Results 141 to 150 of about 76,886 (181)
Some of the next articles are maybe not open access.
Multi-label Connectionist Temporal Classification
2019 International Conference on Document Analysis and Recognition (ICDAR), 2019The Connectionist Temporal Classification (CTC) loss function [1] enables end-to-end training of a neural network for sequence-to-sequence tasks without the need for prior alignments between the input and output. CTC is traditionally used for training sequential, single-label problems; each element in the sequence has only one class.
Scott Cohen +2 more
exaly +3 more sources
Keyword retrieving in continuous speech using connectionist temporal classification
Journal of Ambient Intelligence and Humanized Computing, 2020The issue of Speech Keyword Retrieval (SKR) has received considerable critical attention. SKR aims to retrieve data from a speech repository given by a spoken query. The accuracy of retrieval often depends on the performance of acoustic model. In this paper, we proposed a new speech keyword retrieval framework called DCNN-CTC using Deep Convolutional ...
Qirong Mao, Mao Qirong
exaly +3 more sources
Diffusion-Based Connectionist Temporal Classification
2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)Connectionist temporal classification (CTC) is one of the predominant schemes for end-to-end speech recognition because of its simplicity, efficiency and reliability. However, as a sequence model, CTC assumes conditional independence of the outputs given
Jen-Tzung Chien
exaly +3 more sources
Connectionist Temporal Classification
Studies in Computational Intelligence, 2012This chapter introduces the connectionist temporal classification (CTC) output layer for recurrent neural networks (Graves et al., 2006). As its name suggests, CTC was specifically designed for temporal classification tasks; that is, for sequence labelling problems where the alignment between the inputs and the target labels is unknown.
exaly +2 more sources
Sampled Connectionist Temporal Classification
2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018This article introduces and evaluates Sampled Connectionist Temporal Classification (CTC) which connects the CTC criterion to the Cross Entropy (CE) objective through sampling. Instead of computing the logarithm of the sum of the alignment path likelihoods, at each training step the sampled CTC only computes the CE loss between the sampled alignment ...
Ehsan Variani +4 more
openaire +2 more sources
Uncertainty Estimation for Connectionist Temporal Classification Based Automatic Speech Recognition
INTERSPEECH 2023, 2023Predictive uncertainty estimation of deep neural networks is important when their outputs are used for high stakes decision making. We investigate token-level uncertainty of connectionist temporal classification (CTC) based automatic speech recognition ...
Lars Rumberg +5 more
openaire +2 more sources
A first attempt at polyphonic sound event detection using connectionist temporal classification
2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017Sound event detection is the task of detecting the type, starting time, and ending time of sound events in audio streams. Recently, recurrent neural networks (RNNs) have become the mainstream solution for sound event detection. Because RNNs make a prediction at every frame, it is necessary to provide exact starting and ending times of the sound events ...
Yun Wang 0005, Florian Metze
openaire +2 more sources
IEEE/ACM Transactions on Audio Speech and Language Processing, 2023
In this paper, we propose a method that uses a combination of the Connectionist Temporal Classification (CTC) loss and the cross-entropy loss to train a note-level singing transcription model.
Jyh-Shing Jang, Jun-You Wang
exaly +2 more sources
In this paper, we propose a method that uses a combination of the Connectionist Temporal Classification (CTC) loss and the cross-entropy loss to train a note-level singing transcription model.
Jyh-Shing Jang, Jun-You Wang
exaly +2 more sources

