Sound

Tencent AI Lab has released Covo-Audio, a 7B-parameter end-to-end Large Audio Language Model (LALM). The model is designed to unify speech processing and language...

Speech technology still has a data distribution problem. Automatic Speech Recognition (ASR) and Text-to-Speech (TTS) systems have improved rapidly for high-resource languages, but many...

The landscape of Text-to-Speech (TTS) is moving away from modular pipelines toward integrated Large Audio Models (LAMs). Fish Audio’s release of S2-Pro, the flagship...

Alibaba Cloud’s Qwen team has open-sourced Qwen3-TTS, a family of multilingual text-to-speech models that target three core tasks in one stack, voice clone, voice...

Microsoft has released VibeVoice-ASR as part of the VibeVoice family of open source frontier voice AI models. VibeVoice-ASR is described as a unified speech-to-text...

Chroma 1.0 is a real time speech to speech dialogue model that takes audio as input and returns audio as output while preserving the...

Inworld AI has introduced Inworld TTS-1.5, an upgrade to its TTS-1 family that targets realtime voice agents with strict constraints on latency, quality, and...

In this tutorial, we build an end-to-end streaming voice agent that mirrors how modern low-latency conversational systems operate in real time. We simulate the...

NVIDIA Researchers released PersonaPlex-7B-v1, a full duplex speech to speech conversational model that targets natural voice interactions with precise persona control. From ASR→LLM→TTS to a...

Google's Magenta team has introduced Magenta RealTime (Magenta RT), an open-weight, real-time music generation model that brings unprecedented interactivity to generative audio. Licensed under...

Recent developments have shown that RL can significantly enhance the reasoning abilities of LLMs. Building on this progress, the study aims to improve Audio...

Text-to-audio generation has emerged as a transformative approach for synthesizing sound directly from textual prompts, offering practical use in music production, gaming, and virtual...

The field of Voice AI is evolving toward more representative and adaptable systems. While many existing models have been trained on carefully curated, studio-recorded...

Audio diffusion models have achieved high-quality speech, music, and Foley sound synthesis, yet they predominantly excel at sample generation rather than parameter optimization. Tasks...

AI models have made remarkable strides in generating speech, music, and other forms of audio content, expanding possibilities across communication, entertainment, and human-computer interaction....

Speech generation technology has advanced considerably in recent years, yet there remain significant challenges. Traditional text-to-speech systems often rely on datasets derived from audiobooks....

Humans possess an extraordinary ability to localize sound sources and interpret their environment using auditory cues, a phenomenon termed spatial hearing. This capability enables...

Speech processing systems often struggle to deliver clear audio in noisy environments. This challenge impacts applications such as hearing aids, automatic speech recognition (ASR),...

Text-to-audio generation has transformed how audio content is created, automating processes that traditionally required significant expertise and time. This technology enables the conversion of...

Speech synthesis technology has made notable strides, yet challenges remain in delivering real-time, natural-sounding audio. Common obstacles include latency, pronunciation accuracy, and speaker consistency—issues...

Spoken term detection (STD) is a critical area in speech processing, enabling the identification of specific phrases or terms in large audio archives. This...

Creating, editing, and transforming music and sounds present both technical and creative challenges. Current AI models often struggle with versatility, specializing in narrow tasks...

A critical challenge in Subjective Speech Quality Assessment (SSQA) is enabling models to generalize across diverse and unseen speech domains. General SSQA models evaluate...

Neural audio compression has emerged as a critical challenge in digital signal processing, particularly in achieving efficient audio representation while preserving quality. Traditional audio...

Text-to-Audio (TTA) and Text-to-Music (TTM) generation have seen significant advancements in recent years, driven by audio-domain diffusion models. These models have demonstrated superior audio...

Neural audio codecs have completely changed how audio is compressed and handled, by converting continuous audio signals into discrete tokens. This technique uses generative...

A major challenge in the field of Speech-Language Models (SLMs) is the lack of comprehensive evaluation metrics that go beyond basic textual content modeling....

Speech processing focuses on developing systems to analyze, interpret, and generate human speech. These technologies encompass a range of applications, such as automatic speech...

Large-scale language models have made significant progress in generative tasks involving multiple-speaker speech synthesis, music generation, and audio generation. The integration of speech modality...

Music information retrieval (MIR) has become increasingly vital as the digitalization of music has exploded. MIR involves the development of algorithms that can analyze...

Achieving high-fidelity waveform generation in audio synthesis is a significant challenge, particularly due to the slow inference times associated with traditional models like Conditional...

High-fidelity waveform generation, particularly in text-to-speech (TTS) and audio generation applications, involves several critical challenges. Accurately generating natural-sounding audio remains a primary issue, essential...

