CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models

In our previous work, we introduced CosyVoice, a multilingual speech synthesis model based on supervised discrete speech tokens. By employing progressive semantic decoding with two popular generative models, language models (LMs) and Flow Matching, CosyVoice demonstrated high prosody naturalness, content consistency, and speaker similarity in speech in-context learning. Recently, significant progress has been made in multi-modal large language models (LLMs), where the response latency and real-time factor of speech synthesis play a crucial role in the interactive experience. Therefore, in this report, we present an improved streaming speech synthesis model, CosyVoice 2, which incorporates comprehensive and systematic optimizations. Specifically, we introduce finite-scalar quantization to improve the codebook utilization of speech tokens. For the text-speech LM, we streamline the model architecture to allow direct use of a pre-trained LLM as the backbone. In addition, we develop a chunk-aware causal flow matching model to support various synthesis scenarios, enabling both streaming and non-streaming synthesis within a single model. By training on a large-scale multilingual dataset, CosyVoice 2 achieves human-parity naturalness, minimal response latency, and virtually lossless synthesis quality in the streaming mode. We invite readers to listen to the demos at https://funaudiollm.github.io/cosyvoice2.

FlashAudio: Rectified Flows for Fast and High-Fidelity Text-to-Audio Generation

Recent advancements in latent diffusion models (LDMs) have markedly enhanced text-to-audio generation, yet their iterative sampling processes impose substantial computational demands, limiting practical deployment. While recent methods utilizing consistency-based distillation aim to achieve few-step or single-step inference, their one-step performance is constrained by curved trajectories, preventing them from surpassing traditional diffusion models. In this work, we introduce FlashAudio with rectified flows to learn straight flow for fast simulation. To alleviate the inefficient timesteps allocation and suboptimal distribution of noise, FlashAudio optimizes the time distribution of rectified flow with Bifocal Samplers and proposes immiscible flow to minimize the total distance of data-noise pairs in a batch vias assignment. Furthermore, to address the amplified accumulation error caused by the classifier-free guidance (CFG), we propose Anchored Optimization, which refines the guidance scale by anchoring it to a reference trajectory. Experimental results on text-to-audio generation demonstrate that FlashAudio's one-step generation performance surpasses the diffusion-based models with hundreds of sampling steps on audio quality and enables a sampling speed of 400x faster than real-time on a single NVIDIA 4090Ti GPU.

Both Ears Wide Open: Towards Language-Driven Spatial Audio Generation

Recently, diffusion models have achieved great success in mono-channel audio generation. However, when it comes to stereo audio generation, the soundscapes often have a complex scene of multiple objects and directions. Controlling stereo audio with spatial contexts remains challenging due to high data costs and unstable generative models. To the best of our knowledge, this work represents the first attempt to address these issues. We first construct a large-scale, simulation-based, and GPT-assisted dataset, BEWO-1M, with abundant soundscapes and descriptions even including moving and multiple sources. Beyond text modality, we have also acquired a set of images and rationally paired stereo audios through retrieval to advance multimodal generation. Existing audio generation models tend to generate rather random and indistinct spatial audio. To provide accurate guidance for latent diffusion models, we introduce the SpatialSonic model utilizing spatial-aware encoders and azimuth state matrices to reveal reasonable spatial guidance. By leveraging spatial guidance, our unified model not only achieves the objective of generating immersive and controllable spatial audio from text and image but also enables interactive audio generation during inference. Finally, under fair settings, we conduct subjective and objective evaluations on simulated and real-world data to compare our approach with prevailing methods. The results demonstrate the effectiveness of our method, highlighting its capability to generate spatial audio that adheres to physical rules.

