9 citations · 32 across the 22 of their papers we have counts for
7 papers · 1 filter
Lookahead When It Matters: Adaptive Non-causal Transformers for Streaming Neural Transducers
Grant P. Strimel, Yi Xie, Brian King +3
Streaming speech recognition architectures are employed for low-latency, real-time applications. Such architectures are often characterized by their causality. Causal architectures…
Leveraging Redundancy in Multiple Audio Signals for Far-Field Speech Recognition
Feng-Ju Chang, Anastasios Alexandridis, Rupak Vignesh Swaminathan +6
To achieve robust far-field automatic speech recognition (ASR), existing techniques typically employ an acoustic front end (AFE) cascaded with a neural transducer (NT) ASR model. T…
Sub-8-Bit Quantization Aware Training for 8-Bit Neural Network Accelerator with On-Device Speech Recognition
Kai Zhen, Hieu Duy Nguyen, Raviteja Chinta +4
We present a novel sub-8-bit quantization-aware training (S8BQAT) scheme for 8-bit neural network accelerators. Our method is inspired from Lloyd-Max compression theory with practi…
Multi-Channel Transformer Transducer for Speech Recognition
Feng-Ju Chang, Martin Radfar, Athanasios Mouchtaris +1
Multi-channel inputs offer several advantages over single-channel, to improve the robustness of on-device speech recognition systems. Recent work on multi-channel transformer, has…
End-to-End Multi-Channel Transformer for Speech Recognition
Feng-Ju Chang, Martin Radfar, Athanasios Mouchtaris +2
Transformers are powerful neural architectures that allow integrating different modalities using attention mechanisms. In this paper, we leverage the neural transformer architectur…
Tie Your Embeddings Down: Cross-Modal Latent Spaces for End-to-end Spoken Language Understanding
Bhuvan Agrawal, Markus Müller, Martin Radfar +3
End-to-end (E2E) spoken language understanding (SLU) systems can infer the semantics of a spoken utterance directly from an audio signal. However, training an E2E system remains a…
Streaming End-to-End Bilingual ASR Systems with Joint Language Identification
Surabhi Punjabi, Harish Arsikere, Zeynab Raeesy +11
Multilingual ASR technology simplifies model training and deployment, but its accuracy is known to depend on the availability of language information at runtime. Since language ide…