Speech emotion recognition (SER) is a pivotal technology for human-computer interaction systems. However, 80.77% of SER papers yield results that cannot be reproduced. We develop EMO-SUPERB, short for EMOtion Speech Universal PERformance Benchmark, which aims to enhance open-source initiatives for SER. EMO-SUPERB includes a user-friendly codebase to leverage 15 state-of-the-art speech self-supervised learning models (SSLMs) for exhaustive evaluation across six open-source SER datasets. EMO-SUPERB streamlines result sharing via an online leaderboard, fostering collaboration within a community-driven benchmark and thereby enhancing the development of SER. On average, 2.58% of annotations are annotated using natural language. SER relies on classification models and is unable to process natural languages, leading to the discarding of these valuable annotations. We prompt ChatGPT to mimic annotators, comprehend natural language annotations, and subsequently re-label the data. By utilizing labels generated by ChatGPT, we consistently achieve an average relative gain of 3.08% across all settings.
Our paper investigates effective methods for code generation in "specific-domain" applications, including the use of Large Language Models (LLMs) for data segmentation and renewal, as well as stimulating deeper thinking in LLMs through prompt adjustments. Using a real company product as an example, we provide user manuals, API documentation, and other data. The ideas discussed in this paper help segment and then convert this data into semantic vectors to better reflect their true positioning. Subsequently, user requirements are transformed into vectors to retrieve the most relevant content, achieving about 70% accuracy in simple to medium-complexity tasks through various prompt techniques. This paper is the first to enhance specific-domain code generation effectiveness from this perspective. Additionally, we experiment with generating more scripts from a limited number using llama2-based fine-tuning to test its effectiveness in professional domain code generation. This is a challenging and promising field, and once achieved, it will not only lead to breakthroughs in LLM development across multiple industries but also enable LLMs to understand and learn any new knowledge effectively.
The tasks of automatic lyrics transcription and lyrics alignment have witnessed significant performance improvements in the past few years. However, most of the previous works only focus on English in which large-scale datasets are available. In this paper, we address lyrics transcription and alignment of polyphonic Mandarin pop music in a low-resource setting. To deal with the data scarcity issue, we adapt pretrained Whisper model and fine-tune it on a monophonic Mandarin singing dataset. With the use of data augmentation and source separation model, results show that the proposed method achieves a character error rate of less than 18% on a Mandarin polyphonic dataset for lyrics transcription, and a mean absolute error of 0.071 seconds for lyrics alignment. Our results demonstrate the potential of adapting a pretrained speech model for lyrics transcription and alignment in low-resource scenarios.
Our research focuses on solving the zero-shot text classification problem in NLP, with a particular emphasis on innovative self-training strategies. To achieve this objective, we propose a novel self-training strategy that uses labels rather than text for training, significantly reducing the model's training time. Specifically, we use categories from Wikipedia as our training set and leverage the SBERT pre-trained model to establish positive correlations between pairs of categories within the same text, facilitating associative training. For new test datasets, we have improved the original self-training approach, eliminating the need for prior training and testing data from each target dataset. Instead, we adopt Wikipedia as a unified training dataset to better approximate the zero-shot scenario. This modification allows for rapid fine-tuning and inference across different datasets, greatly reducing the time required for self-training. Our experimental results demonstrate that this method can adapt the model to the target dataset within minutes. Compared to other BERT-based transformer models, our approach significantly reduces the amount of training data by training only on labels, not the actual text, and greatly improves training efficiency by utilizing a unified training set. Additionally, our method achieves state-of-the-art results on both the Yahoo Topic and AG News datasets.
This paper proposes to use both audio input and subject information to predict the personalized preference of two audio segments with the same content in different qualities. A siamese network is used to compare the inputs and predict the preference. Several different structures for each side of the siamese network are investigated, and an LDNet with PANNs' CNN6 as the encoder and a multi-layer perceptron block as the decoder outperforms a baseline model using only audio input the most, where the overall accuracy grows from 77.56% to 78.04%. Experimental results also show that using all the subject information, including age, gender, and the specifications of headphones or earphones, is more effective than using only a part of them.
