News Blog Paper China
Audio Captioning using Gated Recurrent Units2020-06-05   ${\displaystyle \cong }$
Audio captioning is a recently proposed task for automatically generating a textual description of a given audio clip. In this study, a novel deep network architecture with audio embeddings is presented to predict audio captions. Within the aim of extracting audio features in addition to log Mel energies, VGGish audio embedding model is used to explore the usability of audio embeddings in the audio captioning task. The proposed architecture encodes audio and text input modalities separately and combines them before the decoding stage. Audio encoding is conducted through Bi-directional Gated Recurrent Unit (BiGRU) while GRU is used for the text encoding phase. Following this, we evaluate our model by means of the newly published audio captioning performance dataset, namely Clotho, to compare the experimental results with the literature. Our experimental results show that the proposed BiGRU-based deep model outperforms the state of the art results.
Audio Captioning with Composition of Acoustic and Semantic Information2021-05-13   ${\displaystyle \cong }$
Generating audio captions is a new research area that combines audio and natural language processing to create meaningful textual descriptions for audio clips. To address this problem, previous studies mostly use the encoder-decoder based models without considering semantic information. To fill this gap, we present a novel encoder-decoder architecture using bi-directional Gated Recurrent Units (BiGRU) with audio and semantic embeddings. We extract semantic embedding by obtaining subjects and verbs from the audio clip captions and combine these embedding with audio embedding to feed the BiGRU-based encoder-decoder model. To enable semantic embeddings for the test audios, we introduce a Multilayer Perceptron classifier to predict the semantic embeddings of those clips. We also present exhaustive experiments to show the efficiency of different features and datasets for our proposed model the audio captioning task. To extract audio features, we use the log Mel energy features, VGGish embeddings, and a pretrained audio neural network (PANN) embeddings. Extensive experiments on two audio captioning datasets Clotho and AudioCaps show that our proposed model outperforms state-of-the-art audio captioning models across different evaluation metrics and using the semantic information improves the captioning performance. Keywords: Audio captioning; PANNs; VGGish; GRU; BiGRU.
Listen carefully and tell: an audio captioning system based on residual learning and gammatone audio representation2020-07-08   ${\displaystyle \cong }$
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 as 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 work, an automatic audio captioning based on residual learning on the encoder phase is proposed. The encoder phase is 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 in challenge results.
Multi-task Regularization Based on Infrequent Classes for Audio Captioning2020-07-09   ${\displaystyle \cong }$
Audio captioning is a multi-modal task, focusing on using natural language for describing the contents of general audio. Most audio captioning methods are based on deep neural networks, employing an encoder-decoder scheme and a dataset with audio clips and corresponding natural language descriptions (i.e. captions). A significant challenge for audio captioning is the distribution of words in the captions: some words are very frequent but acoustically non-informative, i.e. the function words (e.g. "a", "the"), and other words are infrequent but informative, i.e. the content words (e.g. adjectives, nouns). In this paper we propose two methods to mitigate this class imbalance problem. First, in an autoencoder setting for audio captioning, we weigh each word's contribution to the training loss inversely proportional to its number of occurrences in the whole dataset. Secondly, in addition to multi-class, word-level audio captioning task, we define a multi-label side task based on clip-level content word detection by training a separate decoder. We use the loss from the second task to regularize the jointly trained encoder for the audio captioning task. We evaluate our method using Clotho, a recently published, wide-scale audio captioning dataset, and our results show an increase of 37\% relative improvement with SPIDEr metric over the baseline method.
Self-supervised Audio Spatialization with Correspondence Classifier2019-05-13   ${\displaystyle \cong }$
Spatial audio is an essential medium to audiences for 3D visual and auditory experience. However, the recording devices and techniques are expensive or inaccessible to the general public. In this work, we propose a self-supervised audio spatialization network that can generate spatial audio given the corresponding video and monaural audio. To enhance spatialization performance, we use an auxiliary classifier to classify ground-truth videos and those with audio where the left and right channels are swapped. We collect a large-scale video dataset with spatial audio to validate the proposed method. Experimental results demonstrate the effectiveness of the proposed model on the audio spatialization task.
Autoencoder Based Architecture For Fast & Real Time Audio Style Transfer2018-12-26   ${\displaystyle \cong }$
Recently, there has been great interest in the field of audio style transfer, where a stylized audio is generated by imposing the style of a reference audio on the content of a target audio. We improve on the current approaches which use neural networks to extract the content and the style of the audio signal and propose a new autoencoder based architecture for the task. This network generates a stylized audio for a content audio in a single forward pass. The proposed network architecture proves to be advantageous over the quality of audio produced and the time taken to train the network. The network is experimented on speech signals to confirm the validity of our proposal.
