMGNet: Deep Transformer-based Decoding of Upperlimb sEMG for Hand Gestures Recognitioncited by 7
2022Losses Can Be Blessings: Routing Self-Supervised Speech Representations Towards Efficient Multilingual and Multitask Speech Processingcited by 7
2023Self-Attention Amortized Distributional Projection Optimization for Sliced Wasserstein Point-Cloud Reconstructioncited by 7
2023Folding Attention: Memory and Power Optimization for On-Device Transformer-based Streaming Speech Recognitioncited by 7
2021SRU++: Pioneering Fast Recurrence with Attention for Speech Recognitioncited by 6
2021Bi-APC: Bidirectional Autoregressive Predictive Coding for Unsupervised Pre-training and Its Application to Children's ASRcited by 5
2021Thank you for Attention: A survey on Attention-based Artificial Neural Networks for Automatic Speech Recognitioncited by 5
2021Streaming Transformer Transducer Based Speech Recognition Using Non-Causal Convolutioncited by 5
2021Mixed Precision Low-bit Quantization of Neural Network Language Models for Speech Recognitioncited by 5
2022Learning a Dual-Mode Speech Recognition Model via Self-Pruningcited by 5

50 most cited of 86 All 86 (JSON)