Tom O'Malley — accepted AI-conference papers

2023

Cleanformer: A Multichannel Array Configuration-Invariant Neural Enhancement Frontend for ASR in Smart Speakers

Joseph Caroselli, Arun Narayanan, Nathan Howard, Tom O'Malley

ICASSP 2023accepted

This work introduces Cleanformer —a streaming multichannel neural enhancement frontend for automatic speech recognition (ASR). This model has a Conformer-based architecture which takes as inputs a single channel each of raw and enhanced signals, and uses self-attention to derive a time-frequency mas…

Cited by 0 Source ↗Scholar ↗

2023

Conditional Conformer: Improving Speaker Modulation For Single And Multi-User Speech Enhancement

Tom O'Malley, Shaojin Ding, Arun Narayanan, Quan Wang, Rajeev Rikhye, Qiao Liang +2

ICASSP 2023accepted

Recently, Feature-wise Linear Modulation (FiLM) has been shown to outperform other approaches to incorporate speaker embedding into speech separation and VoiceFilter models. We propose an improved method of incorporating such embeddings into a Voice- Filter frontend for automatic speech recognition…

Cited by 5 Source ↗Scholar ↗