Automated Audio Captioning with Recurrent Neural Networks2017-10-24   ${\displaystyle \cong }$
We present the first approach to automated audio captioning. We employ an encoder-decoder scheme with an alignment model in between. The input to the encoder is a sequence of log mel-band energies calculated from an audio file, while the output is a sequence of words, i.e. a caption. The encoder is a multi-layered, bi-directional gated recurrent unit (GRU) and the decoder a multi-layered GRU with a classification layer connected to the last GRU of the decoder. The classification layer and the alignment model are fully connected layers with shared weights between timesteps. The proposed method is evaluated using data drawn from a commercial sound effects library, ProSound Effects. The resulting captions were rated through metrics utilized in machine translation and image captioning fields. Results from metrics show that the proposed method can predict words appearing in the original caption, but not always correctly ordered.
Self-Supervised Generation of Spatial Audio for 360 Video2018-09-07   ${\displaystyle \cong }$
We introduce an approach to convert mono audio recorded by a 360 video camera into spatial audio, a representation of the distribution of sound over the full viewing sphere. Spatial audio is an important component of immersive 360 video viewing, but spatial audio microphones are still rare in current 360 video production. Our system consists of end-to-end trainable neural networks that separate individual sound sources and localize them on the viewing sphere, conditioned on multi-modal analysis of audio and 360 video frames. We introduce several datasets, including one filmed ourselves, and one collected in-the-wild from YouTube, consisting of 360 videos uploaded with spatial audio. During training, ground-truth spatial audio serves as self-supervision and a mixed down mono track forms the input to our network. Using our approach, we show that it is possible to infer the spatial location of sound sources based only on 360 video and a mono audio track.
Clotho: An Audio Captioning Dataset2019-10-21   ${\displaystyle \cong }$
Audio captioning is the novel task of general audio content description using free text. It is an intermodal translation task (not speech-to-text), where a system accepts as an input an audio signal and outputs the textual description (i.e. the caption) of that signal. In this paper we present Clotho, a dataset for audio captioning consisting of 4981 audio samples of 15 to 30 seconds duration and 24 905 captions of eight to 20 words length, and a baseline method to provide initial results. Clotho is built with focus on audio content and caption diversity, and the splits of the data are not hampering the training or evaluation of methods. All sounds are from the Freesound platform, and captions are crowdsourced using Amazon Mechanical Turk and annotators from English speaking countries. Unique words, named entities, and speech transcription are removed with post-processing. Clotho is freely available online (https://zenodo.org/record/3490684).
Learning Speech Representations from Raw Audio by Joint Audiovisual Self-Supervision2020-07-08   ${\displaystyle \cong }$
The intuitive interaction between the audio and visual modalities is valuable for cross-modal self-supervised learning. This concept has been demonstrated for generic audiovisual tasks like video action recognition and acoustic scene classification. However, self-supervision remains under-explored for audiovisual speech. We propose a method to learn self-supervised speech representations from the raw audio waveform. We train a raw audio encoder by combining audio-only self-supervision (by predicting informative audio attributes) with visual self-supervision (by generating talking faces from audio). The visual pretext task drives the audio representations to capture information related to lip movements. This enriches the audio encoder with visual information and the encoder can be used for evaluation without the visual modality. Our method attains competitive performance with respect to existing self-supervised audio features on established isolated word classification benchmarks, and significantly outperforms other methods at learning from fewer labels. Notably, our method also outperforms fully supervised training, thus providing a strong initialization for speech related tasks. Our results demonstrate the potential of multimodal self-supervision in audiovisual speech for learning good audio representations.
