Combining hybrid DNN-HMM ASR systems with attention-based models using lattice rescoring

Li, Qiujia; Zhang, Chao; Woodland, Philip C.

doi:10.1016/j.specom.2022.12.002

Cited by 7 publications

(1 citation statement)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further a deep neural network as a part of a hybrid Deep neural network-HMM model is applied on a small -scale speech task [16]. Later, a pretrained DNN-HMM is considered on acoustic modeling with varying depths of networks [17]. Further, the Deep neural network is used for speech recognition for large vocabulary speech tasks [18].…”

Section: Introductionmentioning

confidence: 99%

Convolution neural networks with hybrid feature extraction methods for classification of voice sound signals

Rashmi¹,

Singh²

2023

World J. Adv. Eng. Technol. Sci.

View full text Add to dashboard Cite

The convolutional neural networks (CNNs) lead in the domain of Sound Recognition due to its flexibility and ability with different adjusting parameters. The recognition of spoken English Alphabets by different people with deep learning techniques attracted the research community. In this paper, we are exploring the use of convolutional neural network (CNN), a deep learner that can automatically learn features directly from the dataset while training for the classification of sounds signals of English alphabets. In this proposed work, we consider two CNN architectures. In first architecture, we propose MFCC based features for pretrained two convolutional layer CNN architecture. In the second architecture, we propose a hybrid feature extraction method to train a block-based CNN architecture. The proposed systems consist of two components namely hybrid feature extraction and CNN classifier. The five auditory features log-Mel spectrogram (LM), MFCC, chroma, spectral contrast and Tonnetz features are extracted and then LM & MFCC are combined as one feature set. LM, MFCC, and CST features are aggregated as another for training to the proposed two CNNs, respectively. The different sound samples of English alphabets are collected from different people of different age groups. The feature sets collected from the hybrid feature extraction methods are presented to both the proposed CNNs and the experimental results are collected. The experimental results indicate that the taxonomic accuracy of the proposed architectures can surpass the existing methods of CNNs with single feature extraction methods. The proposed second architecture performs more effectively over the proposed first CNN architecture.

show abstract

Section: Introductionmentioning

confidence: 99%

Convolution neural networks with hybrid feature extraction methods for classification of voice sound signals

Rashmi¹,

Singh²

2023

World J. Adv. Eng. Technol. Sci.

View full text Add to dashboard Cite

show abstract

Voice Enabled Form Filling Using Hidden Markov Model

Sallagundla,

Kethavath,

Mitaigiri

et al. 2024

Communications in Computer and Information Science

View full text Add to dashboard Cite

Exploiting beam search confidence for energy-efficient speech recognition

Pinto,

Arnau,

Riera

et al. 2024

J Supercomput

View full text Add to dashboard Cite

With mobile and embedded devices getting more integrated in our daily lives, the focus is increasingly shifting toward human-friendly interfaces, making automatic speech recognition (ASR) a central player as the ideal means of interaction with machines. ASR is essential for many cognitive computing applications, such as speech-based assistants, dictation systems and real-time language translation. Consequently, interest in speech technology has grown in the last few years, with more systems being proposed and higher accuracy levels being achieved, even surpassing human accuracy. However, highly accurate ASR systems are computationally expensive, requiring on the order of billions of arithmetic operations to decode each second of audio, which conflicts with a growing interest in deploying ASR on edge devices. On these devices, efficient hardware acceleration is key for achieving acceptable performance. In this paper, we propose a technique to improve the energy efficiency and performance of ASR systems, focusing on low-power hardware for edge devices. We focus on optimizing the DNN-based acoustic model evaluation, as we have observed it to be the main bottleneck in popular ASR systems, by leveraging run-time information from the beam search. By doing so, we reduce energy and execution time of the acoustic model evaluation by 25.6 and 25.9 %, respectively, with negligible accuracy loss.

show abstract

Combining hybrid DNN-HMM ASR systems with attention-based models using lattice rescoring

Cited by 7 publications

References 43 publications

Convolution neural networks with hybrid feature extraction methods for classification of voice sound signals

Convolution neural networks with hybrid feature extraction methods for classification of voice sound signals

Voice Enabled Form Filling Using Hidden Markov Model

Exploiting beam search confidence for energy-efficient speech recognition

Contact Info

Product

Resources

About