Abstract:Audio-Visual Target Speaker Extraction (AV-TSE) aims to mimic the human ability to enhance auditory perception using visual cues. Although numerous models have been proposed recently, most of them estimate target signals by primarily relying on local dependencies within acoustic features, underutilizing the human-like capacity to infer unclear parts of speech through contextual information. This limitation results in not only suboptimal performance but also inconsistent extraction quality across the utterance, with some segments exhibiting poor quality or inadequate suppression of interfering speakers. To close this gap, we propose a model-agnostic strategy called the Mask-And-Recover (MAR). It integrates both inter- and intra-modality contextual correlations to enable global inference within extraction modules. Additionally, to better target challenging parts within each sample, we introduce a Fine-grained Confidence Score (FCS) model to assess extraction quality and guide extraction modules to emphasize improvement on low-quality segments. To validate the effectiveness of our proposed model-agnostic training paradigm, six popular AV-TSE backbones were adopted for evaluation on the VoxCeleb2 dataset, demonstrating consistent performance improvements across various metrics.
Abstract:We propose Universal target audio Separation (UniSep), addressing the separation task on arbitrary mixtures of different types of audio. Distinguished from previous studies, UniSep is performed on unlimited source domains and unlimited source numbers. We formulate the separation task as a sequence-to-sequence problem, and a large language model (LLM) is used to model the audio sequence in the discrete latent space, leveraging the power of LLM in handling complex mixture audios with large-scale data. Moreover, a novel pre-training strategy is proposed to utilize audio-only data, which reduces the efforts of large-scale data simulation and enhances the ability of LLMs to understand the consistency and correlation of information within audio sequences. We also demonstrate the effectiveness of scaling datasets in an audio separation task: we use large-scale data (36.5k hours), including speech, music, and sound, to train a universal target audio separation model that is not limited to a specific domain. Experiments show that UniSep achieves competitive subjective and objective evaluation results compared with single-task models.
Abstract:Improving context faithfulness in large language models is essential for developing trustworthy retrieval augmented generation systems and mitigating hallucinations, especially in long-form question answering (LFQA) tasks or scenarios involving knowledge conflicts. Existing methods either intervene LLMs only at inference without addressing their inherent limitations or overlook the potential for self-improvement. In this paper, we introduce GenDiE (Generate, Discriminate, Evolve), a novel self-evolving framework that enhances context faithfulness through fine-grained sentence-level optimization. GenDiE combines both generative and discriminative training, equipping LLMs with self-generation and self-scoring capabilities to facilitate iterative self-evolution. This supports both data construction for model alignment and score-guided search during inference. Furthermore, by treating each sentence in a response as an independent optimization unit, GenDiE effectively addresses the limitations of previous approaches that optimize at the holistic answer level, which may miss unfaithful details. Experiments on ASQA (in-domain LFQA) and ConFiQA (out-of-domain counterfactual QA) datasets demonstrate that GenDiE surpasses various baselines in both faithfulness and correctness, and exhibits robust performance for domain adaptation.
Abstract:Empathetic dialogue is crucial for natural human-computer interaction, allowing the dialogue system to respond in a more personalized and emotionally aware manner, improving user satisfaction and engagement. The emergence of large language models (LLMs) has revolutionized dialogue generation by harnessing their powerful capabilities and shown its potential in multimodal domains. Many studies have integrated speech with text-based LLMs to take speech question as input and output text response. However, the lack of spoken question-answering datasets that include speech style information to supervised fine-tuning (SFT) limits the performance of these systems. As a result, while these systems excel at understanding speech content, they often struggle to generate empathetic responses. In response, we propose a novel approach that circumvents the need for question-answering data, called Listen, Perceive, and Express (LPE). Our method employs a two-stage training process, initially guiding the LLM to listen the content and perceive the emotional aspects of speech. Subsequently, we utilize Chain-of-Thought (CoT) prompting to unlock the model's potential for expressing empathetic responses based on listened spoken content and perceived emotional cues. We employ experiments to prove the effectiveness of proposed method. To our knowledge, this is the first attempt to leverage CoT for speech-based dialogue.
Abstract:Controlling text-to-speech (TTS) systems to synthesize speech with the prosodic characteristics expected by users has attracted much attention. To achieve controllability, current studies focus on two main directions: (1) using reference speech as prosody prompt to guide speech synthesis, and (2) using natural language descriptions to control the generation process. However, finding reference speech that exactly contains the prosody that users want to synthesize takes a lot of effort. Description-based guidance in TTS systems can only determine the overall prosody, which has difficulty in achieving fine-grained prosody control over the synthesized speech. In this paper, we propose DrawSpeech, a sketch-conditioned diffusion model capable of generating speech based on any prosody sketches drawn by users. Specifically, the prosody sketches are fed to DrawSpeech to provide a rough indication of the expected prosody trends. DrawSpeech then recovers the detailed pitch and energy contours based on the coarse sketches and synthesizes the desired speech. Experimental results show that DrawSpeech can generate speech with a wide variety of prosody and can precisely control the fine-grained prosody in a user-friendly manner. Our implementation and audio samples are publicly available.
