Current state-of-the-art automatic speech recognition systems are trained to work in
specificdomains', defined based on factors like application, sampling rate and codec. When …

We present a frontend for improving robustness of automatic speech recognition (ASR), that
jointly implements three modules within a single model: acoustic echo cancellation, speech …

This work introduces cross-attention conformer, an attention-based architecture for context
modeling in speech enhancement. Given that the context information can often be …

Recognition of accented speech is a long-standing challenge for automatic speech
recognition (ASR) systems, given the increasing worldwide population of bi-lingual speakers …

We propose two approaches for speaker adaptation in end-to-end (E2E) automatic speech
recognition systems. One is Kullback-Leibler divergence (KLD) regularization and the other …

In this paper, we present an incremental domain adaptation technique to prevent
catastrophic forgetting for an end-to-end automatic speech recognition (ASR) model …

Building deep neural network acoustic models directly based on far-field speech from
multiple recording environments with different acoustic properties is an increasingly popular …

End-to-end automatic speech recognition (ASR) has simplified the traditional ASR system
building pipeline by eliminating the need to have multiple components and also the …

Non-native speech causes automatic speech recognition systems to degrade in
performance. Past strategies to address this challenge have considered model adaptation …

Recently, Feature-wise Linear Modulation (FiLM) has been shown to outperform other
approaches to incorporate speaker embedding into speech separation and VoiceFilter …