Content deleted Content added
Rescuing orphaned refs ("Yamaguchi111990" from Convolutional neural network) |
adding links to references using Google Scholar |
||
Line 1:
[[File:TDNN Diagram.png|thumb|right|TDNN Diagram]]
'''Time delay neural network''' ('''TDNN''') <ref name="phoneme detection">[[Alex Waibel|Alexander Waibel]], Tashiyuki Hanazawa, [[Geoffrey Hinton]], Kiyohito Shikano, Kevin J. Lang, ''[http://www.inf.ufrgs.br/~engel/data/media/file/cmp121/waibel89_TDNN.pdf Phoneme Recognition Using Time-Delay Neural Networks]'', IEEE Transactions on Acoustics, Speech, and Signal Processing, Volume 37, No. 3, pp. 328. - 339 March 1989.</ref> is a multilayer [[artificial neural network]] architecture whose purpose is to 1) classify patterns with shift-invariance, and 2) model context at each layer of the network.
Shift-invariant classification means that the classifier does not require explicit segmentation prior to classification. For the classification of a temporal pattern (such as speech), the TDNN thus avoids having to determine the beginning and end points of sounds before classifying them.
Line 8:
== History ==
The TDNN was first proposed to classify [[phonemes]] in speech signals for automatic [[speech recognition]], where the automatic determination of precise segments or feature boundaries is difficult or impossible. Because the TDNN recognizes phonemes and their underlying acoustic/phonetic features, independent of position in time, it improved performance over static classification.<ref name="phoneme detection" /><ref name=":0">Alexander Waibel, ''[http://www.inf.ufrgs.br/~engel/data/media/file/cmp121/waibel89_TDNN.pdf Phoneme Recognition Using Time-Delay Neural Networks]'', SP87-100, Meeting of the Institute of Electrical, Information and Communication Engineers (IEICE), December, 1987,Tokyo, Japan.</ref> It was also applied to two-dimensional signals (time-frequency patterns in speech,<ref name=":1">John B. Hampshire and Alexander Waibel, ''[http://papers.nips.cc/paper/213-connectionist-architectures-for-multi-speaker-phoneme-recognition.pdf Connectionist Architectures for Multi-Speaker Phoneme Recognition]'', Advances in Neural Information Processing Systems, 1990, Morgan Kaufmann.</ref> and coordinate space pattern in OCR<ref name=":2">Stefan Jaeger, Stefan Manke, Juergen Reichert, Alexander Waibel, ''[https://www.researchgate.net/profile/Stefan_Jaeger/publication/220163530_Online_handwriting_recognition_the_NPen_recognizer_Int_J_Doc_Anal_Recognit_3169-180/links/0c96051af3e6133ed0000000.pdf Online handwriting recognition: the NPen++recognizer]'', International Journal on Document Analysis and Recognition Vol. 3, Issue 3, March 2001</ref>).
==== Max pooling ====
In 1990 Yamaguchi et al. introduced the concept of max pooling. They did so by combining TDNNs with max pooling in order to realize a speaker independent isolated word recognition system.<ref name=Yamaguchi111990>{{cite conference |title=A Neural Network for Speaker-Independent Isolated Word Recognition |last1=Yamaguchi |first1=Kouichi |last2=Sakamoto |first2=Kenji |last3=Akabane |first3=Toshio |last4=Fujimoto |first4=Yoshiji |date=November 1990 |___location=Kobe, Japan |conference=First International Conference on Spoken Language Processing (ICSLP 90)|url=https://www.isca-speech.org/archive/icslp_1990/i90_1077.html}}</ref>
==Overview==
Line 22:
In the case of a speech signal, inputs are spectral coefficients over time.
In order to learn critical acoustic-phonetic features (for example formant transitions, bursts, frication, etc.) without first requiring precise localization, the TDNN is trained time-shift-invariantly. Time-shift invariance is achieved through weight sharing across time during training: Time shifted copies of the TDNN are made over the input range (from left to right in Fig.1). Backpropagation is then performed from an overall classification target vector (see TDNN diagram, three phoneme class targets (/b/, /d/, /g/) are shown in the output layer), resulting in gradients that will generally vary for each of the time-shifted network copies. Since such time-shifted networks are only copies, however, the position dependence is removed by weight sharing. In this example, this is done by averaging the gradients from each time-shifted copy before performing the weight update. In speech, time-shift invariant training was shown to learn weight matrices that are independent of precise positioning of the input. The weight matrices could also be shown to detect important acoustic-phonetic features that are known to be important for human speech perception, such as formant transitions, bursts, etc.<ref name="phoneme detection" /> TDNNs could also be combined or grown by way of pre-training.<ref name=":3">Alexander Waibel, Hidefumi Sawai, Kiyohiro Shikano, ''[https://ieeexplore.ieee.org/abstract/document/45535/ Modularity and Scaling in Large Phonemic Neural Networks]'', IEEE Transactions on Acoustics, Speech, and Signal Processing, December, December 1989.</ref>
=== Implementation ===
The precise architecture of TDNNs (time-delays, number of layers) is mostly determined by the designer depending on the classification problem and the most useful context sizes. The delays or context windows are chosen specific to each application. Work has also been done to create adaptable time-delay TDNNs <ref>Christian Koehler and Joachim K. Anlauf, ''[https://pdfs.semanticscholar.org/9a0a/08e4d9a4cea6fa035555f2ee54bdae673614.pdf An adaptable time-delay neural-network algorithm for image sequence analysis]'', IEEE Transactions on Neural Networks 10.6 (1999): 1531-1536</ref> where this manual tuning is eliminated.
