SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network

Domain:

natural language processing

Record type:

papermodeldataset

Creator:

ChaParLee

Host:

We present SpeechStew, a speech recognition model that is trained on a combination of various publicly available speech recognition datasets: AMI, Broadcast News, Common Voice, LibriSpeech, Switchboard/Fisher, Tedlium, and Wall Street Journal. SpeechStew simply mixes all of these datasets together, without any special re-weighting or re-balancing of the datasets. SpeechStew achieves SoTA or near SoTA results across a variety of tasks, without the use of an external language model. Our results include 9.0\% WER on AMI-IHM, 4.7\% WER on Switchboard, 8.3\% WER on CallHome, and 1.3\% on WSJ, which significantly outperforms prior work with strong external language models. We also demonstrate that SpeechStew learns powerful transfer learning representations. We fine-tune SpeechStew on a noisy low resource speech dataset, CHiME-6. We achieve 38.9\% WER without a language model, which compares to 38.6\% WER to a strong HMM baseline with a language model. submitted to INTERSPEECH

Visit

arxiv.org

Tasks

automatic speech recognition speech processing

Neural Network Based Hausa Language Speech Recognition

NEURAL NETWORK BASED ARCHITECTURE FOR AUTOMATIC SPEECH RECOGNITION IN YORUBA

The Application of Probabilistic Neural Network in Speech Recognition Based on Partition Clustering

A probabilistic neural network (PNN) speech recognition model based on the partition clustering algo

Advanced Convolutional Neural Network-Based Hybrid Acoustic Models for Low-Resource Speech Recognition

Deep neural networks (DNNs) have shown a great achievement in acoustic modeling for speech recogniti

Convolutional neural network for speech emotion recognition in the Moroccan Arabic dialect language

Extracting the speaker's emotional state has become an active research topic lately due to the deman