Abstract:Early detection of neurocognitive disorders (NCDs) is crucial for timely intervention and disease management. Speech analysis offers a non-intrusive and scalable screening method, particularly through narrative tasks in neuropsychological assessment tools. Traditional narrative analysis often focuses on local indicators in microstructure, such as word usage and syntax. While these features provide insights into language production abilities, they often fail to capture global narrative patterns, or microstructures. Macrostructures include coherence, thematic organization, and logical progressions, reflecting essential cognitive skills potentially critical for recognizing NCDs. Addressing this gap, we propose to investigate specific cognitive and linguistic challenges by analyzing topical shifts, temporal dynamics, and the coherence of narratives over time, aiming to reveal cognitive deficits by identifying narrative impairments, and exploring their impact on communication and cognition. The investigation is based on the CU-MARVEL Rabbit Story corpus, which comprises recordings of a story-telling task from 758 older adults. We developed two approaches: the Dynamic Topic Models (DTM)-based temporal analysis to examine the evolution of topics over time, and the Text-Image Temporal Alignment Network (TITAN) to evaluate the coherence between spoken narratives and visual stimuli. DTM-based approach validated the effectiveness of dynamic topic consistency as a macrostructural metric (F1=0.61, AUC=0.78). The TITAN approach achieved the highest performance (F1=0.72, AUC=0.81), surpassing established microstructural and macrostructural feature sets. Cross-comparison and regression tasks further demonstrated the effectiveness of proposed dynamic macrostructural modeling approaches for NCD detection.
Abstract:Grapheme-to-phoneme (G2P) conversion serves as an essential component in Chinese Mandarin text-to-speech (TTS) system, where polyphone disambiguation is the core issue. In this paper, we propose an end-to-end framework to predict the pronunciation of a polyphonic character, which accepts sentence containing polyphonic character as input in the form of Chinese character sequence without the necessity of any preprocessing. The proposed method consists of a pre-trained bidirectional encoder representations from Transformers (BERT) model and a neural network (NN) based classifier. The pre-trained BERT model extracts semantic features from a raw Chinese character sequence and the NN based classifier predicts the polyphonic character's pronunciation according to BERT output. In out experiments, we implemented three classifiers, a fully-connected network based classifier, a long short-term memory (LSTM) network based classifier and a Transformer block based classifier. The experimental results compared with the baseline approach based on LSTM demonstrate that, the pre-trained model extracts effective semantic features, which greatly enhances the performance of polyphone disambiguation. In addition, we also explored the impact of contextual information on polyphone disambiguation.
Abstract:Identifying the emotional state from speech is essential for the natural interaction of the machine with the speaker. However, extracting effective features for emotion recognition is difficult, as emotions are ambiguous. We propose a novel approach to learn discriminative features from variable length spectrograms for emotion recognition by cooperating softmax cross-entropy loss and center loss together. The softmax cross-entropy loss enables features from different emotion categories separable, and center loss efficiently pulls the features belonging to the same emotion category to their center. By combining the two losses together, the discriminative power will be highly enhanced, which leads to network learning more effective features for emotion recognition. As demonstrated by the experimental results, after introducing center loss, both the unweighted accuracy and weighted accuracy are improved by over 3\% on Mel-spectrogram input, and more than 4\% on Short Time Fourier Transform spectrogram input.
Abstract:We propose an ontology-grounded approach to Knowledge Graph (KG) construction using Large Language Models (LLMs) on a knowledge base. An ontology is authored by generating Competency Questions (CQ) on knowledge base to discover knowledge scope, extracting relations from CQs, and attempt to replace equivalent relations by their counterpart in Wikidata. To ensure consistency and interpretability in the resulting KG, we ground generation of KG with the authored ontology based on extracted relations. Evaluation on benchmark datasets demonstrates competitive performance in knowledge graph construction task. Our work presents a promising direction for scalable KG construction pipeline with minimal human intervention, that yields high quality and human-interpretable KGs, which are interoperable with Wikidata semantics for potential knowledge base expansion.
Abstract:Automatic Speech Recognition (ASR) plays an important role in speech-based automatic detection of Alzheimer's disease (AD). However, recognition errors could propagate downstream, potentially impacting the detection decisions. Recent studies have revealed a non-linear relationship between word error rates (WER) and AD detection performance, where ASR transcriptions with notable errors could still yield AD detection accuracy equivalent to that based on manual transcriptions. This work presents a series of analyses to explore the effect of ASR transcription errors in BERT-based AD detection systems. Our investigation reveals that not all ASR errors contribute equally to detection performance. Certain words, such as stopwords, despite constituting a large proportion of errors, are shown to play a limited role in distinguishing AD. In contrast, the keywords related to diagnosis tasks exhibit significantly greater importance relative to other words. These findings provide insights into the interplay between ASR errors and the downstream detection model.