Linear hidden transformations for adaptation of hybrid ANN/HMM models

Gemello, Roberto; Mana, Franco; Scanzio, Stefano; Laface, Pietro; Mori, Renato De

doi:10.1016/j.specom.2006.11.005

Cited by 140 publications

(79 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first category performs speaker normalisation at signal level, such as Vocal Tract Length Normalisation (VTLN [1]), or speaker transformation at feature level, such as feature-MLLR (fMLLR [3]). The second category includes speaker dependent discriminative transformations into DNN structures, for example Linear Input Network (LIN [5]), Linear Output Network (LON [6]), Linear Hidden Layer (LHN [7]) and feature-space Discriminative Linear Regression (fDLR [3]). The third category, "informed DNN training", informs DNNs with meta-information during training process by augmenting the DNN input with auxiliary codes that carry speaker information.…”

Section: Introductionmentioning

confidence: 99%

An investigation into speaker informed DNN front-end for LVCSR

Liu

Karanasou

Hain

2015

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Deep Neural Network (DNN) has become a standard method in many ASR tasks. Recently there is considerable interest in "informed training" of DNNs, where DNN input is augmented with auxiliary codes, such as i-vectors, speaker codes, speaker separation bottleneck (SSBN) features, etc. This paper compares different speaker informed DNN training methods in LVCSR task. We discuss mathematical equivalence between speaker informed DNN training and "bias adaptation" which uses speaker dependent biases, and give detailed analysis on influential factors such as dimension, discrimination and stability of auxiliary codes. The analysis is supported by experiments on a meeting recognition task using bottleneck feature based system. Results show that i-vector based adaptation is also effective in bottleneck feature based system (not just hybrid systems). However all tested methods show poor generalisation to unseen speakers. We introduce a system based on speaker classification followed by speaker adaptation of biases, which yields equivalent performance to an i-vector based system with 10.4% relative improvement over baseline on seen speakers. The new approach can serve as a fast alternative especially for short utterances.

show abstract

Section: Introductionmentioning

confidence: 99%

An investigation into speaker informed DNN front-end for LVCSR

Liu

Karanasou

Hain

2015

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

show abstract

“…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]. However, it is still outperformed by the GMM system with VTLN.…”

Section: Read Continuous Speech Recognition Taskmentioning

confidence: 73%

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

“…Model transformation based adaptation [103,36,80,150] In model transformation approach, the network is augmented with an affine transformation network to the input layer, hidden layer or the output layer. + similarity graph embedding 27.66% 27.60% Table 6.14: Similarity graph embedding features for LSTM-CTC systems on SVB-10k.…”

Section: Connections To Speaker Adaptationmentioning

confidence: 99%

Graph-Based Semisupervised Learning for Acoustic Modeling in Automatic Speech Recognition

Liu

Kirchhoff

2016

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

Graph-based semi-supervised learning (SSL) is a widely used semi-supervised learning method in which the labeled data and unlabeled data are jointly represented as a weighted graph, and the information is propagated from the labeled data to the unlabeled data. The key assumption that graph-based SSL makes is that data samples lie on a low dimensional manifold, where samples that are close to each other are expected to have the same class label. More importantly, by exploiting the relationship between training and test samples, graph-based SSL implicitly adapts to the test data.In this thesis, we address several key challenges in applying graph-based SSL to acoustic modeling. We first investigate and compare several state-of-the-art graph-based SSL algorithms on a benchmark dataset. In addition, we propose novel graph construction methods that allow graph-based SSL to handle variable-length input features. We next investigate the efficacy of graph-based SSL in context of a fully-fledged DNN-based ASR system. We compare two different integration frameworks for graph-based learning. First, we propose a lattice-based late integration framework that combines graph-based SSL with the DNN-based acoustic modeling and evaluate the framework on continuous word recognition tasks. Second, we propose an early integration framework using neural graph embeddings and compare two different neural graph embedding features that capture the information of the manifold at different levels. The embedding features are used as input to a DNN system and are shown to outperform the conventional acoustic feature inputs on several medium-to-large vocabulary conversational speech recognition tasks.

show abstract

Linear hidden transformations for adaptation of hybrid ANN/HMM models

Cited by 140 publications

References 18 publications

An investigation into speaker informed DNN front-end for LVCSR

An investigation into speaker informed DNN front-end for LVCSR

Recent advances in LVCSR : A benchmark comparison of performances

Graph-Based Semisupervised Learning for Acoustic Modeling in Automatic Speech Recognition

Contact Info

Product

Resources

About