MEDIC: Zero-shot Music Editing with Disentangled Inversion Control

Text-guided diffusion models catalyze a paradigm shift in audio generation, facilitating the adaptability of source audio to conform to specific textual prompts. Recent advancements introduce inversion techniques, like DDIM inversion, to zero-shot editing, exploiting pre-trained diffusion models for audio modification. Nonetheless, our investigation exposes that DDIM inversion suffers from an accumulation of errors across each diffusion step, undermining its efficacy. And the lack of attention control hinders the fine-grained manipulations of music. To counteract these limitations, we introduce the \textit{Disentangled Inversion} technique, which is designed to disentangle the diffusion process into triple branches, thereby magnifying their individual capabilities for both precise editing and preservation. Furthermore, we propose the \textit{Harmonized Attention Control} framework, which unifies the mutual self-attention and cross-attention with an additional Harmonic Branch to achieve the desired composition and structural information in the target music. Collectively, these innovations comprise the \textit{Disentangled Inversion Control (DIC)} framework, enabling accurate music editing whilst safeguarding structural integrity. To benchmark audio editing efficacy, we introduce \textit{ZoME-Bench}, a comprehensive music editing benchmark hosting 1,100 samples spread across 10 distinct editing categories, which facilitates both zero-shot and instruction-based music editing tasks. Our method demonstrates unparalleled performance in edit fidelity and essential content preservation, outperforming contemporary state-of-the-art inversion techniques.

AudioLCM: Text-to-Audio Generation with Latent Consistency Models

Recent advancements in Latent Diffusion Models (LDMs) have propelled them to the forefront of various generative tasks. However, their iterative sampling process poses a significant computational burden, resulting in slow generation speeds and limiting their application in text-to-audio generation deployment. In this work, we introduce AudioLCM, a novel consistency-based model tailored for efficient and high-quality text-to-audio generation. AudioLCM integrates Consistency Models into the generation process, facilitating rapid inference through a mapping from any point at any time step to the trajectory's initial point. To overcome the convergence issue inherent in LDMs with reduced sample iterations, we propose the Guided Latent Consistency Distillation with a multi-step Ordinary Differential Equation (ODE) solver. This innovation shortens the time schedule from thousands to dozens of steps while maintaining sample quality, thereby achieving fast convergence and high-quality generation. Furthermore, to optimize the performance of transformer-based neural network architectures, we integrate the advanced techniques pioneered by LLaMA into the foundational framework of transformers. This architecture supports stable and efficient training, ensuring robust performance in text-to-audio synthesis. Experimental results on text-to-sound generation and text-to-music synthesis tasks demonstrate that AudioLCM needs only 2 iterations to synthesize high-fidelity audios, while it maintains sample quality competitive with state-of-the-art models using hundreds of steps. AudioLCM enables a sampling speed of 333x faster than real-time on a single NVIDIA 4090Ti GPU, making generative models practically applicable to text-to-audio generation deployment. Our extensive preliminary analysis shows that each design in AudioLCM is effective.

AV-TranSpeech: Audio-Visual Robust Speech-to-Speech Translation

Direct speech-to-speech translation (S2ST) aims to convert speech from one language into another, and has demonstrated significant progress to date. Despite the recent success, current S2ST models still suffer from distinct degradation in noisy environments and fail to translate visual speech (i.e., the movement of lips and teeth). In this work, we present AV-TranSpeech, the first audio-visual speech-to-speech (AV-S2ST) translation model without relying on intermediate text. AV-TranSpeech complements the audio stream with visual information to promote system robustness and opens up a host of practical applications: dictation or dubbing archival films. To mitigate the data scarcity with limited parallel AV-S2ST data, we 1) explore self-supervised pre-training with unlabeled audio-visual data to learn contextual representation, and 2) introduce cross-modal distillation with S2ST models trained on the audio-only corpus to further reduce the requirements of visual data. Experimental results on two language pairs demonstrate that AV-TranSpeech outperforms audio-only models under all settings regardless of the type of noise. With low-resource audio-visual data (10h, 30h), cross-modal distillation yields an improvement of 7.6 BLEU on average compared with baselines. Audio samples are available at https://AV-TranSpeech.github.io

ViT-TTS: Visual Text-to-Speech with Scalable Diffusion Transformer

Text-to-speech(TTS) has undergone remarkable improvements in performance, particularly with the advent of Denoising Diffusion Probabilistic Models (DDPMs). However, the perceived quality of audio depends not solely on its content, pitch, rhythm, and energy, but also on the physical environment. In this work, we propose ViT-TTS, the first visual TTS model with scalable diffusion transformers. ViT-TTS complement the phoneme sequence with the visual information to generate high-perceived audio, opening up new avenues for practical applications of AR and VR to allow a more immersive and realistic audio experience. To mitigate the data scarcity in learning visual acoustic information, we 1) introduce a self-supervised learning framework to enhance both the visual-text encoder and denoiser decoder; 2) leverage the diffusion transformer scalable in terms of parameters and capacity to learn visual scene information. Experimental results demonstrate that ViT-TTS achieves new state-of-the-art results, outperforming cascaded systems and other baselines regardless of the visibility of the scene. With low-resource data (1h, 2h, 5h), ViT-TTS achieves comparative results with rich-resource baselines.~\footnote{Audio samples are available at \url{https://ViT-TTS.github.io/.}}