Audio-visual synchronization aims to determine whether the mouth movements and speech in the video are synchronized. VocaLiST reaches state-of-the-art performance by incorporating multimodal Transformers to model audio-visual interact information. However, it requires high computing resources, making it impractical for real-world applications. This paper proposed an MTDVocaLiST model, which is trained by our proposed multimodal Transformer distillation (MTD) loss. MTD loss enables MTDVocaLiST model to deeply mimic the cross-attention distribution and value-relation in the Transformer of VocaLiST. Our proposed method is effective in two aspects: From the distillation method perspective, MTD loss outperforms other strong distillation baselines. From the distilled model's performance perspective: 1) MTDVocaLiST outperforms similar-size SOTA models, SyncNet, and PM models by 15.69% and 3.39%; 2) MTDVocaLiST reduces the model size of VocaLiST by 83.52%, yet still maintaining similar performance.
Audio-visual active speaker detection (AVASD) is well-developed, and now is an indispensable front-end for several multi-modal applications. However, to the best of our knowledge, the adversarial robustness of AVASD models hasn't been investigated, not to mention the effective defense against such attacks. In this paper, we are the first to reveal the vulnerability of AVASD models under audio-only, visual-only, and audio-visual adversarial attacks through extensive experiments. What's more, we also propose a novel audio-visual interaction loss (AVIL) for making attackers difficult to find feasible adversarial examples under an allocated attack budget. The loss aims at pushing the inter-class embeddings to be dispersed, namely non-speech and speech clusters, sufficiently disentangled, and pulling the intra-class embeddings as close as possible to keep them compact. Experimental results show the AVIL outperforms the adversarial training by 33.14 mAP (%) under multi-modal attacks.
The countermeasure (CM) model is developed to protect Automatic Speaker Verification (ASV) systems from spoof attacks and prevent resulting personal information leakage. Based on practicality and security considerations, the CM model is usually deployed on edge devices, which have more limited computing resources and storage space than cloud-based systems. This work proposes training strategies for a lightweight CM model for ASV, using generalized end-to-end (GE2E) pre-training and adversarial fine-tuning to improve performance, and applying knowledge distillation (KD) to reduce the size of the CM model. In the evaluation phase of the ASVspoof 2021 Logical Access task, the lightweight ResNetSE model reaches min t-DCF 0.2695 and EER 3.54%. Compared to the teacher model, the lightweight student model only uses 22.5% of parameters and 21.1% of multiply and accumulate operands of the teacher model.
In this paper, we propose a new dataset named EGDB, that con-tains transcriptions of the electric guitar performance of 240 tab-latures rendered with different tones. Moreover, we benchmark theperformance of two well-known transcription models proposed orig-inally for the piano on this dataset, along with a multi-loss Trans-former model that we newly propose. Our evaluation on this datasetand a separate set of real-world recordings demonstrate the influenceof timbre on the accuracy of guitar sheet transcription, the potentialof using multiple losses for Transformers, as well as the room forfurther improvement for this task.
Due to the rapid development of deep learning, we can now successfully separate singing voice from mono audio music. However, this separation can only extract human voices from other musical instruments, which is undesirable for karaoke content generation applications that only require the separation of lead singers. For this karaoke application, we need to separate the music containing male and female duets into two vocals, or extract a single lead vocal from the music containing vocal harmony. For this reason, we propose in this article to use a singer separation system, which generates karaoke content for one or two separated lead singers. In particular, we introduced three models for the singer separation task and designed an automatic model selection scheme to distinguish how many lead singers are in the song. We also collected a large enough data set, MIR-SingerSeparation, which has been publicly released to advance the frontier of this research. Our singer separation is most suitable for sentimental ballads and can be directly applied to karaoke content generation. As far as we know, this is the first singer-separation work for real-world karaoke applications.