Large Vocabulary Continuous Speech Recognition With Reservoir-Based Acoustic Models

Triefenbach, Fabian; Demuynck, Kris; Martens, Jean‐Pierre

doi:10.1109/lsp.2014.2302080

Cited by 27 publications

(17 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Echo State Networks (ESNs), proposed by Herbert Jaeger [15], are a special kind of Recurrent Neural Networks (RNNs) and have achieved comparable results to CNNs in several recognition tasks, such as speech and image recognition [16], [17]. However, they are fairly new in the context of Music Information Retrieval (MIR).…”

Section: Introductionmentioning

confidence: 99%

Multipitch tracking in music signals using Echo State Networks

Steiner

Stone

Birkholz

et al. 2021

2020 28th European Signal Processing Conference (EUSIPCO)

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Multipitch tracking in music signals using Echo State Networks

Steiner

Stone

Birkholz

et al. 2021

2020 28th European Signal Processing Conference (EUSIPCO)

View full text Add to dashboard Cite

“…Note that the masking scheme and BP algorithm is easily extended to multidimensional in -and output sequences (more details are provided in the Supplementary material). The TIMIT task has been studied before in the context of RC, which has shown it to be challenging, typically requiring extremely large reservoirs to obtain competitive performance [26,27]. For all these tasks we compared performance of the fully trained system to traditional RC, where we kept the input and bias masks fixed and random, and only optimised their global scaling and the feedback strength parameter µ.…”

mentioning

confidence: 99%

Embodiment of Learning in Electro-Optical Signal Processors

et al. 2016

View full text Add to dashboard Cite

Delay-coupled electro-optical systems have received much attention for their dynamical properties and their potential use in signal processing. In particular it has recently been demonstrated, using the artificial intelligence algorithm known as reservoir computing, that photonic implementations of such systems solve complex tasks such as speech recognition. Here we show how the backpropagation algorithm can be physically implemented on the same electro-optical delay-coupled architecture used for computation with only minor changes to the original design. We find that, compared when the backpropagation algorithm is not used, the error rate of the resulting computing device, evaluated on three benchmark tasks, decreases considerably. This demonstrates that electro-optical analog computers can embody a large part of their own training process, allowing them to be applied to new, more difficult tasks.Published version : http://dx

show abstract

“…[16] 8.5 6.5 RC-HMM, [17] 6.2 3.9 GMM-HMM (ML), [17] 6.0 3.8 GMM-HMM (MMI+VTLN), [16] -3.0 DNN-HMM (STC features), [18] 5.2 - Table 2 shows a recapitulation of the key performances of some state-of-the-art systems in the field. The fisrt two systems in the list are based on a GMM-HMM acoustic models: the first one was trained using the maximum-likelihood (ML) criteria [17], while the second one using the maximum mutual information (MMI) criteria with the vocal tract length normalization (VTLN) [16].Triefenbach et al [17], proposed also a Reservoir Computing (RC) HMM hybrid system for phoneme recognition using a bigram phonotactic utterance model. The RC-HMM performs significantly better than the MLP-HMM hybrids proposed by Gemello et al [19].…”

Section: Read Continuous Speech Recognition Taskmentioning

confidence: 99%

Recent advances in LVCSR : A benchmark comparison of performances

Errattahi

2017

IJECE

View full text Add to dashboard Cite

Large Vocabulary Continuous Speech Recognition (LVCSR), which is characterized by a high variability of the speech, is the most challenging task in automatic speech recognition (ASR). Believing that the evaluation of ASR systems on relevant and common speech corpora is one of the key factors that help accelerating research, we present, in this paper, a benchmark comparison of the performances of the current state-of-the-art LVCSR systems over different speech recognition tasks. Furthermore, we put objectively into evidence the best performing technologies and the best accuracy achieved so far in each task. The benchmarks have shown that the Deep Neural Networks and Convolutional Neural Networks have proven their efficiency on several LVCSR tasks by outperforming the traditional Hidden Markov Models and Guaussian Mixture Models. They have also shown that despite the satisfying performances in some LVCSR tasks, the problem of large-vocabulary speech recognition is far from being solved in some others, where more research efforts are still needed.Copyright c 2017 Institute of Advanced Engineering and Science.All rights reserved.Corresponding Author: Rahhal Errattahi Laboratory of Information Technology, National School of Applied Sciences, University of Chouaib Doukkali, EL Jadida, Morocco errattahi.r@ucd.ac.ma INTRODUCTIONSpeech is a natural and fundamental communication vehicle which can be considered as one of the most appropriate media for human-machine interactions. The aim of Automatic Speech Recognition (ASR) systems is to convert a speech signal into a sequence of words either for text-based communication purposes or for device controlling. ASR is usually used when the keyboard becomes inconvenient such, for example, when our hands are busy or with limited mobility, when we are using the phone, we are in the dark, or we are moving around etc. ASR finds application in many different areas: dictation, meeting and lectures transcription, speech translation, voice-search, phone based services and others. Those systems are, in general, extremely dependent on the data used for training the models, configuration of front-ends etc. Hence a large part of system development usually involves investigations of appropriate configurations for a new domain, new training data, and new language.There are several tasks of speech recognition and the difference between these tasks rests mainly on: (i) the speech type (isolated or continuous speech), (ii) the speaker mode (speaker dependent or independent), (iii) the vocabulary size (small, medium or large) and (iv) the speaking style (read or spontaneous speech). Even though ASR has matured to the point of commercial applications, the Speaker Independent Large Vocabulary Continuous Speech Recognition tasks (commonly designed as LVCSR) pose a particular challenge to ASR technology developers. Three of the major problems that arise when LVCSR systems are being developed are: First speaker independent systems require a large amount of training data in order to cover speak...

show abstract

Large Vocabulary Continuous Speech Recognition With Reservoir-Based Acoustic Models

Cited by 27 publications

References 45 publications

Multipitch tracking in music signals using Echo State Networks

Multipitch tracking in music signals using Echo State Networks

Embodiment of Learning in Electro-Optical Signal Processors

Recent advances in LVCSR : A benchmark comparison of performances

Contact Info

Product

Resources

About