A real-time end-to-end multilingual speech recognition architecture
J Gonzalez-Dominguez, D Eustis… - IEEE Journal of …, 2014 - ieeexplore.ieee.org
Automatic speech recognition (ASR) systems are used daily by millions of people worldwide
to dictate messages, control devices, initiate searches or to facilitate data input in small …
to dictate messages, control devices, initiate searches or to facilitate data input in small …
Leveraging language id in multilingual end-to-end speech recognition
Recent advances in end-to-end speech recognition have made it possible to build
multilingual models, capable of recognizing speech in multiple languages. Multilingual …
multilingual models, capable of recognizing speech in multiple languages. Multilingual …
MediaParl: Bilingual mixed language accented speech database
MediaParl is a Swiss accented bilingual database containing recordings in both French and
German as they are spoken in Switzerland. The data were recorded at the Valais …
German as they are spoken in Switzerland. The data were recorded at the Valais …
Multilingual speech recognition training and adaptation with language-specific gate units
D Liu, X Wan, J Xu, P Zhang - 2018 11th International …, 2018 - ieeexplore.ieee.org
Multi-task learning (MTL) framework is usually adopted to build automatic speech
recognition (ASR) system for multiple languages. The shared-hidden-layer multilingual deep …
recognition (ASR) system for multiple languages. The shared-hidden-layer multilingual deep …
Dyn-asr: Compact, multilingual speech recognition via spoken language and accent identification
S Ghangam, D Whitenack, J Nemecek - arXiv preprint arXiv:2108.02034, 2021 - arxiv.org
Running automatic speech recognition (ASR) on edge devices is non-trivial due to resource
constraints, especially in scenarios that require supporting multiple languages. We propose …
constraints, especially in scenarios that require supporting multiple languages. We propose …
[PDF][PDF] On recognition of non-native speech using probabilistic lexical model
M Razavi, M Magimai-Doss - … of the 15th Annual Conference of …, 2014 - infoscience.epfl.ch
Despite various advances in automatic speech recognition (ASR) technology, recognition of
speech uttered by non-native speakers is still a challenging problem. In this paper, we …
speech uttered by non-native speakers is still a challenging problem. In this paper, we …
DYN-ASR: Compact, multilingual speech recognition via spoken language and accent identification
SG Manepalli, D Whitenack… - 2021 IEEE 7th World …, 2021 - ieeexplore.ieee.org
Running automatic speech recognition (ASR) on edge devices is non-trivial due to resource
constraints, especially in scenarios that require supporting multiple languages. We propose …
constraints, especially in scenarios that require supporting multiple languages. We propose …
[PDF][PDF] Biometric Person Identification using Multilingual Speech Processing
TKSV Jain - academia.edu
In this paper we explain the multilingual speaker identification system. Speaker identification
is conducted on 3 Indian languages Hindi, Marathi and Rajasthani. We create a database of …
is conducted on 3 Indian languages Hindi, Marathi and Rajasthani. We create a database of …
[PDF][PDF] MFCC Analysis of Biometric Person Identification System in Multilingual Speech Environment
TK Sahu, V Jain - academia.edu
In this paper we explain the multilingual speaker identification system. Speaker identification
is conducted on 3 Indian languages (Hindi, Marathi and Rajasthani). We create a database …
is conducted on 3 Indian languages (Hindi, Marathi and Rajasthani). We create a database …
[PDF][PDF] Image-based Activity Recognition using UAVs
H Caesar - 2014 - researchgate.net
In this chapter we introduce the reader to the topic and contents of this work. Section 1.1
explains what activity recognition is and where it can be used. The general questions that …
explains what activity recognition is and where it can be used. The general questions that …