In the field of Artificial Intelligence, open, generative models stand out as a cornerstone for progress. These models are vital for advancing research and...

Voice interaction technology has significantly evolved with the advancements in artificial intelligence (AI). The field focuses on enhancing natural communication between humans and machines,...

Researchers from C4DM, Queen Mary University of London, Sony AI, and Music X Lab, MBZUAI, have introduced Instruct-MusicGen to address the challenge of text-to-music...

Audio classification has evolved significantly with the adoption of deep learning models. Initially dominated by Convolutional Neural Networks (CNNs), this field has shifted towards...

Brain-computer interfaces (BCIs) focus on creating direct communication pathways between the brain and external devices. This technology has applications in medical, entertainment, and communication...

In the ever-expanding landscape of artificial intelligence, Large Language Models (LLMs) have emerged as versatile tools, making significant strides across various domains. As they...

With the introduction of some brilliant generative Artificial intelligence models, such as ChatGPT, GEMINI, and BARD, the demand for AI-generated content is rising in...

Navigating through the intricate landscape of speech separation, researchers have continually sought to refine the clarity and intelligibility of audio in bustling environments. This...

The intersection of AI and the arts, especially music, has become an important field of study due to its deep implications for human creativity....

Recent advancements in self-supervised representation learning, sequence modeling, and audio synthesis have significantly enhanced the performance of conditional audio generation. The prevailing approach involves...

Advancements in creative media generation, with audio editing at the forefront of this technological renaissance. The innovative use of Large Language Models (LLMs) for...

Music generation has long been a fascinating domain, blending creativity with technology to produce compositions that resonate with human emotions. The process involves generating...

In the past decade or so, Artificial Intelligence (AI) has made significant strides and is now part of automation pipelines in various applications. New...

In the rapidly evolving field of audio synthesis, a new frontier has been crossed with the development of Stable Audio, a state-of-the-art generative model....

Technological advancements have been pivotal in transcending the boundaries of what's achievable in the domain of audio generation, especially in high-fidelity audio synthesis. As...

Significant improvements have been made in enhancing the accuracy and efficiency of Automatic Speech Recognition (ASR) systems. The recent research delves into integrating an...

Synthesizers, electronic instruments producing diverse sounds, are integral to music genres. Traditional sound design involves intricate parameter adjustments, demanding expertise. Neural networks aid by...

A key challenge in text-to-music generation using diffusion models is controlling pre-trained text-to-music diffusion models at inference time. While effective, these models can only...

In audio technology, researchers have made significant strides in developing models for audio generation. However, the challenge lies in creating models that can efficiently...

In recent years, there has been remarkable progress in speech generation, achieving one-shot generation capability virtually indistinguishable from real human voice. The demand for...

Parallel Text-to-Speech (TTS) models are commonly used for on-the-fly speech synthesis, providing enhanced control and faster synthesis than traditional auto-regressive models. Despite their advantages,...

The necessity for large-scale music datasets with natural language captions is a difficulty for text-to-music production, which this research addresses. Although closed-source captioned datasets...

There are two challenges in voice cloning: 1) Flexible Voice Style Control- Many Instant Voice Cloning (IVC) approaches cannot manipulate voice styles after cloning...

With the growing number of advancements in Artificial Intelligence, the fields of Natural Language Processing, Natural Language Generation, and Computer Vision have gained massive...

Audio plays an important role in the field of media and entertainment. It influences everything from movies and podcasts to audiobooks and video games....

In machine learning, a diffusion model is a generative model commonly used for image and audio generation tasks. The diffusion model uses a diffusion...

A key aspect of generative AI is audio generation. In recent years, the popularity of generative AI has led to increasingly diverse and emerging...

A key challenge in the field of digital audio processing is audio super-resolution. It aims to enhance the quality of audio signals by anticipating...

The intelligibility and naturalness of synthesized speech have improved due to recent developments in text-to-speech systems. Large-scale TTS systems have been created for multi-speaker...

The development of neural networks and their constantly increasing popularity have led to substantial improvements in speech synthesis technologies. The majority of speech synthesis...

The paper introduces VITS2, a single-stage text-to-speech model that synthesizes more natural speech by improving various aspects of previous models. The model addresses issues...

Music, often hailed as the universal language of humanity by Henry Wadsworth Longfellow, carries within it the essence of harmony, melody, and rhythm, weaving...

In recent years, Significant progress has been made in music generation using Machine Learning models. However, there are still challenges in achieving efficiency and...

Significant improvements in the autoregressive creation of speech and music have recently been made due to discrete acoustic token modeling developments. For effective picture...

Self-supervised learning is being prominently used in Artificial Intelligence to develop intelligent systems. The transformer models like BERT and T5 have recently got popular...