Multi-modal Dense Video Captioning2020-05-05   ${\displaystyle \cong }$
Dense video captioning is a task of localizing interesting events from an untrimmed video and producing textual description (captions) for each localized event. Most of the previous works in dense video captioning are solely based on visual information and completely ignore the audio track. However, audio, and speech, in particular, are vital cues for a human observer in understanding an environment. In this paper, we present a new dense video captioning approach that is able to utilize any number of modalities for event description. Specifically, we show how audio and speech modalities may improve a dense video captioning model. We apply automatic speech recognition (ASR) system to obtain a temporally aligned textual description of the speech (similar to subtitles) and treat it as a separate input alongside video frames and the corresponding audio track. We formulate the captioning task as a machine translation problem and utilize recently proposed Transformer architecture to convert multi-modal input data into textual descriptions. We demonstrate the performance of our model on ActivityNet Captions dataset. The ablation studies indicate a considerable contribution from audio and speech components suggesting that these modalities contain substantial complementary information to video frames. Furthermore, we provide an in-depth analysis of the ActivityNet Caption results by leveraging the category tags obtained from original YouTube videos. Code is publicly available: github.com/v-iashin/MDVC
Comparison and Analysis of Deep Audio Embeddings for Music Emotion Recognition2021-04-13   ${\displaystyle \cong }$
Emotion is a complicated notion present in music that is hard to capture even with fine-tuned feature engineering. In this paper, we investigate the utility of state-of-the-art pre-trained deep audio embedding methods to be used in the Music Emotion Recognition (MER) task. Deep audio embedding methods allow us to efficiently capture the high dimensional features into a compact representation. We implement several multi-class classifiers with deep audio embeddings to predict emotion semantics in music. We investigate the effectiveness of L3-Net and VGGish deep audio embedding methods for music emotion inference over four music datasets. The experiments with several classifiers on the task show that the deep audio embedding solutions can improve the performances of the previous baseline MER models. We conclude that deep audio embeddings represent musical emotion semantics for the MER task without expert human engineering.
Deep Neural Networks based Invisible Steganography for Audio-into-Image Algorithm2021-02-18   ${\displaystyle \cong }$
In the last few years, steganography has attracted increasing attention from a large number of researchers since its applications are expanding further than just the field of information security. The most traditional method is based on digital signal processing, such as least significant bit encoding. Recently, there have been some new approaches employing deep learning to address the problem of steganography. However, most of the existing approaches are designed for image-in-image steganography. In this paper, the use of deep learning techniques to hide secret audio into the digital images is proposed. We employ a joint deep neural network architecture consisting of two sub-models: the first network hides the secret audio into an image, and the second one is responsible for decoding the image to obtain the original audio. Extensive experiments are conducted with a set of 24K images and the VIVOS Corpus audio dataset. Through experimental results, it can be seen that our method is more effective than traditional approaches. The integrity of both image and audio is well preserved, while the maximum length of the hidden audio is significantly improved.
Deep Audio Prior2019-12-21   ${\displaystyle \cong }$
Deep convolutional neural networks are known to specialize in distilling compact and robust prior from a large amount of data. We are interested in applying deep networks in the absence of training dataset. In this paper, we introduce deep audio prior (DAP) which leverages the structure of a network and the temporal information in a single audio file. Specifically, we demonstrate that a randomly-initialized neural network can be used with carefully designed audio prior to tackle challenging audio problems such as universal blind source separation, interactive audio editing, audio texture synthesis, and audio co-separation. To understand the robustness of the deep audio prior, we construct a benchmark dataset \emph{Universal-150} for universal sound source separation with a diverse set of sources. We show superior audio results than previous work on both qualitative and quantitative evaluations. We also perform thorough ablation study to validate our design choices.
A Case Study of Deep-Learned Activations via Hand-Crafted Audio Features2019-07-03   ${\displaystyle \cong }$
The explainability of Convolutional Neural Networks (CNNs) is a particularly challenging task in all areas of application, and it is notably under-researched in music and audio domain. In this paper, we approach explainability by exploiting the knowledge we have on hand-crafted audio features. Our study focuses on a well-defined MIR task, the recognition of musical instruments from user-generated music recordings. We compute the similarity between a set of traditional audio features and representations learned by CNNs. We also propose a technique for measuring the similarity between activation maps and audio features which typically presented in the form of a matrix, such as chromagrams or spectrograms. We observe that some neurons' activations correspond to well-known classical audio features. In particular, for shallow layers, we found similarities between activations and harmonic and percussive components of the spectrum. For deeper layers, we compare chromagrams with high-level activation maps as well as loudness and onset rate with deep-learned embeddings.
