The combination of Computational Intelligence (CI) and music has attracted many efforts. In these studies, how to evaluate artificial music is a hot topic. The design of an evaluation system based on expert experiences is time-consuming and the performance is sometimes not satisfied. Therefore, learning a system from data is a feasible way. However, existing learning-based methods depend highly on the types of data and the downstream machine-learning tasks. In this paper, we model the evaluation system design problem as an offline inverse reinforcement learning problem. Specifically, we use a linear function to act as the evaluation system. The system is trained by natural evolution strategies (NES) using the Chinese traditional folk music data. The experiments show that the learned evaluation system can reasonably evaluate the developed music data and artificial music data generated by existing EC-based mutation operators. Meanwhile, the learned system can not only be applied to Chinese folk music data but also to Chinese opera music data which is not used in the training process.

Phonation modes play a vital role in voice quality evaluation and vocal health diagnosis. Existing studies on phonation modes cover feature analysis and classification of vowels, which does not apply to real-life scenarios. In this paper, we define the phonation mode detection (PMD) problem, which entails the prediction of phonation mode labels as well as their onset and offset timestamps. To address the PMD problem, we propose the first dataset PMSing, and an end-to-end PMD network (P-Net) to integrate phonation mode identification and boundary detection, which also prevents the oversegmentation of frame-level output. Furthermore, we introduce an adapted P-Net model (AP-Net) based on an adversarial discriminative training process using labeled data from one singer and unlabeled data from unseen singers. Experiments show that the P-Net outperforms the state-of-the-art methods with an F-score of 0.680, and the AP-Net also achieves an F-score of 0.658 for unseen singers.

Phonation mode detection predicts phonation modes and their temporal boundaries in singing and speech, holding promise for characterizing voice quality and vocal health. However, it is very challenging due to the domain disparities between training data and unannotated real-world recordings. To tackle this problem, we develop a disentangled adversarial domain adaptation network, which adapts the phonation mode detection model with the structure of the convolutional recurrent neural network pre-trained on the source domain to the target domain without phonation mode labels. Based on our curated sung and spoken dataset for phonation mode detection, we demonstrate that the subject and the singing-speech mismatches cause performance decline. By disentangling domain-invariant phonation mode and domain-specific embeddings, our method greatly enhances the effectiveness and explainability of unsupervised adversarial domain adaptation. Experiments show that the performance drop caused by the subject mismatch is alleviated via adaptation, resulting in 44.7% and 6.8% improvement of the F-score for singing and speech, respectively. The singing and speech domain adaptation experiment indicates that a model trained on singing data can be adapted to speech, yielding an F-score of 0.56, commensurate with the F-score of 0.59 achieved using a model exclusively trained on speech data. By further investigating the disentangled embeddings, we find that the phonation mode feature shared by singing and speech is invariant to pitch. These results inspire reliable and versatile applications in voice quality evaluation and paralinguistic information retrieval.

Music tone quality evaluation is generally performed by experts. It could be subjective and short of consistency and fairness as well as time-consuming. In this paper we present a new method for identifying the clarinet reed quality by evaluating tone quality based on the harmonic structure and energy distribution. We first decouple the quality of reed and clarinet pipe based on the acoustic harmonics, and discover that the reed quality is strongly relevant to the even parts of the harmonics. Then we construct a features set consisting of the even harmonic envelope and the energy distribution of harmonics in spectrum. The annotated clarinet audio data are recorded from 3 levels of performers and the tone quality is classified by machine learning. The results show that our new method for identifying low and medium high tones significantly outperforms previous methods.