1 |
Multistream neural architectures for cued-speech recognition using a pre-trained visual feature extractor and constrained CTC decoding
|
|
|
|
In: ICASSP 2022 - IEEE International Conference on Acoustics, Speech and Signal Processing ; https://hal.archives-ouvertes.fr/hal-03578503 ; ICASSP 2022 - IEEE International Conference on Acoustics, Speech and Signal Processing, May 2022, Singapour, Singapore (2022)
|
|
BASE
|
|
Show details
|
|
2 |
Multistream neural architectures for cued-speech recognition using a pre-trained visual feature extractor and constrained CTC decoding
|
|
|
|
In: ICASSP 2022 - IEEE International Conference on Acoustics, Speech and Signal Processing ; https://hal.archives-ouvertes.fr/hal-03578503 ; ICASSP 2022 - IEEE International Conference on Acoustics, Speech and Signal Processing, May 2022, Singapour, Singapore (2022)
|
|
BASE
|
|
Show details
|
|
3 |
Estimating Vocal Tract Resonances of Synthesized High-Pitched Vowels Using CNN ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Characterizing News Portrayal of Civil Unrest in Hong Kong, 1998–2020 ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Jibes & Delights: A Dataset of Targeted Insults and Compliments to Tackle Online Abuse ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Bird’s Eye: Probing for Linguistic Graph Structures with a Simple Information-Theoretic Approach ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Face Biometric Spoof Detection Method Using a Remote Photoplethysmography Signal
|
|
|
|
In: Sensors; Volume 22; Issue 8; Pages: 3070 (2022)
|
|
BASE
|
|
Show details
|
|
8 |
ECG Recurrence Plot-Based Arrhythmia Classification Using Two-Dimensional Deep Residual CNN Features
|
|
|
|
In: Sensors; Volume 22; Issue 4; Pages: 1660 (2022)
|
|
BASE
|
|
Show details
|
|
9 |
Automatic Classification Framework of Tongue Feature Based on Convolutional Neural Networks
|
|
|
|
In: Micromachines; Volume 13; Issue 4; Pages: 501 (2022)
|
|
BASE
|
|
Show details
|
|
10 |
Short Text Aspect-Based Sentiment Analysis Based on CNN + BiGRU
|
|
|
|
In: Applied Sciences; Volume 12; Issue 5; Pages: 2707 (2022)
|
|
BASE
|
|
Show details
|
|
11 |
Impact of Sentence Representation Matching in Neural Machine Translation
|
|
|
|
In: Applied Sciences; Volume 12; Issue 3; Pages: 1313 (2022)
|
|
BASE
|
|
Show details
|
|
12 |
A Combined Text-Based and Metadata-Based Deep-Learning Framework for the Detection of Spam Accounts on the Social Media Platform Twitter
|
|
|
|
In: Processes; Volume 10; Issue 3; Pages: 439 (2022)
|
|
BASE
|
|
Show details
|
|
13 |
Application of Modern Digital Systems and Approaches to Business Process Management
|
|
|
|
In: Sustainability; Volume 14; Issue 3; Pages: 1697 (2022)
|
|
BASE
|
|
Show details
|
|
14 |
BenSignNet: Bengali Sign Language Alphabet Recognition Using Concatenated Segmentation and Convolutional Neural Network
|
|
|
|
In: Applied Sciences; Volume 12; Issue 8; Pages: 3933 (2022)
|
|
BASE
|
|
Show details
|
|
15 |
Bangla Sign Language (BdSL) Alphabets and Numerals Classification Using a Deep Learning Model
|
|
|
|
In: Sensors; Volume 22; Issue 2; Pages: 574 (2022)
|
|
BASE
|
|
Show details
|
|
16 |
TASE: Task-Aware Speech Enhancement for Wake-Up Word Detection in Voice Assistants
|
|
|
|
In: Applied Sciences; Volume 12; Issue 4; Pages: 1974 (2022)
|
|
Abstract:
Wake-up word spotting in noisy environments is a critical task for an excellent user experience with voice assistants. Unwanted activation of the device is often due to the presence of noises coming from background conversations, TVs, or other domestic appliances. In this work, we propose the use of a speech enhancement convolutional autoencoder, coupled with on-device keyword spotting, aimed at improving the trigger word detection in noisy environments. The end-to-end system learns by optimizing a linear combination of losses: a reconstruction-based loss, both at the log-mel spectrogram and at the waveform level, as well as a specific task loss that accounts for the cross-entropy error reported along the keyword spotting detection. We experiment with several neural network classifiers and report that deeply coupling the speech enhancement together with a wake-up word detector, e.g., by jointly training them, significantly improves the performance in the noisiest conditions. Additionally, we introduce a new publicly available speech database recorded for the Telefónica’s voice assistant, Aura. The OK Aura Wake-up Word Dataset incorporates rich metadata, such as speaker demographics or room conditions, and comprises hard negative examples that were studiously selected to present different levels of phonetic similarity with respect to the trigger words “OK Aura”.
|
|
Keyword:
convolutional neural network; deep learning; keyword spotting; speech enhancement; wake-up word
|
|
URL: https://doi.org/10.3390/app12041974
|
|
BASE
|
|
Hide details
|
|
17 |
Factors Influencing Students’ Intention to Use E-Textbooks and Their Impact on Academic Achievement in Bilingual Environment: An Empirical Study Jordan
|
|
|
|
In: Information; Volume 13; Issue 5; Pages: 233 (2022)
|
|
BASE
|
|
Show details
|
|
18 |
Active Binaural Auditory Perceptual System for a Socially Interactive Humanoid Robot
|
|
|
|
In: Engineering Proceedings; Volume 12; Issue 1; Pages: 83 (2022)
|
|
BASE
|
|
Show details
|
|
19 |
Rethinking the Methods and Algorithms for Inner Speech Decoding and Making Them Reproducible
|
|
|
|
In: NeuroSci; Volume 3; Issue 2; Pages: 226-244 (2022)
|
|
BASE
|
|
Show details
|
|
20 |
Multitask Pointer Network for Multi-Representational Parsing
|
|
|
|
BASE
|
|
Show details
|
|
|
|