High-Fidelity Audio Generation and Representation Learning with Guided Adversarial Autoencoder2020-06-01   ${\displaystyle \cong }$
Unsupervised disentangled representation learning from the unlabelled audio data, and high fidelity audio generation have become two linchpins in the machine learning research fields. However, the representation learned from an unsupervised setting does not guarantee its' usability for any downstream task at hand, which can be a wastage of the resources, if the training was conducted for that particular posterior job. Also, during the representation learning, if the model is highly biased towards the downstream task, it losses its generalisation capability which directly benefits the downstream job but the ability to scale it to other related task is lost. Therefore, to fill this gap, we propose a new autoencoder based model named "Guided Adversarial Autoencoder (GAAE)", which can learn both post-task-specific representations and the general representation capturing the factors of variation in the training data leveraging a small percentage of labelled samples; thus, makes it suitable for future related tasks. Furthermore, our proposed model can generate audio with superior quality, which is indistinguishable from the real audio samples. Hence, with the extensive experimental results, we have demonstrated that by harnessing the power of the high-fidelity audio generation, the proposed GAAE model can learn powerful representation from unlabelled dataset leveraging a fewer percentage of labelled data as supervision/guidance.
MusCaps: Generating Captions for Music Audio2021-04-24   ${\displaystyle \cong }$
Content-based music information retrieval has seen rapid progress with the adoption of deep learning. Current approaches to high-level music description typically make use of classification models, such as in auto-tagging or genre and mood classification. In this work, we propose to address music description via audio captioning, defined as the task of generating a natural language description of music audio content in a human-like manner. To this end, we present the first music audio captioning model, MusCaps, consisting of an encoder-decoder with temporal attention. Our method combines convolutional and recurrent neural network architectures to jointly process audio-text inputs through a multimodal encoder and leverages pre-training on audio data to obtain representations that effectively capture and summarise musical features in the input. Evaluation of the generated captions through automatic metrics shows that our method outperforms a baseline designed for non-music audio captioning. Through an ablation study, we unveil that this performance boost can be mainly attributed to pre-training of the audio encoder, while other design choices - modality fusion, decoding strategy and the use of attention - contribute only marginally. Our model represents a shift away from classification-based music description and combines tasks requiring both auditory and linguistic understanding to bridge the semantic gap in music information retrieval.
LEAF: A Learnable Frontend for Audio Classification2021-01-21   ${\displaystyle \cong }$
Mel-filterbanks are fixed, engineered audio features which emulate human perception and have been used through the history of audio understanding up to today. However, their undeniable qualities are counterbalanced by the fundamental limitations of handmade representations. In this work we show that we can train a single learnable frontend that outperforms mel-filterbanks on a wide range of audio signals, including speech, music, audio events and animal sounds, providing a general-purpose learned frontend for audio classification. To do so, we introduce a new principled, lightweight, fully learnable architecture that can be used as a drop-in replacement of mel-filterbanks. Our system learns all operations of audio features extraction, from filtering to pooling, compression and normalization, and can be integrated into any neural network at a negligible parameter cost. We perform multi-task training on eight diverse audio classification tasks, and show consistent improvements of our model over mel-filterbanks and previous learnable alternatives. Moreover, our system outperforms the current state-of-the-art learnable frontend on Audioset, with orders of magnitude fewer parameters.
Vision-Infused Deep Audio Inpainting2019-10-24   ${\displaystyle \cong }$
Multi-modality perception is essential to develop interactive intelligence. In this work, we consider a new task of visual information-infused audio inpainting, \ie synthesizing missing audio segments that correspond to their accompanying videos. We identify two key aspects for a successful inpainter: (1) It is desirable to operate on spectrograms instead of raw audios. Recent advances in deep semantic image inpainting could be leveraged to go beyond the limitations of traditional audio inpainting. (2) To synthesize visually indicated audio, a visual-audio joint feature space needs to be learned with synchronization of audio and video. To facilitate a large-scale study, we collect a new multi-modality instrument-playing dataset called MUSIC-Extra-Solo (MUSICES) by enriching MUSIC dataset. Extensive experiments demonstrate that our framework is capable of inpainting realistic and varying audio segments with or without visual contexts. More importantly, our synthesized audio segments are coherent with their video counterparts, showing the effectiveness of our proposed Vision-Infused Audio Inpainter (VIAI). Code, models, dataset and video results are available at https://hangz-nju-cuhk.github.io/projects/AudioInpainting
A Comprehensive Survey of Deep Learning for Image Captioning2018-10-14   ${\displaystyle \cong }$
Generating a description of an image is called image captioning. Image captioning requires to recognize the important objects, their attributes and their relationships in an image. It also needs to generate syntactically and semantically correct sentences. Deep learning-based techniques are capable of handling the complexities and challenges of image captioning. In this survey paper, we aim to present a comprehensive review of existing deep learning-based image captioning techniques. We discuss the foundation of the techniques to analyze their performances, strengths and limitations. We also discuss the datasets and the evaluation metrics popularly used in deep learning based automatic image captioning.