Using deep neural networks (DNNs) for encoding of microphone array (MA) signals to the Ambisonics spatial audio format can surpass certain limitations of established conventional methods, but existing DNN-based methods need to be trained separately for each MA. This paper proposes a DNN-based method for Ambisonics encoding that can generalize to arbitrary MA geometries unseen during training. The method takes as inputs the MA geometry and MA signals and uses a multi-level encoder consisting of separate paths for geometry and signal data, where geometry features inform the signal encoder at each level. The method is validated in simulated anechoic and reverberant conditions with one and two sources. The results indicate improvement over conventional encoding across the whole frequency range for dry scenes, while for reverberant scenes the improvement is frequency-dependent.

Speech denoising (SD) is an important task of many, if not all, modern signal processing chains used in devices and for everyday-life applications. While there are many published and powerful deep neural network (DNN)-based methods for SD, few are optimized for resource-constrained platforms such as mobile devices. Additionally, most DNN-based methods for SD are not focusing on full-band (FB) signals, i.e. having 48 kHz sampling rate, and/or low latency cases. In this paper we present a causal, low latency, and lightweight DNN-based method for full-band SD, leveraging both short and long temporal patterns. The method is based on a modified UNet architecture employing look-back frames, temporal spanning of convolutional kernels, and recurrent neural networks for exploiting short and long temporal patterns in the signal and estimated denoising mask. The DNN operates on a causal frame-by-frame basis taking as an input the STFT magnitude, utilizes inverted bottlenecks inspired by MobileNet, employs causal instance normalization for channel-wise normalization, and achieves a real-time factor below 0.02 when deployed on a modern mobile phone. The proposed method is evaluated using established speech denoising metrics and publicly available datasets, demonstrating its effectiveness in achieving an (SI-)SDR value that outperforms existing FB and low latency SD methods.

In order to study how early emotional experiences shape infant development, one approach is to analyze the emotional content of speech heard by infants, as captured by child-centered daylong recordings, and as analyzed by automatic speech emotion recognition (SER) systems. However, since large-scale daylong audio is initially unannotated and differs from typical speech corpora from controlled environments, there are no existing in-domain SER systems for the task. Based on existing literature, it is also unclear what is the best approach to deploy a SER system for a new domain. Consequently, in this study, we investigated alternative strategies for deploying a SER system for large-scale child-centered audio recordings from a neonatal hospital environment, comparing cross-corpus generalization, active learning (AL), and domain adaptation (DA) methods in the process. We first conducted simulations with existing emotion-labeled speech corpora to find the best strategy for SER system deployment. We then tested how the findings generalize to our new initially unannotated dataset. As a result, we found that the studied AL method provided overall the most consistent results, being less dependent on the specifics of the training corpora or speech features compared to the alternative methods. However, in situations without the possibility to annotate data, unsupervised DA proved to be the best approach. We also observed that deployment of a SER system for real-world daylong child-centered audio recordings achieved a SER performance level comparable to those reported in literature, and that the amount of human effort required for the system deployment was overall relatively modest.

We investigate unsupervised learning of correspondences between sound events and textual phrases through aligning audio clips with textual captions describing the content of a whole audio clip. We align originally unaligned and unannotated audio clips and their captions by scoring the similarities between audio frames and words, as encoded by modality-specific encoders and using a ranking-loss criterion to optimize the model. After training, we obtain clip-caption similarity by averaging frame-word similarities and estimate event-phrase correspondences by calculating frame-phrase similarities. We evaluate the method with two cross-modal tasks: audio-caption retrieval, and phrase-based sound event detection (SED). Experimental results show that the proposed method can globally associate audio clips with captions as well as locally learn correspondences between individual sound events and textual phrases in an unsupervised manner.

Automatic estimation of domestic activities from audio can be used to solve many problems, such as reducing the labor cost for nursing the elderly people. This study focuses on solving the problem of domestic activity clustering from audio. The target of domestic activity clustering is to cluster audio clips which belong to the same category of domestic activity into one cluster in an unsupervised way. In this paper, we propose a method of domestic activity clustering using a depthwise separable convolutional autoencoder network. In the proposed method, initial embeddings are learned by the depthwise separable convolutional autoencoder, and a clustering-oriented loss is designed to jointly optimize embedding refinement and cluster assignment. Different methods are evaluated on a public dataset (a derivative of the SINS dataset) used in the challenge on Detection and Classification of Acoustic Scenes and Events (DCASE) in 2018. Our method obtains the normalized mutual information (NMI) score of 54.46%, and the clustering accuracy (CA) score of 63.64%, and outperforms state-of-the-art methods in terms of NMI and CA. In addition, both computational complexity and memory requirement of our method is lower than that of previous deep-model-based methods. Codes: https://github.com/vinceasvp/domestic-activity-clustering-from-audio

Self-supervised audio representation learning offers an attractive alternative for obtaining generic audio embeddings, capable to be employed into various downstream tasks. Published approaches that consider both audio and words/tags associated with audio do not employ text processing models that are capable to generalize to tags unknown during training. In this work we propose a method for learning audio representations using an audio autoencoder (AAE), a general word embed-dings model (WEM), and a multi-head self-attention (MHA) mechanism. MHA attends on the output of the WEM, pro-viding a contextualized representation of the tags associated with the audio, and we align the output of MHA with the out-put of the encoder of AAE using a contrastive loss. We jointly optimize AAE and MHA and we evaluate the audio representations (i.e. the output of the encoder of AAE) by utilizing them in three different downstream tasks, namely sound, music genre, and music instrument classification. Our results show that employing multi-head self-attention with multiple heads in the tag-based network can induce better learned audio representations.