=== State of the art ===
TDNN-based phoneme recognizers compared favourably in early comparisons with HMM-based phone models.<ref name="phoneme detection" /><ref name=":3" /> Modern deep TDNN architectures include many more hidden layers and sub-sample or pool connections over broader contexts at higher layers. They achieve up to 50% word error reduction over [[Mixture model|GMM]]-based acoustic models.<ref name=":4">Vijayaditya Peddinti, Daniel Povey, Sanjeev Khudanpur, ''[https://pdfs.semanticscholar.org/ced2/11de5412580885279090f44968a428f1710b.pdf A time delay neural network architecture for efficient modeling of long temporal contexts]'', Proceedings of Interspeech 2015</ref><ref name=":5">David Snyder, Daniel Garcia-Romero, Daniel Povey, ''[http://danielpovey.com/files/2015_asru_tdnn_ubm.pdf A Time-Delay Deep Neural Network-Based Universal Background Models for Speaker Recognition]'', Proceedings of ASRU 2015.</ref> While the different layers of TDNNs are intended to learn features of increasing context width, they do model local contexts. When longer-distance relationships and pattern sequences have to be processed, learning states and state-sequences is important and TDNNs can be combined with other modelling techniques <ref name=":6">Patrick Haffner, Alexander Waibel, ''[http://papers.nips.cc/paper/580-multi-state-time-delay-networks-for-continuous-speech-recognition.pdf Multi-State Time Delay Neural Networks for Continuous Speech Recognition]'', Advances in Neural Information Processing Systems, 1992, Morgan Kaufmann.</ref><ref name=":1" /><ref name=":2" />
==Applications==
Line 40:
=== Large vocabulary speech recognition ===
Large vocabulary speech recognition requires recognizing sequences of phonemes that make up words subject to the constraints of a large pronunciation vocabulary. Integration of TDNNs into large vocabulary speech recognizers is possible by introducing state transitions and search between phonemes that make up a word. The resulting Multi-State Time-Delay Neural Network (MS-TDNN) can be trained discriminative from the word level, thereby optimizing the entire arrangement toward word recognition instead of phoneme classification.<ref name=":6" /><ref name=":7">Christoph Bregler, Hermann Hild, Stefan Manke, Alexander Waibel, ''[http://isl.anthropomatik.kit.edu/cmu-kit/downloads/Improving_Connected_Letter_Recognition_by_Lipreading.pdf Improving Connected Letter Recognition by Lipreading]'', IEEE Proceedings International Conference on Acoustics, Speech, and Signal Processing, Minneapolis, 1993.</ref><ref name=":2" />
=== Speaker independence ===
Line 56:
=== Handwriting recognition ===
TDNNs have been used effectively in compact and high-performance [[handwriting recognition]] systems. Shift-invariance was also adapted to spatial patterns (x/y-axes) in image offline handwriting recognition.<ref name=":2" />
=== Video analysis ===
Video has a temporal dimension that makes a TDNN an ideal solution to analysing motion patterns. An example of this analysis is a combination of vehicle detection and recognizing pedestrians.<ref>Christian Woehler and Joachim K. Anlauf, [https://www.sciencedirect.com/science/article/pii/S0262885601000403 Real-time object recognition on image sequences with the adaptable time delay neural network algorithm—applications for autonomous vehicles]." Image and Vision Computing 19.9 (2001): 593-618.</ref> When examining videos, subsequent images are fed into the TDNN as input where each image is the next frame in the video. The strength of the TDNN comes from its ability to examine objects shifted in time forward and backward to define an object detectable as the time is altered. If an object can be recognized in this manner, an application can plan on that object to be found in the future and perform an optimal action.
=== Image recognition ===
Line 69:
*TDNNs can be implemented in virtually all machine-learning frameworks using one-dimensional [[convolutional neural network]]s, due to the equivalence of the methods.
*[[Matlab]]: The neural network toolbox has explicit functionality designed to produce a time delay neural network give the step size of time delays and an optional training function. The default training algorithm is a Supervised Learning back-propagation algorithm that updates filter weights based on the Levenberg-Marquardt optimizations. The function is timedelaynet(delays, hidden_layers, train_fnc) and returns a time-delay neural network architecture that a user can train and provide inputs to.<ref>''"[https://www.mathworks.com/help/deeplearning/time-series-and-dynamic-systems.html Time Series and Dynamic Systems - MATLAB & Simulink]".'' mathworks.com. Retrieved 21 June 2016.</ref>
*The [[Kaldi (software)|Kaldi ASR Toolkit]] has an implementation of TDNNs with several optimizations for speech recognition <ref>Vijayaditya Peddinti, Guoguo Chen, Vimal Manohar, Tom Ko, Daniel Povey, Sanjeev Khudanpur, ''[http://danielpovey.com/files/2015_asru_aspire.pdf JHU ASpIRE system: Robust LVCSR with TDNNs i-vector Adaptation and RNN-LMs]'', Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2015.</ref>
==See also==
| |||