research
∙
06/01/2023
Quantization-Aware and Tensor-Compressed Training of Transformers for Natural Language Understanding
Fine-tuned transformer models have shown superior performances in many n...
share
research
∙
04/03/2023
Dual-Attention Neural Transducers for Efficient Wake Word Spotting in Speech Recognition
We present dual-attention neural biasing, an architecture designed to bo...
research
∙
05/26/2022
Contextual Adapters for Personalized Speech Recognition in Neural Transducers
Personal rare word recognition in end-to-end Automatic Speech Recognitio...
research
∙
11/05/2021
Context-Aware Transformer Transducer for Speech Recognition
End-to-end (E2E) automatic speech recognition (ASR) systems often have d...
research
∙
10/31/2021
FANS: Fusing ASR and NLU for on-device SLU
Spoken language understanding (SLU) systems translate voice input comman...
research
∙
06/11/2021
Exploiting Large-scale Teacher-Student Training for On-device Acoustic Models
We present results from Alexa speech teams on semi-supervised learning (...
research
∙
02/08/2021
End-to-End Multi-Channel Transformer for Speech Recognition
Transformers are powerful neural architectures that allow integrating di...
research
∙
11/18/2020
Tie Your Embeddings Down: Cross-Modal Latent Spaces for End-to-end Spoken Language Understanding
End-to-end (E2E) spoken language understanding (SLU) systems can infer t...
research
∙
08/12/2020
End-to-End Neural Transformer Based Spoken Language Understanding
Spoken language understanding (SLU) refers to the process of inferring t...
research
∙
07/08/2020