We are largely used to hearing explanations. For example, if someone thinks you are sad today, they might reply to your “why?” with “because you were so Hmmmmm-mmm-mmm”. Today’s Artificial Intelligence (AI), however, is – if at all – largely providing explanations of decisions in a visual or textual manner. While such approaches are good for communication via visual media such as in research papers or screens of intelligent devices, they may not always be the best way to explain; especially when the end user is not an expert. In particular, when the AI’s task is about Audio Intelligence, visual explanations appear less intuitive than audible, sonified ones. Sonification has also great potential for explainable AI (XAI) in systems that deal with non-audio data – for example, because it does not require visual contact or active attention of a user. Hence, sonified explanations of AI decisions face a challenging, yet highly promising and pioneering task. That involves incorporating innovative XAI algorithms to allow pointing back at the learning data responsible for decisions made by an AI, and to include decomposition of the data to identify salient aspects. It further aims to identify the components of the preprocessing, feature representation, and learnt attention patterns that are responsible for the decisions. Finally, it targets decision-making at the model-level, to provide a holistic explanation of the chain of processing in typical pattern recognition problems from end-to-end. Sonified AI explanations will need to unite methods for sonification of the identified aspects that benefit decisions, decomposition and recomposition of audio to sonify which parts in the audio were responsible for the decision, and rendering attention patterns and salient feature representations audible. Benchmarking sonified XAI is challenging, as it will require a comparison against a backdrop of existing, state-of-the-art visual and textual alternatives, as well as synergistic complementation of all modalities in user evaluations. Sonified AI explanations will need to target different user groups to allow personalisation of the sonification experience for different user needs, to lead to a major breakthrough in comprehensibility of AI via hearing how decisions are made, hence supporting tomorrow’s humane AI’s trustability. Here, we introduce and motivate the general idea, and provide accompanying considerations including milestones of realisation of sonifed XAI and foreseeable risks.

Researchers have recently started to study how the emotional speech heard by young infants can affect their developmental outcomes. As a part of this research, hundreds of hours of daylong recordings from preterm infants' audio environments were collected from two hospitals in Finland and Estonia in the context of so-called APPLE study. In order to analyze the emotional content of speech in such a massive dataset, an automatic speech emotion recognition (SER) system is required. However, there are no emotion labels or existing indomain SER systems to be used for this purpose. In this paper, we introduce this initially unannotated large-scale real-world audio dataset and describe the development of a functional SER system for the Finnish subset of the data. We explore the effectiveness of alternative state-of-the-art techniques to deploy a SER system to a new domain, comparing cross-corpus generalization, WGAN-based domain adaptation, and active learning in the task. As a result, we show that the best-performing models are able to achieve a classification performance of 73.4% unweighted average recall (UAR) and 73.2% UAR for a binary classification for valence and arousal, respectively. The results also show that active learning achieves the most consistent performance compared to the two alternatives.

Modeling various aspects that make a music piece unique is a challenging task, requiring the combination of multiple sources of information. Deep learning is commonly used to obtain representations using various sources of information, such as the audio, interactions between users and songs, or associated genre metadata. Recently, contrastive learning has led to representations that generalize better compared to traditional supervised methods. In this paper, we present a novel approach that combines multiple types of information related to music using cross-modal contrastive learning, allowing us to learn an audio feature from heterogeneous data simultaneously. We align the latent representations obtained from playlists-track interactions, genre metadata, and the tracks' audio, by maximizing the agreement between these modality representations using a contrastive loss. We evaluate our approach in three tasks, namely, genre classification, playlist continuation and automatic tagging. We compare the performances with a baseline audio-based CNN trained to predict these modalities. We also study the importance of including multiple sources of information when training our embedding model. The results suggest that the proposed method outperforms the baseline in all the three downstream tasks and achieves comparable performance to the state-of-the-art.

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 online1.

Convolutional recurrent neural networks (CRNNs) have achieved state-of-the-art performance for sound event detection (SED). In this paper, we propose to use a dilated CRNN, namely a CRNN with a dilated convolutional kernel, as the classifier for the task of SED. We investigate the effectiveness of dilation operations which provide a CRNN with expanded receptive fields to capture long temporal context without increasing the amount of CRNN's parameters. Compared to the classifier of the baseline CRNN, the classifier of the dilated CRNN obtains a maximum increase of 1.9%, 6.3% and 2.5% at F1 score and a maximum decrease of 1.7%, 4.1% and 3.9% at error rate (ER), on the publicly available audio corpora of the TUTSED Synthetic 2016, the TUT Sound Event 2016 and the TUT Sound Event 2017, respectively.

