@techreport{koizumi2020_t1,
    Author = "Koizumi, Yuma and Takeuchi, Daiki and Ohishi, Yasunori and Harada, Noboru and Kashino, Kunio",
    title = "The {NTT} {DCASE2020} Challenge Task 6 System: Automated Audio Captioning With Keywords and Sentence Length Estimation",
    institution = "DCASE2020 Challenge",
    year = "2020",
    month = "June",
    abstract = "This technical report describes the system participating to the Detection and Classification of Acoustic Scenes and Events (DCASE) 2020 Challenge, Task 6: automated audio captioning. Our submission focuses on solving two indeterminacy problems in automated audio captioning: word selection indeterminacy and sentence length indeterminacy. We simultaneously solve the main caption generation and sub indeterminacy problems by estimating keywords and sentence length through multi-task learning. We tested a simplified model of our submission using the development-testing dataset. Our model achieved 20.7 SPIDEr score where that of the baseline system was 5.4."
}

@techreport{kuzmin2020_t6,
    Author = "Kuzmin, Nikita and Dyakonov, Alexander",
    title = "Automated Audio Captioning",
    institution = "DCASE2020 Challenge",
    year = "2020",
    month = "June",
    abstract = "This task can be stated as an automated generation textual content description from the raw audio file. We propose a method for the automated audio captioning task. We examined the impact of augmentations (MixUp, Reverb, Pitch, Over-drive, Speed) on method performance. Our method based on modified encoder-decoder architecture. The encoder consists of three bidirectional gated recurrent units (GRU). The decoder consists of one gated recurrent unit (GRU) and one fully-connected layer for classification. The encoder input is log-mel spectrogram features for every part of audio file segmented by Hann window [1] of 1024 samples with a 50\% overlap. The decoder output is a matrix with probabilities of words for each position in a sentence. We used BLEU1, BLEU2, BLEU3, BLEU4, ROUGEL, METEOR, CIDEr, SPICE, SPIDEr metrics to compare methods."
}

@techreport{naranjoalcazar2020_t6,
    Author = "Naranjo-Alcazar, Javier and Perez-Castanos, Sergi and Zuccarello, Pedro and Cobos, Maximo",
    title = "Task 6 {DCASE} 2020: Listen Carefully and Tell: An Audio Captioning System Based on Residual Learning and Gammatone Audio Representation",
    institution = "DCASE2020 Challenge",
    year = "2020",
    month = "June",
    abstract = "Automated audio captioning is machine listening task whose goal is to describe an audio using free text. An automated audio captioning system has to be implemented as it accepts an audio as input and outputs a textual description, that is, the caption of the signal. This task can be useful in many applications such as automatic content description or machine-to-machine interaction. In this technical report, a automatic audio captioning based on residual learning on the encoder phase is proposed. The encoder phase implemented via different Residual Networks configurations. The decoder phase (create the caption) is run using recurrent layers plus attention mechanism. The audio representation chosen has been Gammatone. Results show that the framework proposed in this work surpass the baseline system improving all metrics."
}

@techreport{pellegrini2020_t6,
    Author = "Pellegrini, Thomas",
    title = "{IRIT}-{UPS} {DCASE} 2020 audio captioning system",
    institution = "DCASE2020 Challenge",
    year = "2020",
    month = "June",
    abstract = "This technical report is a short description of the sequence-to-sequence model used in the DCASE 2020 task 6 dedicated to audio captioning. Four submissions were made: i) a baseline one using greedy search, ii) beam search, iii) beam search integrating a 2g language model, iv) with a model trained with a vocabulary limited to the most frequent word types (1k words instead of about 5k words)."
}

@techreport{sampathkumar2020_t6,
    Author = "Sampathkumar, Arunodhayan and Kowerko, Danny",
    title = "Automated Audio Captioning",
    institution = "DCASE2020 Challenge",
    year = "2020",
    month = "June",
    abstract = "The audio captioning is a novel approach to describe an audio scene based on human like perception. The human like perception of audio events not only perform detection and localization, but also tries to summarize the relationship between different audio events. The DCASE2020 has developed a strongly labelled caption dataset to perform automated audio captioning. In this research, mel spectrogram is used to extract the audio features. A Recurrent Neural Network (RNN) encoder-decoder is employed to train the dataset. Finally the network is evaluated using the MS COCO metrics where BLEU3 \& BLEU1 scores were strong and is discussed in detail in section 5."
}

