wav2letter++: The Fastest Open-source Speech Recognition System
arXiv:1812.07625 · doi:10.1109/ICASSP.2019.8683535
Abstract
This paper introduces wav2letter++, the fastest open-source deep learning speech recognition framework. wav2letter++ is written entirely in C++, and uses the ArrayFire tensor library for maximum efficiency. Here we explain the architecture and design of the wav2letter++ system and compare it to other major open-source speech recognition systems. In some cases wav2letter++ is more than 2x faster than other optimized frameworks for training end-to-end neural networks for speech recognition. We also show that wav2letter++'s training times scale linearly to 64 GPUs, the highest we tested, for models with 100 million parameters. High-performance frameworks enable fast iteration, which is often a crucial factor in successful research and model tuning on new datasets and tasks.
References in corpus (8)
- Neural Machine Translation by Jointly Learning to Align and Translate
- TensorFlow: A system for large-scale machine learning
- Attention-Based Models for Speech Recognition
- cuDNN: Efficient Primitives for Deep Learning
- Wav2Letter: an End-to-End ConvNet-based Speech Recognition System
- ESPnet: End-to-End Speech Processing Toolkit
- Mixed-Precision Training for NLP and Speech Recognition with OpenSeq2Seq
- Letter-Based Speech Recognition with Gated ConvNets
Cited by in corpus (42)
- WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing
- Libri-Light: A Benchmark for ASR with Limited or No Supervision
- MLS: A Large-Scale Multilingual Dataset for Speech Research
- Self-Training for End-to-End Speech Recognition
- End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures
- Effectiveness of self-supervised pre-training for speech recognition
- fairseq S2T: Fast Speech-to-Text Modeling with fairseq
- Applying Wav2vec2.0 to Speech Recognition in Various Low-resource Languages
- SUPERB: Speech processing Universal PERformance Benchmark
- ATCSpeech: a multilingual pilot-controller speech corpus from real Air Traffic Control environment
- Efficiently Fusing Pretrained Acoustic and Linguistic Encoders for Low-resource Speech Recognition
- Semi-Supervised Speech Recognition via Local Prior Matching
- Who Needs Words? Lexicon-Free Speech Recognition
- Iterative Pseudo-Labeling for Speech Recognition
- CrossASR++: A Modular Differential Testing Framework for Automatic Speech Recognition
- Unsupervised Speech Recognition
- Espresso: A Fast End-to-end Neural Speech Recognition Toolkit
- Self-training and Pre-training are Complementary for Speech Recognition
- Convolutional Neural Networks for Speech Controlled Prosthetic Hands
- CAT: CRF-based ASR Toolkit
- Differentiable Weighted Finite-State Transducers
- ESPnet-ST: All-in-One Speech Translation Toolkit
- A Comparison of Methods for OOV-word Recognition on a New Public Dataset
- General-Purpose Speech Representation Learning through a Self-Supervised Multi-Granularity Framework
- Current Challenges in Spoken Dialogue Systems and Why They Are Critical for Those Living with Dementia
- CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition
- DARTS: Dialectal Arabic Transcription System
- Convolutional Speech Recognition with Pitch and Voice Quality Features
- Self-Training for End-to-End Speech Translation
- Data Techniques For Online End-to-end Speech Recognition
- Adversarial Meta Sampling for Multilingual Low-Resource Speech Recognition
- End-to-End Learning of Speech 2D Feature-Trajectory for Prosthetic Hands
- EasyASR: A Distributed Machine Learning Platform for End-to-end Automatic Speech Recognition
- Speech recognition for air traffic control via feature learning and end-to-end training
- Improving Distinction between ASR Errors and Speech Disfluencies with Feature Space Interpolation
- Fine-Grained Classroom Activity Detection from Audio with Neural Networks
- CAT: A CTC-CRF based ASR Toolkit Bridging the Hybrid and the End-to-end Approaches towards Data Efficiency and Low Latency
- Incorporating VAD into ASR System by Multi-task Learning
- Multimodal Aggregation Approach for Memory Vision-Voice Indoor Navigation with Meta-Learning
- Population Based Training for Data Augmentation and Regularization in Speech Recognition
- A Comparison of Discrete Latent Variable Models for Speech Representation Learning
- Influence of ASR and Language Model on Alzheimer's Disease Detection