State-of-the-art sound event detection (SED) methods usually employ a series of convolutional neural networks (CNNs) to extract useful features from the input audio signal, and then recurrent neural networks (RNNs) to model longer temporal context in the extracted features. The number of the channels of the CNNs and size of the weight matrices of the RNNs have a direct effect on the total amount of parameters of the SED method, which is to a couple of millions. Additionally, the usually long sequences that are used as an input to an SED method along with the employment of an RNN, introduce implications like increased training time, difficulty at gradient flow, and impeding the parallelization of the SED method. To tackle all these problems, we propose the replacement of the CNNs with depthwise separable convolutions and the replacement of the RNNs with dilated convolutions. We compare the proposed method to a baseline convolutional neural network on a SED task, and achieve a reduction of the amount of parameters by 85% and average training time per epoch by 78%, and an increase the average frame-wise F1score and reduction of the average error rate by 4.6% and 3.8%, respectively.

This work addresses the problem of multichannel source separation combining two powerful approaches, multichannel spectral factorization with recent monophonic deep learning (DL) based spectrum inference. Individual source spectra at different channels are estimated with a Masker-Denoiser twin network, able to model long-term temporal patterns of a musical piece. The monophonic source spectrograms are used within a spatial covariance mixing model based on complex-valued multichannel non-negative matrix factorization (CMNMF) that predicts the spatial characteristics of each source. The proposed framework is evaluated on the task of singing voice separation with a large multichannel dataset. Experimental results show that our joint DL+CMNMF method outperforms both the individual monophonic DL-based separation and the multichannel CMNMF baseline methods.

Recent approaches for music source separation are almost exclusively based on deep neural networks, mostly employing recurrent neural networks (RNNs). Although RNNs are in many cases superior than other types of deep neural networks for sequence processing, they are known to have specific difficulties in training and parallelization, especially for the typically long sequences encountered in music source separation. In this paper we present a use-case of replacing RNNs with depth-wise separable (DWS) convolutions, which are a lightweight and faster variant of the typical convolutions. We focus on singing voice separation, employing an RNN architecture, and we replace the RNNs with DWS convolutions (DWS-CNNs). We conduct an ablation study and examine the effect of the number of channels and layers of DWS-CNNs on the source separation performance, by utilizing the standard metrics of signal-to-artifacts, signal-to-interference, and signal-to-distortion ratio. Our results show that by replacing RNNs with DWS-CNNs yields an improvement of 1.20, 0.06, 0.37 dB, respectively, while using only 20.57% of the amount of parameters of the RNN architecture.

Singing voice separation based on deep learning relies on the usage of time-frequency masking. In many cases the masking process is not a learnable function or is not encapsulated into the deep learning optimization. Consequently, most of the existing methods rely on a post processing step using the generalized Wiener filtering. This work proposes a method that learns and optimizes (during training) a source-dependent mask and does not need the aforementioned post processing step. We introduce a recurrent inference algorithm, a sparse transformation step to improve the mask generation process, and a learned denoising filter. Obtained results show an increase of 0.49 dB for the signal to distortion ratio and 0.30 dB for the signal to interference ratio, compared to previous state-of-the-art approaches for monaural singing voice separation.

Monaural singing voice separation task focuses on the prediction of the singing voice from a single channel music mixture signal. Current state of the art (SOTA) results in monaural singing voice separation are obtained with deep learning based methods. In this work we present a novel recurrent neural approach that learns long-term temporal patterns and structures of a musical piece. We build upon the recently proposed Masker-Denoiser (MaD) architecture and we enhance it with the Twin Networks, a technique to regularize a recurrent generative network using a backward running copy of the network. We evaluate our method using the Demixing Secret Dataset and we obtain an increment to signal-to-distortion ratio (SDR) of 0.37 dB and to signal-to-interference ratio (SIR) of 0.23 dB, compared to previous SOTA results.

S.332-336

Emotion recognition from sound signals represents an emerging field of recent research. Although many existing works focus on emotion recognition from music, there seems to be a relative scarcity of research on emotion recognition from general sounds. One of the key characteristics of sound events is the sound source spatial position, i.e. the location of the source relatively to the acoustic receiver. Existing studies that aim to investigate the relation of the latter source placement and the elicited emotions are limited to distance, front and back spatial localization and/or specific emotional categories. In this paper we analytically investigate the effect of the source angular position on the listener's emotional state, modeled in the well-established valence/arousal affective space. Towards this aim, we have developed an annotated sound events dataset using binaural processed versions of the available International Affective Digitized Sound (IADS) sound events library. All subjective affective annotations were obtained using the Self Assessment Manikin (SAM) approach. Preliminary results obtained by processing these annotation scores are likely to indicate a systematic change in the listener affective state as the sound source angular position changes. This trend is more obvious when the sound source is located outside of the visible field of the listener.