Automatic speech recognition system for tonal languages: State-of-the-art survey

J Kaur, A Singh, V Kadyan - Archives of Computational Methods in …, 2021 - Springer
Natural language and human–machine interaction is a very much traversed as well as
challenging research domain. However, the main objective is of getting the system that can …

[PDF][PDF] Data augmentation, feature combination, and multilingual neural networks to improve ASR and KWS performance for low-resource languages.

Z Tüske, P Golik, D Nolden, R Schlüter, H Ney - Interspeech, 2014 - academia.edu
This paper presents the progress of acoustic models for lowresourced languages
(Assamese, Bengali, Haitian Creole, Lao, Zulu) developed within the second evaluation …

Compensating for speaker or lexical variabilities in speech for emotion recognition

S Mariooryad, C Busso - Speech Communication, 2014 - Elsevier
Affect recognition is a crucial requirement for future human machine interfaces to effectively
respond to nonverbal behaviors of the user. Speech emotion recognition systems analyze …

Multilingual MRASTA features for low-resource keyword search and speech recognition systems

Z Tüske, D Nolden, R Schlüter… - 2014 IEEE International …, 2014 - ieeexplore.ieee.org
This paper investigates the application of hierarchical MRASTA bottleneck (BN) features for
under-resourced languages within the IARPA Babel project. Through multilingual training of …

Mandarin tone classification without pitch tracking

N Ryant, J Yuan, M Liberman - 2014 IEEE international …, 2014 - ieeexplore.ieee.org
A deep neural network (DNN) based classifier achieved 27.38% frame error rate (FER) and
15.62% segment error rate (SER) in recognizing five tonal categories in Mandarin Chinese …

Improving mandarin tone recognition based on dnn by combining acoustic and articulatory features using extended recognition networks

J Lin, W Li, Y Gao, Y **e, NF Chen… - Journal of Signal …, 2018 - Springer
In this paper, we investigate the effectiveness of articulatory information for Mandarin tone
modeling and recognition in a deep neural network–hidden Markov model (DNN-HMM) …

[PDF][PDF] Tone Classification in Mandarin Chinese Using Convolutional Neural Networks.

C Chen, RC Bunescu, L Xu, C Liu - Interspeech, 2016 - isca-archive.org
In tone languages, different tone patterns of the same syllable may convey different
meanings. Tone perception is important for sentence recognition in noise conditions …

[PDF][PDF] Highly accurate mandarin tone classification in the absence of pitch information

N Ryant, M Slaney, M Liberman… - … of Speech Prosody, 2014 - researchgate.net
A deep neural network (DNN) classifier based only on 40 mel-frequency cepstral coefficients
(MFCCs) achieved 29.99% frame error rate (FER) and 16.86% segment error rate (SER) in …

Prosody features based low resource Punjabi children ASR and T-NT classifier using data augmentation

V Kadyan, T Hasija, A Singh - Multimedia Tools and Applications, 2023 - Springer
Automatic children speech recognition is always challenging due to limited corpus and
varying acoustic features. One among those is zero speech corpus and large acoustic …

English broadcast news speech recognition by humans and machines

S Thomas, M Suzuki, Y Huang, G Kurata… - ICASSP 2019-2019 …, 2019 - ieeexplore.ieee.org
With recent advances in deep learning, considerable attention has been given to achieving
automatic speech recognition performance close to human performance on tasks like …