Efficient viterbi beam search algorithm using dynamic pruning

Xie, Lingyun; Du, Liang

doi:10.1109/icosp.2004.1452759

Cited by 16 publications

(7 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, when the constellation size m and the channel memory l grow large, the Viterbi algorithm becomes computationally complex due to the need to compute the log-likelihood for each of the possible m l different values of s. Consequently, the complexity of ViterbiNet is expected to grow exponentially as m and l grow, since the label space of the DNN grows exponentially. It is noted that greedy schemes for reducing the complexity of the Viterbi algorithm, such as beam search [35] and reduced-state equalization [36], were shown to result in minimal performance degradation, and we thus expect that these methods can inspire similar modifications to ViterbiNet, facilitating its application with large m and l. We leave the research into reducing the complexity of ViterbiNet through such methods to future investigation.…”

Section: B Discussionmentioning

confidence: 99%

ViterbiNet: A Deep Learning Based Viterbi Algorithm for Symbol Detection

Shlezinger

Farsad

Eldar

et al. 2020

IEEE Trans. Wireless Commun.

148

130

View full text Add to dashboard Cite

Symbol detection plays an important role in the implementation of digital receivers. In this work, we propose ViterbiNet, which is a data-driven symbol detector that does not require channel state information (CSI). ViterbiNet is obtained by integrating deep neural networks (DNNs) into the Viterbi algorithm. We identify the specific parts of the Viterbi algorithm that are channel-model-based, and design a DNN to implement only those computations, leaving the rest of the algorithm structure intact.We then propose a meta-learning based approach to train ViterbiNet online based on recent decisions, allowing the receiver to track dynamic channel conditions without requiring new training samples for every coherence block. Our numerical evaluations demonstrate that the performance of ViterbiNet, which is ignorant of the CSI, approaches that of the CSI-based Viterbi algorithm, and is capable of tracking time-varying channels without needing instantaneous CSI or additional training data. Moreover, unlike conventional Viterbi detection, ViterbiNet is robust to CSI uncertainty, and it can be reliably implemented in complex channel models with constrained computational burden. More broadly, our results demonstrate the conceptual benefit of designing communication systems to that integrate DNNs into established algorithms.Parts of this work were accepted for presentation in the

show abstract

Section: B Discussionmentioning

confidence: 99%

ViterbiNet: A Deep Learning Based Viterbi Algorithm for Symbol Detection

Shlezinger

Farsad

Eldar

et al. 2020

IEEE Trans. Wireless Commun.

148

130

View full text Add to dashboard Cite

show abstract

“…When the memory length is long, it is not computationally feasible to consider all the states in the trellis as they grow exponentially with memory length. Therefore, in this work we implement the Viterbi beam search algorithm [63]. In this scheme, at each time slot, only the transition from the previous N states with the largest log-likelihoods are considered.…”

Section: A the Viterbi Detectormentioning

confidence: 99%

Neural Network Detection of Data Sequences in Communication Systems

Farsad

Goldsmith

2018

IEEE Trans. Signal Process.

320

155

View full text Add to dashboard Cite

We consider detection based on deep learning, and show it is possible to train detectors that perform well without any knowledge of the underlying channel models. Moreover, when the channel model is known, we demonstrate that it is possible to train detectors that do not require channel state information (CSI). In particular, a technique we call a sliding bidirectional recurrent neural network (SBRNN) is proposed for detection where, after training, the detector estimates the data in realtime as the signal stream arrives at the receiver. We evaluate this algorithm, as well as other neural network (NN) architectures, using the Poisson channel model, which is applicable to both optical and molecular communication systems. In addition, we also evaluate the performance of this detection method applied to data sent over a molecular communication platform, where the channel model is difficult to model analytically. We show that SBRNN is computationally efficient, and can perform detection under various channel conditions without knowing the underlying channel model. We also demonstrate that the bit error rate (BER) performance of the proposed SBRNN detector is better than that of a Viterbi detector with imperfect CSI as well as that of other NN detectors that have been previously proposed. Finally, we show that the SBRNN can perform well in rapidly changing channels, where the coherence time is on the order of a single symbol duration.

show abstract

“…Active states 1 and 4 are pruned away as their likelihoods are smaller than the beam. The search algorithm combined with the pruning is commonly referred as Viterbi beam search [26].…”

Section: Speech Recognition With Wfstmentioning

confidence: 99%

A Low-Power, High-Performance Speech Recognition Accelerator

Yazdani

Arnau

González

2019

IEEE Trans. Comput.

View full text Add to dashboard Cite

Automatic Speech Recognition (ASR) is becoming increasingly ubiquitous, especially in the mobile segment. Fast and accurate ASR comes at high energy cost, not being affordable for the tiny power-budgeted mobile devices. Hardware acceleration reduces energy-consumption of ASR systems, while delivering high-performance. In this paper, we present an accelerator for large-vocabulary, speaker-independent, continuous speech-recognition. It focuses on the Viterbi search algorithm representing the main bottleneck in an ASR system. The proposed design consists of innovative techniques to improve the memory subsystem, since memory is the main bottleneck for performance and power in these accelerators' design. It includes a prefetching scheme tailored to the needs of ASR systems that hides main memory latency for a large fraction of the memory accesses, negligibly impacting area. Additionally, we introduce a novel bandwidth-saving technique that removes off-chip memory accesses by 20%. Finally, we present a power saving technique that significantly reduces the leakage power of the accelerators scratchpad memories, providing between 8.5% and 29.2% reduction in entire power dissipation. Overall, the proposed design outperforms implementations running on the CPU by orders of magnitude, and achieves speedups between 1.7x and 5.9x for different speech decoders over a highly optimized CUDA implementation running on Geforce-GTX-980 GPU, while reducing the energy by 123-454x.

show abstract

Efficient viterbi beam search algorithm using dynamic pruning

Cited by 16 publications

References 1 publication

ViterbiNet: A Deep Learning Based Viterbi Algorithm for Symbol Detection

ViterbiNet: A Deep Learning Based Viterbi Algorithm for Symbol Detection

Neural Network Detection of Data Sequences in Communication Systems

A Low-Power, High-Performance Speech Recognition Accelerator

Contact Info

Product

Resources

About