Recent studies focus on developing efficient systems for acoustic scene classification (ASC) using convolutional neural networks (CNNs), which typically consist of consecutive kernels. This paper highlights the benefits of using separate kernels as a more powerful and efficient design approach in ASC tasks. Inspired by the time-frequency nature of audio signals, we propose TF-SepNet, a CNN architecture that separates the feature processing along the time and frequency dimensions. Features resulted from the separate paths are then merged by channels and directly forwarded to the classifier. Instead of the conventional two dimensional (2D) kernel, TF-SepNet incorporates one dimensional (1D) kernels to reduce the computational costs. Experiments have been conducted using the TAU Urban Acoustic Scene 2022 Mobile development dataset. The results show that TF-SepNet outperforms similar state-of-the-arts that use consecutive kernels. A further investigation reveals that the separate kernels lead to a larger effective receptive field (ERF), which enables TF-SepNet to capture more time-frequency features.
Pitch and meter are two fundamental music features for symbolic music generation tasks, where researchers usually choose different encoding methods depending on specific goals. However, the advantages and drawbacks of different encoding methods have not been frequently discussed. This paper presents a integrated analysis of the influence of two low-level feature, pitch and meter, on the performance of a token-based sequential music generation model. First, the commonly used MIDI number encoding and a less used class-octave encoding are compared. Second, an dense intra-bar metric grid is imposed to the encoded sequence as auxiliary features. Different complexity and resolutions of the metric grid are compared. For complexity, the single token approach and the multiple token approach are compared; for grid resolution, 0 (ablation), 1 (bar-level), 4 (downbeat-level) 12, (8th-triplet-level) up to 64 (64th-note-grid-level) are compared; for duration resolution, 4, 8, 12 and 16 subdivisions per beat are compared. All different encodings are tested on separately trained Transformer-XL models for a melody generation task. Regarding distribution similarity of several objective evaluation metrics to the test dataset, results suggest that the class-octave encoding significantly outperforms the taken-for-granted MIDI encoding on pitch-related metrics; finer grids and multiple-token grids improve the rhythmic quality, but also suffer from over-fitting at early training stage. Results display a general phenomenon of over-fitting from two aspects, the pitch embedding space and the test loss of the single-token grid encoding. From a practical perspective, we both demonstrate the feasibility and raise the concern of easy over-fitting problem of using smaller networks and lower embedding dimensions on the generation task. The findings can also contribute to futural models in terms of feature engineering.
Audio captioning is the task of generating captions that describe the content of audio clips. In the real world, many objects produce similar sounds. It is difficult to identify these auditory ambiguous sound events with access to audio information only. How to accurately recognize ambiguous sounds is a major challenge for audio captioning systems. In this work, inspired by the audio-visual multi-modal perception of human beings, we propose visually-aware audio captioning, which makes use of visual information to help the recognition of ambiguous sounding objects. Specifically, we introduce an off-the-shelf visual encoder to process the video inputs, and incorporate the extracted visual features into an audio captioning system. Furthermore, to better exploit complementary contexts from redundant audio-visual streams, we propose an audio-visual attention mechanism that integrates audio and visual information adaptively according to their confidence levels. Experimental results on AudioCaps, the largest publicly available audio captioning dataset, show that the proposed method achieves significant improvement over a strong baseline audio captioning system and is on par with the state-of-the-art result.
MobileNet is widely used for Acoustic Scene Classification (ASC) in embedded systems. Existing works reduce the complexity of ASC algorithms by pruning some components, e.g. pruning channels in the convolutional layer. In practice, the maximum proportion of channels being pruned, which is defined as Ratio of Prunable Channels ($R_\textit{PC}$), is often decided empirically. This paper proposes a method that determines the $R_\textit{PC}$ by simple linear regression models related to the Sparsity of Channels ($S_C$) in the convolutional layers. In the experiment, $R_\textit{PC}$ is examined by removing inactive channels until reaching a knee point of performance decrease. Simple methods for calculating the $S_C$ of trained models and resulted $R_\textit{PC}$ are proposed. The experiment results demonstrate that 1) the decision of $R_\textit{PC}$ is linearly dependent on $S_C$ and the hyper-parameters have a little impact on the relationship; 2) MobileNet shows a high sensitivity and stability on proposed method.