@techreport{shi2020_t6,
    Author = "Shi, Anna",
    title = "Audio Captioning With the Transformer",
    institution = "DCASE2020 Challenge",
    year = "2020",
    month = "June",
    abstract = "In this technical report, we present the techniques and models applied to our submission for DCASE 2020 task 6: automated audio captioning. We aim to focus primarily on how to apply transformer methods efficiently to deal with large amount of audio data. Our experiments with the public DCASE2020 challenge task 6 Clotho evaluation data resulted in a SPIDEr of 0.1171, while the SPIDEr of the official baseline is 0.054."
}

@techreport{wang2020_t6,
    Author = "Wang, Helin and Yang, Bang and Zou, Yuexian and Chong, Dading",
    title = "Automated Audio Captioning With Temporal Attention",
    institution = "DCASE2020 Challenge",
    year = "2020",
    month = "June",
    abstract = "This technical report describes the ADSPLAB team’s submission for Task6 of DCASE2020 challenge (automated audio captioning). Our audio captioning system is based on the sequence-to-sequence model. Convolutional neural network (CNN) is used as the encoder and a long-short term memory (LSTM)-based decoder with temporal attention is used to generate the captions. No extra data or pre-trained models are employed and no extra annotations are used. The experimental results show that our system could achieve the SPIDEr of 0.172 (official baseline: 0.054) on the evaluation split of the Clotho dataset."
}

@techreport{wu2020_t6,
    Author = "Wu, Qianyang and Tao, Shengqi and Yang, Xingyu",
    title = "Automatic Audio Captioning System Based on Convolutional Neural Network",
    institution = "DCASE2020 Challenge",
    year = "2020",
    month = "June",
    abstract = "Automated audio captioning has been a new issue in natural language processing (NLP) for recent years. The key point of automatic audio captioning system is that it describes non-audio sig- nals in the form of natural language. The system should take audio as input, and output as descriptive audio sentences. Most of approaches use seq2seq model with RNNs as both the encoder and decoder. It results in considerable time to get the training process finished. This paper proposed a neural network with CNN as the encoder and GRU as the decoder. Encoder is based on VGG16, which has deeper networks and three fully-connected layers. Despite the low accuracy of prediction, our model decreases the train- ing time significantly. It proves that the application of CNN can be a choice for automated audio captioning."
}

@techreport{wuyusong2020_t6,
    Author = "Wu, Yusong and Chen, Kun and Wang, Ziyue and Zhang, Xuan and Nian, Fudong and Li, Shengchen and Shao, Xi",
    title = "Audio Captioning Based on Transformer and Pre-Training for 2020 {DCASE} Audio Captioning Challenge",
    institution = "DCASE2020 Challenge",
    year = "2020",
    month = "June",
    abstract = "This report proposes an automated audio captioning model for the 2020 DCASE audio captioning challenge. In this challenge, a model is required to be trained from scratch to generate natural language descriptions of a given audio signal. However, as limited data available and restrictions on using pre-trained models trained by external data, training directly from scratch can result in poor performance where acoustic events and language are poorly modeled. For better acoustic event and language modeling, a sequence-to-sequence model is proposed which consists of a CNN encoder and a Transformer decoder. In the proposed model, the encoder and word embedding are firstly pre-trained. Regulations and data augmentations are applied during training, while fine-tuning is applied after training. Experiments show that the proposed model can achieve a SPIDEr score of 0.227 on audio captioning performance."
}

@techreport{xu2020_t6,
    Author = "Xu, Xuenan and Dinkel, Heinrich and Wu, Mengyue and Yu, Kai",
    title = "The {SJTU} Submission for {DCASE2020} Task 6: A {CRNN}-{GRU} Based Reinforcement Learning Approach to Audiocaption",
    institution = "DCASE2020 Challenge",
    year = "2020",
    month = "June",
    abstract = "This paper proposes the SJTU AudioCaption system for the DCASE2020 Task 6 challenge. Our system consists of a powerful CRNN encoder combined with a GRU decoder. In addition to standard cross-entropy Audiocaption, reinforcement learning is also investigated. Our approach significantly improves against the challenge baseline model on all shown metrics achieving a relative improvement of at least 34\%. Our best submission achieves a {BLEU4} of 0.146, {Rouge}-{L} of 0.352, {CIDEr} of 0.280, {METEOR} of 0.149, and {SPICE} of 0.099 on Clotho evaluation set."
}