相关论文: Nonparametric Bayesian Double Articulation Analyze…

This research presents a hybrid emotion recognition system integrating advanced Deep Learning, Natural Language Processing (NLP), and Large Language Models (LLMs) to analyze audio and textual data for enhancing customer interactions in…

Classification tasks are typically handled using Machine Learning (ML) models, which lack a balance between accuracy and interpretability. This paper introduces a new approach for classification tasks using Large Language Models (LLMs) in…

Speech disfluency modeling is the bottleneck for both speech therapy and language learning. However, there is no effective AI solution to systematically tackle this problem. We solidify the concept of disfluent speech and disfluent speech…

Recent research has focused on applying speech large language model (SLLM) to improve speech emotion recognition (SER). However, the inherently high frame rate in speech modality severely limits the signal processing and understanding…

Deep Metric Learning (DML) plays a critical role in various machine learning tasks. However, most existing deep metric learning methods with binary similarity are sensitive to noisy labels, which are widely present in real-world data. Since…

Frame alignments can be computed by different methods in GMM-based speaker verification. By incorporating a phonetic Gaussian mixture model (PGMM), we are able to compare the performance using alignments extracted from the deep neural…

Recent advances in Speech Large Language Models (Speech LLMs) have led to great progress in speech understanding tasks such as Automatic Speech Recognition (ASR) and Speech Emotion Recognition (SER). However, whether these models can…

In this paper, we describe a statistical parametric speech synthesis approach with unit-level acoustic representation. In conventional deep neural network based speech synthesis, the input text features are repeated for the entire duration…

Direct speech-to-speech translation (S2ST) translates speech from one language into another using a single model. However, due to the presence of linguistic and acoustic diversity, the target speech follows a complex multimodal…

In this paper we aim to automatically discover high quality frame-level speech features and acoustic tokens directly from unlabeled speech data. A Multi-granular Acoustic Tokenizer (MAT) was proposed for automatic discovery of multiple sets…

We introduce a two-stage self-supervised framework that combines the Joint-Embedding Predictive Architecture (JEPA) with a Density Adaptive Attention Mechanism (DAAM) for learning robust speech representations. Stage~1 uses JEPA with DAAM…

Diadochokinetic speech tasks (DDK), in which participants repeatedly produce syllables, are commonly used as part of the assessment of speech motor impairments. These studies rely on manual analyses that are time-intensive, subjective, and…

Speech recognition systems are often highly domain dependent, a fact widely reported in the literature. However the concept of domain is complex and not bound to clear criteria. Hence it is often not evident if data should be considered to…

This paper presents a novel hybrid Automatic Speech Recognition (ASR) system designed specifically for resource-constrained robots. The proposed approach combines Hidden Markov Models (HMMs) with deep learning models and leverages socket…

We present an unsupervised learning algorithm that acquires a natural-language lexicon from raw speech. The algorithm is based on the optimal encoding of symbol sequences in an MDL framework, and uses a hierarchical representation of…

In this paper we present our researches regarding automat parsing of audio recordings. These recordings are obtained from children with dyslalia and are necessary for an accurate identification of speech problems. We develop the ADM…

We introduce a new beam search decoder that is fully differentiable, making it possible to optimize at training time through the inference procedure. Our decoder allows us to combine models which operate at different granularities (e.g.…

We propose HILBERT (HIerarchical Long-sequence Balanced Embedding with Reciprocal contrastive Training), a cross-attentive multimodal framework for learning document-level audio-text representations from long, segmented sequences in…

In this work we aim to discover high quality speech features and linguistic units directly from unlabeled speech data in a zero resource scenario. The results are evaluated using the metrics and corpora proposed in the Zero Resource Speech…

We propose a novel document generation process based on hierarchical latent tree models (HLTMs) learned from data. An HLTM has a layer of observed word variables at the bottom and multiple layers of latent variables on top. For each…