This paper refers to the extraction of multiple fundamental frequencies (multiple F0) based on PYIN, an algorithm for extracting the fundamental frequency (F0) of monophonic music, and a trained convolutional neural networks (CNN) model, where a pitch salience function of the input signal is produced to estimate the multiple F0. The implementation of these two algorithms and their corresponding advantages and disadvantages are discussed in this article. Analysing the different performance of these two methods, PYIN is applied to supplement the F0 extracted from the trained CNN model to combine the advantages of these two algorithms. For evaluation, four pieces played by two violins are used, and the performance of the models are evaluated accoring to the flatness of the F0 curve extracted. The result shows the combined model outperforms the original algorithms when extracting F0 from monophonic music and polyphonic music.
Audio captioning is a task that generates description of audio based on content. Pre-trained models are widely used in audio captioning due to high complexity. Unless a comprehensive system is re-trained, it is hard to determine how well pre-trained models contribute to audio captioning system. To prevent the time consuming and energy consuming process of retraining, it is necessary to propose a preditor of performance for the pre-trained model in audio captioning. In this paper, a series of pre-trained models are investigated for the correlation between extracted audio features and the performance of audio captioning. A couple of predictor is proposed based on the experiment results.The result demonstrates that the kurtosis and skewness of audio features extracted may act as an indicator of the performance of audio captioning systems for pre-trained audio due to the high correlation between kurtosis and skewness of audio features and the performance of audio captioning systems.
Keyword spotting (KWS) is beneficial for voice-based user interactions with low-power devices at the edge. The edge devices are usually always-on, so edge computing brings bandwidth savings and privacy protection. The devices typically have limited memory spaces, computational performances, power and costs, for example, Cortex-M based microcontrollers. The challenge is to meet the high computation and low-latency requirements of deep learning on these devices. This paper firstly shows our small-footprint KWS system running on STM32F7 microcontroller with Cortex-M7 core @216MHz and 512KB static RAM. Our selected convolutional neural network (CNN) architecture has simplified number of operations for KWS to meet the constraint of edge devices. Our baseline system generates classification results for each 37ms including real-time audio feature extraction part. This paper further evaluates the actual performance for different pruning and quantization methods on microcontroller, including different granularity of sparsity, skipping zero weights, weight-prioritized loop order, and SIMD instruction. The result shows that for microcontrollers, there are considerable challenges for accelerate unstructured pruned models, and the structured pruning is more friendly than unstructured pruning. The result also verified that the performance improvement for quantization and SIMD instruction.
Automated audio captioning aims to use natural language to describe the content of audio data. This paper presents an audio captioning system with an encoder-decoder architecture, where the decoder predicts words based on audio features extracted by the encoder. To improve the proposed system, transfer learning from either an upstream audio-related task or a large in-domain dataset is introduced to mitigate the problem induced by data scarcity. Besides, evaluation metrics are incorporated into the optimization of the model with reinforcement learning, which helps address the problem of ``exposure bias'' induced by ``teacher forcing'' training strategy and the mismatch between the evaluation metrics and the loss function. The resulting system was ranked 3rd in DCASE 2021 Task 6. Ablation studies are carried out to investigate how much each element in the proposed system can contribute to final performance. The results show that the proposed techniques significantly improve the scores of the evaluation metrics, however, reinforcement learning may impact adversely on the quality of the generated captions.
Heart Sound (also known as phonocardiogram (PCG)) analysis is a popular way that detects cardiovascular diseases (CVDs). Most PCG analysis uses supervised way, which demands both normal and abnormal samples. This paper proposes a method of unsupervised PCG analysis that uses beta variational auto-encoder ($\beta-\text{VAE}$) to model the normal PCG signals. The best performed model reaches an AUC (Area Under Curve) value of 0.91 in ROC (Receiver Operating Characteristic) test for PCG signals collected from the same source. Unlike majority of $\beta-\text{VAE}$s that are used as generative models, the best-performed $\beta-\text{VAE}$ has a $\beta$ value smaller than 1. Further experiments then find that the introduction of a light weighted KL divergence between distribution of latent space and normal distribution improves the performance of anomaly PCG detection based on anomaly scores resulted by reconstruction loss. The fact suggests that anomaly score based on reconstruction loss may be better than anomaly scores based on latent vectors of samples
In this paper, the dataset used for the data challenge organised by Conference on Sound and Music Technology (CSMT) is introduced. The CSMT data challenge requires participants to identify whether a given piece of melody is generated by computer or is composed by human. The dataset is formed by two parts: development dataset and evaluation dataset. The development dataset contains only computer generated melodies whereas the evaluation dataset contain both computer generated melodies and human composed melodies. The aim of the dataset is to examine whether it is possible to distinguish computer generated melodies by learning the feature of generated melodies.