Related papers: PicoAudio2: Temporal Controllable Text-to-Audio Ge…

The practical utility of Speech Emotion Recognition (SER) systems is undermined by their fragility to domain shifts, such as speaker variability, the distinction between acted and naturalistic emotions, and cross-corpus variations. While…

Despite significant advancements in natural language generation, controlling language models to produce texts with desired attributes remains a formidable challenge. In this work, we introduce RSA-Control, a training-free controllable text…

Voice design from natural language aims to generate speaker timbres directly from free-form textual descriptions, allowing users to create voices tailored to specific roles, personalities, and emotions. Such controllable voice creation…

Test-time domain adaptation aims to adapt a source pre-trained model to a target domain without using any source data. Existing works mainly consider the case where the target domain is static. However, real-world machine perception systems…

Speech LLM post-training increasingly relies on efficient cross-modal alignment and robust low-resource adaptation, yet collecting large-scale audio-text pairs remains costly. Text-only alignment methods such as TASU reduce this burden by…

Audio-driven talking head generation aims to create vivid and realistic videos from a static portrait and speech. Existing AR-based methods rely on intermediate facial representations, which limit their expressiveness and realism.…

Scarcity of training data for task-oriented dialogue systems is a well known problem that is usually tackled with costly and time-consuming manual data annotation. An alternative solution is to rely on automatic text generation which,…

Test-Time Augmentation (TTA) is a very powerful heuristic that takes advantage of data augmentation during testing to produce averaged output. Despite the experimental effectiveness of TTA, there is insufficient discussion of its…

Although current text-guided music generation technology can cope with simple creative scenarios, achieving fine-grained control over individual text-modality conditions remains challenging as user demands become more intricate.…

The video-to-audio (V2A) generation task has drawn attention in the field of multimedia due to the practicality in producing Foley sound. Semantic and temporal conditions are fed to the generation model to indicate sound events and temporal…

The availability of highly convincing audio deepfake generators highlights the need for designing robust audio deepfake detectors. Existing works often rely solely on real and fake data available in the training set, which may lead to…

Data availability is a bottleneck during early stages of development of new capabilities for intelligent artificial agents. We investigate the use of text generation techniques to augment the training data of a popular commercial artificial…

Speech Foundation Models encounter significant performance degradation when deployed in real-world scenarios involving acoustic domain shifts, such as background noise and speaker accents. Test-time adaptation (TTA) has recently emerged as…

An end-to-end (e2e) text-to-speech (TTS) system is a deep architecture that learns to associate a text string with acoustic speech patterns from a curated dataset. It is expected that all aspects associated with speech production, such as…

We introduce SRC-gAudio, a novel audio generation model designed to facilitate text-to-audio generation across a wide range of sampling rates within a single model architecture. SRC-gAudio incorporates the sampling rate as part of the…

Text-to-Time Series generation holds significant potential to address challenges such as data sparsity, imbalance, and limited availability of multimodal time series datasets across domains. While diffusion models have achieved remarkable…

We investigate the use of zero-shot text-to-speech (ZS-TTS) as a data augmentation source for low-resource personalized speech synthesis. While synthetic augmentation can provide linguistically rich and phonetically diverse speech, naively…

Recent advances in Text-to-Speech (TTS) systems have substantially increased the realism of synthetic speech, raising new challenges for audio deepfake detection. This work presents a comparative evaluation of three state-of-the-art TTS…

Table-to-text generation involves generating appropriate textual descriptions given structured tabular data. It has attracted increasing attention in recent years thanks to the popularity of neural network models and the availability of…

We propose a general feedback-driven retrieval-augmented generation (RAG) approach that leverages Large Audio Language Models (LALMs) to address the missing or imperfect synthesis of specific sound events in text-to-audio (TTA) generation.…