Time delay neural network: Difference between revisions

Revision as of 08:41, 30 December 2018

Revision as of 18:28, 10 March 2019

Line 20:

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" /> TDNN’sTDNNs could also be combined or grown by way of pre-training.<ref name=":3">Alexander Waibel, Hidefumi Sawai, Kiyohiro Shikano, ''Modularity and Scaling in Large Phonemic Neural Networks'', IEEE Transactions on Acoustics, Speech, and Signal Processing, December, December 1989.</ref>

=== Implementation ===

Line 26:

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, ''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 Artart ===

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, ''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, ''A Time-Delay Deep Neural Network-Based Universal Background Models for Speaker Recognition'', Proceedings of ASRU 2015.</ref> While the different layers of TDNN’sTDNNs 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, ''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==

=== Speech Recognitionrecognition ===

TDNNs used to solve problems in speech recognition that were introduced in 1987 <ref name=":0" /> and initially focused on shift-invariant phoneme recognition. Speech lends itself nicely to TDNNs as spoken sounds are rarely of uniform length and precise segmentation is difficult or impossible. By scanning a sound over past and future, the TDNN is able to construct a model for the key elements of that sound in a time-shift invariant manner. This is particularly useful as sounds are smeared out through reverberation.<ref name=":4" /><ref name=":5" /> Large phonetic TDNN’s can be constructed modularly through pre-training and combining smaller networks.<ref name=":3" />

=== Large Vocabularyvocabulary Speechspeech Recognitionrecognition ===

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, ''Improving Connected Letter Recognition by Lipreading'', IEEE Proceedings International Conference on Acoustics, Speech, and Signal Processing, Minneapolis, 1993.</ref><ref name=":2" />

=== Speaker Independenceindependence ===

Two-dimensional variants of the TDNN’s were proposed for speaker independence.<ref name=":1" /> Here, shift-invariance is applied to the time ''as well as'' to the frequency axis in order to learn hidden features that are independent of precise ___location in time and in frequency (the latter being due to speaker variability).

Line 48:

One of the persistent problems in speech recognition is recognizing speech when it is corrupted by echo and reverberation (as is the case in large rooms and distant microphones). Reverberation can be viewed as corrupting speech with delayed versions of itself. In general, it is difficult, however, to de-reverberate a signal as the impulse response function (and thus the convolutional noise experienced by the signal) is not known for any arbitrary space. The TDNN was shown to be effective to recognize speech robustly despite different levels of reverberation.<ref name=":4" /><ref name=":5" />

=== Lip-reading – Audioaudio-Visualvisual Speechspeech ===

TDNNs were also successfully used in early demonstrations of audio-visual speech, where the sounds of speech are complemented by visually reading lip movement.<ref name=":7" /> Here, TDNN based recognizers used visual and acoustic features jointly to achieve improved recognition accuracy, particularly in the presence of noise, where complementary information from an alternate modality could be fused nicely in a neural net.

=== Handwriting Recognitionrecognition ===

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" />

Line 60:

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, 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 Recognitionrecognition ===

Two-dimensional TDNNs were later applied to other image -recognition tasks under the name of “[[Convolutional neural network|Convolutional Neural Networks]]”, where shift-invariant training is applied to the x/y axes of an image.

=== Common Libraries ===

*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>''"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, ''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>