Speech discrimination by dynamic programming

By T. K. Vintsyuk. 1968

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Continual Learning for Named Entity Recognition (2021, methodology): “The ﬁnal tags are obtained by the Viterbi algorithm (Vintsyuk 1968) applied as a post-process for the n + m entity types.”
Listening while speaking: Speech chain by deep learning (2017, methodology): “approaches have relied on acoustic-phonetics knowledge [2] in early works to template-based schemes with dynamic time warping (DTW) [3, 4] and data-driven approaches with rigorous statistical modeling of a hidden Markov model-Gaussian mixture model (HMM-GMM) [5, 6].”
Developments and directions in speech recognition and understanding, Part 1 [DSP Education] (2009, background): “…search, broadly applied to search alternative hypotheses, derives from dynamic programming in the 1950s [6] and was subsequently used in speech applications from the 1960s to the 1980s and beyond, from Russia and Japan to the United States and Europe [3], [7], [9], [36], [45], [46], [48], [49].”
BeatGAN: Anomalous Rhythm Detection using Adversarially Generated Time Series (2019, background): “Time series have a special similarity metric, dynamic time warping (DTW) [Vintsyuk, 1968], which measures similarity in a way that is more robust against variations in speed (i.e. ‘time warping’).”
Machine Speech Chain (2020, background): “acoustic-phonetics knowledge [2] in earlier works to templatebased schemes with dynamic time warping (DTW) [3], [4]”
Learning Word Embeddings: Unsupervised Methods for Fixed-size Representations of Variable-length Speech Segments (2018, methodology): “In [22], word embeddings are obtained unsupervisedly by first memorizing a reference set of N words, and calculating the Dynamic Time Warping [23] (DTW) distance of a new target word with each of these references.”
Computational principles and challenges in single-cell data integration (2021, methodology): “To address this, computational strategies such as dynamic time warping (DTW; originally developed for speech recognition 91 ) have been successfully adapted and applied to align time series (Fig.”
BinHunt: Automatically Finding Semantic Differences in Binary Programs (2008, unknown): “, dynamic programming [14,12].”
Joint Phoneme Alignment and Text-Informed Speech Separation on Highly Corrupted Speech (2020, methodology): “We retrieve onsets from the attention weights using the DTW algorithm [21].”
Speech Recognition by Machine, A Review (2010, unknown): “Abbreviations: QR: Quiet Room Ofc: Office RF:Radio Frequency”
Dynamic Neural Program Embedding for Program Repair (2017, methodology): “Our solution is to (1) execute all programs to collect traces for all variables, (2) perform dynamic time wrapping (Vintsyuk, 1968) on the variable traces across all programs to ﬁnd the top-n most used variables that account for the vast majority of variable usage, and (3) rename the top-n most…”