Audio-Based Linguistic Feature Extraction for Enhancing Multi-lingual and Low-Resource Text-to-Speech

The difficulty of acquiring abundant, high-quality data, especially in multi-lingual contexts, has sparked interest in addressing low-resource scenarios. Moreover, current literature rely on fixed expressions from language IDs, which results in the inadequate learning of language representations, and the failure to generate speech in unseen languages. To address these challenges, we propose a novel method that directly extracts linguistic features from audio input while effectively filtering out miscellaneous acoustic information including speaker-specific attributes like timbre. Subjective and objective evaluations affirm the effectiveness of our approach for multi-lingual text-to-speech, and highlight its superiority in low-resource transfer learning for previously unseen language.

An Investigation Into Explainable Audio Hate Speech Detection

Research on hate speech has predominantly revolved around detection and interpretation from textual inputs, leaving verbal content largely unexplored. While there has been limited exploration into hate speech detection within verbal acoustic speech inputs, the aspect of interpretability has been overlooked. Therefore, we introduce a new task of explainable audio hate speech detection. Specifically, we aim to identify the precise time intervals, referred to as audio frame-level rationales, which serve as evidence for hate speech classification. Towards this end, we propose two different approaches: cascading and End-to-End (E2E). The cascading approach initially converts audio to transcripts, identifies hate speech within these transcripts, and subsequently locates the corresponding audio time frames. Conversely, the E2E approach processes audio utterances directly, which allows it to pinpoint hate speech within specific time frames. Additionally, due to the lack of explainable audio hate speech datasets that include audio frame-level rationales, we curated a synthetic audio dataset to train our models. We further validated these models on actual human speech utterances and found that the E2E approach outperforms the cascading method in terms of the audio frame Intersection over Union (IoU) metric. Furthermore, we observed that including frame-level rationales significantly enhances hate speech detection accuracy for the E2E approach. \textbf{Disclaimer} The reader may encounter content of an offensive or hateful nature. However, given the nature of the work, this cannot be avoided.

Leveraging the Interplay Between Syntactic and Acoustic Cues for Optimizing Korean TTS Pause Formation

Contemporary neural speech synthesis models have indeed demonstrated remarkable proficiency in synthetic speech generation as they have attained a level of quality comparable to that of human-produced speech. Nevertheless, it is important to note that these achievements have predominantly been verified within the context of high-resource languages such as English. Furthermore, the Tacotron and FastSpeech variants show substantial pausing errors when applied to the Korean language, which affects speech perception and naturalness. In order to address the aforementioned issues, we propose a novel framework that incorporates comprehensive modeling of both syntactic and acoustic cues that are associated with pausing patterns. Remarkably, our framework possesses the capability to consistently generate natural speech even for considerably more extended and intricate out-of-domain (OOD) sentences, despite its training on short audio clips. Architectural design choices are validated through comparisons with baseline models and ablation studies using subjective and objective metrics, thus confirming model performance.

Multi-Level Attention Aggregation for Language-Agnostic Speaker Replication

This paper explores the task of language-agnostic speaker replication, a novel endeavor that seeks to replicate a speaker's voice irrespective of the language they are speaking. Towards this end, we introduce a multi-level attention aggregation approach that systematically probes and amplifies various speaker-specific attributes in a hierarchical manner. Through rigorous evaluations across a wide range of scenarios including seen and unseen speakers conversing in seen and unseen lingua, we establish that our proposed model is able to achieve substantial speaker similarity, and is able to generalize to out-of-domain (OOD) cases.

Enhancing Zero-Shot Multi-Speaker TTS with Negated Speaker Representations

Zero-shot multi-speaker TTS aims to synthesize speech with the voice of a chosen target speaker without any fine-tuning. Prevailing methods, however, encounter limitations at adapting to new speakers of out-of-domain settings, primarily due to inadequate speaker disentanglement and content leakage. To overcome these constraints, we propose an innovative negation feature learning paradigm that models decoupled speaker attributes as deviations from the complete audio representation by utilizing the subtraction operation. By eliminating superfluous content information from the speaker representation, our negation scheme not only mitigates content leakage, thereby enhancing synthesis robustness, but also improves speaker fidelity. In addition, to facilitate the learning of diverse speaker attributes, we leverage multi-stream Transformers, which retain multiple hypotheses and instigate a training paradigm akin to ensemble learning. To unify these hypotheses and realize the final speaker representation, we employ attention pooling. Finally, in light of the imperative to generate target text utterances in the desired voice, we adopt adaptive layer normalizations to effectively fuse the previously generated speaker representation with the target text representations, as opposed to mere concatenation of the text and audio modalities. Extensive experiments and validations substantiate the efficacy of our proposed approach in preserving and harnessing speaker-specific attributes vis-`a-vis alternative baseline models.

Exploring the Viability of Synthetic Audio Data for Audio-Based Dialogue State Tracking

Dialogue state tracking plays a crucial role in extracting information in task-oriented dialogue systems. However, preceding research are limited to textual modalities, primarily due to the shortage of authentic human audio datasets. We address this by investigating synthetic audio data for audio-based DST. To this end, we develop cascading and end-to-end models, train them with our synthetic audio dataset, and test them on actual human speech data. To facilitate evaluation tailored to audio modalities, we introduce a novel PhonemeF1 to capture pronunciation similarity. Experimental results showed that models trained solely on synthetic datasets can generalize their performance to human voice data. By eliminating the dependency on human speech data collection, these insights pave the way for significant practical advancements in audio-based DST. Data and code are available at https://github.com/JihyunLee1/E2E-DST.

Multi-Channel Volumetric Neural Network for Knee Cartilage Segmentation in Cone-beam CT

Analyzing knee cartilage thickness and strain under load can help to further the understanding of the effects of diseases like Osteoarthritis. A precise segmentation of the cartilage is a necessary prerequisite for this analysis. This segmentation task has mainly been addressed in Magnetic Resonance Imaging, and was rarely investigated on contrast-enhanced Computed Tomography, where contrast agent visualizes the border between femoral and tibial cartilage. To overcome the main drawback of manual segmentation, namely its high time investment, we propose to use a 3D Convolutional Neural Network for this task. The presented architecture consists of a V-Net with SeLu activation, and a Tversky loss function. Due to the high imbalance between very few cartilage pixels and many background pixels, a high false positive rate is to be expected. To reduce this rate, the two largest segmented point clouds are extracted using a connected component analysis, since they most likely represent the medial and lateral tibial cartilage surfaces. The resulting segmentations are compared to manual segmentations, and achieve on average a recall of 0.69, which confirms the feasibility of this approach.