AIConfPaper
← Search

Anastasios Alexandridis

6 accepted papers

2023

Dual-Attention Neural Transducers for Efficient Wake Word Spotting in Speech Recognition

Saumya Y. Sahai, Jing Liu, Thejaswi Muniyappa, Kanthashree Mysore Sathyendra, Anastasios Alexandridis, Grant P. Strimel +5
ICASSP 2023accepted

We present dual-attention neural biasing, an architecture designed to boost Wake Words (WW) recognition and improve inference time latency on speech recognition tasks. This architecture enables a dynamic switch for its runtime compute paths by exploiting WW spotting to select which branch of its att…

Cited by 6Source ↗Scholar ↗
2023

Gated Contextual Adapters For Selective Contextual Biasing In Neural Transducers

Anastasios Alexandridis, Kanthashree Mysore Sathyendra, Grant P. Strimel, Feng-Ju Chang, Ariya Rastrow, Nathan Susanj +1
ICASSP 2023accepted

Neural contextual biasing for end-to-end neural ASR transducers has shown significant improvements in the recognition of named entities, such as contact names or device names. However, it comes with the cost of increased compute, as the biasing layers (which are usually based on cross-attention) add…

Cited by 12Source ↗Scholar ↗
2023

Multilingual End-To-End Spoken Language Understanding For Ultra-Low Footprint Applications

Markus Müller, Anastasios Alexandridis, Zach Trozenski, Joel Whiteman, Grant P. Strimel, Nathan Susanj +2
ICASSP 2023accepted

Tiny Signal-to-Interpretation (TinyS2I) has been recently introduced as an ultra low-footprint end-to-end spoken language understanding (SLU) model. This architecture is capable of running in ultra resource constrained environments like voice assistant devices, while at the same time reducing latenc…

Cited by 0Source ↗Scholar ↗
2022

Caching Networks: Capitalizing on Common Speech for ASR

Anastasios Alexandridis, Grant P. Strimel, Ariya Rastrow, Pavel Kveton, Jon Webb, Maurizio Omologo +2
ICASSP 2022accepted

We introduce Caching Networks (CachingNets), a speech recognition network architecture capable of delivering faster, more accurate decoding by leveraging common speech patterns. By explicitly incorporating select sentences unique to each user into the network’s design, we show how to train the model…

Cited by 0Source ↗Scholar ↗
2022

TINYS2I: A Small-Footprint Utterance Classification Model with Contextual Support for On-Device SLU

Anastasios Alexandridis, Kanthashree Mysore Sathyendra, Grant P. Strimel, Pavel Kveton, Jon Webb, Athanasios Mouchtaris
ICASSP 2022accepted

On-device spoken language understanding (SLU) offers the potential for significant latency savings compared to cloud-based processing, as the audio stream does not need to be transmitted to a server. We present Tiny Signal-to-interpretation (TinyS2I), an end-to-end on-device SLU approach which is fo…

Cited by 0Source ↗Scholar ↗
2017

Towards wireless acoustic sensor networks for location estimation and counting of multiple speakers in real-life conditions

Anastasios Alexandridis, Nikolaos Stefanakis, Athanasios Mouchtaris
ICASSP 2017accepted

Speaker localization and counting in real-life conditions remains a challenging task. The computational burden, transmission usage and synchronization issues pose several limitations. Moreover, the physical characteristics of real speakers in terms of directivity pattern and orientation, as well as…

Cited by 0Source ↗Scholar ↗