Results 131 to 140 of about 939 (162)

Speechformer-CTC: Sequential Modeling of Depression Detection with Speech Temporal Classification. [PDF]

Speech Commun
Wang J, Ravi V, Flint J, Alwan A.
europepmc   +1 more source

Tibetan-Chinese speech-to-speech translation based on discrete units. [PDF]

Sci Rep
Gong Z, Xu X, Zhao Y.
europepmc   +1 more source

NeuroQ: Quantum-Inspired Brain Emulation. [PDF]

Biomimetics (Basel)
Vallverdú J, Rius G.
europepmc   +1 more source

Impact of Natural Language Processing models on diagnosis and decision-making in healthcare, business, education, and sports: a review. [PDF]

Front Artif Intell
Choudhary A, Pamidimokkala S, R K, R M B.   +3 more
europepmc   +1 more source

Some of the next articles are maybe not open access.

Related searches:

Variational Connectionist Temporal Classification

Lecture Notes in Computer Science, 2020
Connectionist Temporal Classification (CTC) is a training criterion designed for sequence labelling problems where the alignment between the inputs and the target labels is unknown. One of the key steps is to add a blank symbol to the target vocabulary. However, CTC tends to output spiky distributions since it prefers to output blank symbol most of the
Jingdong Chen, Chen Jingdong
exaly   +2 more sources

Multi-label Connectionist Temporal Classification

2019 International Conference on Document Analysis and Recognition (ICDAR), 2019
The 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, Curtis Wigington, Brian Price   +2 more
exaly   +2 more sources

Sampled Connectionist Temporal Classification

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018
This 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 ...
Kamel Lahouel, Ehsan Variani, Erik Mcdermott   +2 more
exaly   +2 more sources

Connectionist temporal classification loss for vector quantized variational autoencoder in zero-shot voice conversion

Digital Signal Processing, 2021
Abstract Vector quantized variational autoencoder (VQ-VAE) has recently become an increasingly popular method in non-parallel zero-shot voice conversion (VC). The reason behind is that VQ-VAE is capable of disentangling the content and the speaker representations from the speech by using a content encoder and a speaker encoder, which is suitable for ...
Hao Huang
exaly   +2 more sources

Connectionist Temporal Classification

Studies in Computational Intelligence, 2012
This 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

Connectionist Temporal Classification-based Sound Event Encoder for Converting Sound Events into Onomatopoeic Representations

2018 26th European Signal Processing Conference (EUSIPCO), 2018
In this paper, we propose a sound event encoder for converting sound events into their onomatopoeic representations. The proposed method uses connectionist temporal classification (CTC) as an end-to-end approach to directly convert a sequence of feature vectors of each sound event into a corresponding onomatopoeic word representation which accurately ...
Tomoki Hayashi, Kazuya Takeda, Tomoki Toda   +2 more
exaly   +2 more sources