Wav2SQL: Direct Generalizable Speech-To-SQL Parsing

Speech-to-SQL (S2SQL) aims to convert spoken questions into SQL queries given relational databases, which has been traditionally implemented in a cascaded manner while facing the following challenges: 1) model training is faced with the major issue of data scarcity, where limited parallel data is available; and 2) the systems should be robust enough to handle diverse out-of-domain speech samples that differ from the source data. In this work, we propose the first direct speech-to-SQL parsing model Wav2SQL which avoids error compounding across cascaded systems. Specifically, 1) to accelerate speech-driven SQL parsing research in the community, we release a large-scale and multi-speaker dataset MASpider; 2) leveraging the recent progress in the large-scale pre-training, we show that it alleviates the data scarcity issue and allow for direct speech-to-SQL parsing; and 3) we include the speech re-programming and gradient reversal classifier techniques to reduce acoustic variance and learned style-agnostic representation, improving generalization to unseen out-of-domain custom data. Experimental results demonstrate that Wav2SQL avoids error compounding and achieves state-of-the-art results by up to 2.5\% accuracy improvement over the baseline.

RMSSinger: Realistic-Music-Score based Singing Voice Synthesis

We are interested in a challenging task, Realistic-Music-Score based Singing Voice Synthesis (RMS-SVS). RMS-SVS aims to generate high-quality singing voices given realistic music scores with different note types (grace, slur, rest, etc.). Though significant progress has been achieved, recent singing voice synthesis (SVS) methods are limited to fine-grained music scores, which require a complicated data collection pipeline with time-consuming manual annotation to align music notes with phonemes. Furthermore, these manual annotation destroys the regularity of note durations in music scores, making fine-grained music scores inconvenient for composing. To tackle these challenges, we propose RMSSinger, the first RMS-SVS method, which takes realistic music scores as input, eliminating most of the tedious manual annotation and avoiding the aforementioned inconvenience. Note that music scores are based on words rather than phonemes, in RMSSinger, we introduce word-level modeling to avoid the time-consuming phoneme duration annotation and the complicated phoneme-level mel-note alignment. Furthermore, we propose the first diffusion-based pitch modeling method, which ameliorates the naturalness of existing pitch-modeling methods. To achieve these, we collect a new dataset containing realistic music scores and singing voices according to these realistic music scores from professional singers. Extensive experiments on the dataset demonstrate the effectiveness of our methods. Audio samples are available at https://rmssinger.github.io/.

ProDiff: Progressive Fast Diffusion Model For High-Quality Text-to-Speech

Denoising diffusion probabilistic models (DDPMs) have recently achieved leading performances in many generative tasks. However, the inherited iterative sampling process costs hinder their applications to text-to-speech deployment. Through the preliminary study on diffusion model parameterization, we find that previous gradient-based TTS models require hundreds or thousands of iterations to guarantee high sample quality, which poses a challenge for accelerating sampling. In this work, we propose ProDiff, on progressive fast diffusion model for high-quality text-to-speech. Unlike previous work estimating the gradient for data density, ProDiff parameterizes the denoising model by directly predicting clean data to avoid distinct quality degradation in accelerating sampling. To tackle the model convergence challenge with decreased diffusion iterations, ProDiff reduces the data variance in the target site via knowledge distillation. Specifically, the denoising model uses the generated mel-spectrogram from an N-step DDIM teacher as the training target and distills the behavior into a new model with N/2 steps. As such, it allows the TTS model to make sharp predictions and further reduces the sampling time by orders of magnitude. Our evaluation demonstrates that ProDiff needs only 2 iterations to synthesize high-fidelity mel-spectrograms, while it maintains sample quality and diversity competitive with state-of-the-art models using hundreds of steps. ProDiff enables a sampling speed of 24x faster than real-time on a single NVIDIA 2080Ti GPU, making diffusion models practically applicable to text-to-speech synthesis deployment for the first time. Our extensive ablation studies demonstrate that each design in ProDiff is effective, and we further show that ProDiff can be easily extended to the multi-speaker setting. Audio samples are available at \url{https://ProDiff.github.io/.}