Related papers: Robust Wake-Up Word Detection by Two-stage Multi-r…

Fast and accurate spoken content retrieval is vital for applications such as voice search. Query-by-Example Spoken Term Detection (STD) involves retrieving matching segments from an audio database given a spoken query. Token-based STD…

Always-on spoken language interfaces, e.g. personal digital assistants, rely on a wake word to start processing spoken input. We present novel methods to train a hybrid DNN/HMM wake word detection system from partially labeled training…

Interactions with virtual assistants typically start with a trigger phrase followed by a command. In this work, we explore the possibility of making these interactions more natural by eliminating the need for a trigger phrase. Our goal is…

This paper further explores our previous wake word spotting system ranked 2-nd in Track 1 of the MISP Challenge 2021. First, we investigate a robust unimodal approach based on 3D and 2D convolution and adopt the simple attention module…

In this work, we present a two-stage method for speaker extraction under reverberant and noisy conditions. Given a reference signal of the desired speaker, the clean, but the still reverberant, desired speaker is first extracted from the…

In this work, we propose a classifier for distinguishing device-directed queries from background speech in the context of interactions with voice assistants. Applications include rejection of false wake-ups or unintended interactions as…

This paper proposes a dual-stage, low complexity, and reconfigurable technique to enhance the speech contaminated by various types of noise sources. Driven by input data and audio contents, the proposed dual-stage speech enhancement…

Automatic speaker verification, like every other biometric system, is vulnerable to spoofing attacks. Using only a few minutes of recorded voice of a genuine client of a speaker verification system, attackers can develop a variety of…

Weakly supervised video anomaly detection (WS-VAD) is a crucial area in computer vision for developing intelligent surveillance systems. This system uses three feature streams: RGB video, optical flow, and audio signals, where each stream…

In automatic speech recognition, often little training data is available for specific challenging tasks, but training of state-of-the-art automatic speech recognition systems requires large amounts of annotated speech. To address this…

The rapid proliferation of IoT nodes equipped with microphones and capable of performing on-device audio classification exposes highly sensitive data while operating under tight resource constraints. To protect against this, we present a…

Speech emotion recognition is a challenging task, and extensive reliance has been placed on models that use audio features in building well-performing classifiers. In this paper, we propose a novel deep dual recurrent encoder model that…

Noisy labels can impair model performance, making the study of learning with noisy labels an important topic. Two conventional approaches are noise modeling and noise detection. However, these two methods are typically studied…

Identifying emotion from speech is a non-trivial task pertaining to the ambiguous definition of emotion itself. In this work, we adopt a feature-engineering based approach to tackle the task of speech emotion recognition. Formalizing our…

Recently, video recognition is emerging with the help of multi-modal learning, which focuses on integrating distinct modalities to improve the performance or robustness of the model. Although various multi-modal learning methods have been…

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…

In recent years, self-supervised learning (SSL) models have made significant progress in audio deepfake detection (ADD) tasks. However, existing SSL models mainly rely on large-scale real speech for pre-training and lack the learning of…

Most sound event detection (SED) systems perform well on clean datasets but degrade significantly in noisy environments. Language-queried audio source separation (LASS) models show promise for robust SED by separating target events;…

Self-supervised learning method that provides generalized speech representations has recently received increasing attention. Wav2vec 2.0 is the most famous example, showing remarkable performance in numerous downstream speech processing…

The deep learning models used for speaker verification rely heavily on large amounts of data and correct labeling. However, noisy (incorrect) labels often occur, which degrades the performance of the system. In this paper, we propose a…