Search Results for author:
Found 6 papers, 0 papers with code
Accelerator-Aware Training for Transducer-Based Speech Recognition
Machine learning model weights and activations are represented in full-precision during training.
Leveraging Redundancy in Multiple Audio Signals for Far-Field Speech Recognition
We augment the MC fusion networks to a conformer transducer model and train it in an end-to-end fashion.
Contextual-Utterance Training for Automatic Speech Recognition
Also, we propose a dual-mode contextual-utterance training technique for streaming automatic speech recognition (ASR) systems.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
ConvRNN-T: Convolutional Augmented Recurrent Neural Network Transducers for Streaming Speech Recognition
Very recently, as an alternative to LSTM layers, the Conformer architecture was introduced where the encoder of RNN-T is replaced with a modified Transformer encoder composed of convolutional layers at the frontend and between attention layers.
CoDERT: Distilling Encoder Representations with Co-learning for Transducer-based Speech Recognition
We find that tandem training of teacher and student encoders with an inplace encoder distillation outperforms the use of a pre-trained and static teacher transducer.
Exploiting Large-scale Teacher-Student Training for On-device Acoustic Models
We present results from Alexa speech teams on semi-supervised learning (SSL) of acoustic models (AM) with experiments spanning over 3000 hours of GPU time, making our study one of the largest of its kind.
