Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Recent advancements in large language models (LLMs) have driven significant progress in zero-shot text-to-speech (TTS) synthesis. However, existing foundation models rely on multi-stage processing or complex architectures for predicting multiple codebooks, limiting efficiency and integration flexibility. To overcome these challenges, we introduce Spark-TTS, a novel system powered by BiCodec, a single-stream speech codec that decomposes speech into two complementary token types: low-bitrate semantic tokens for linguistic content and fixed-length global tokens for speaker attributes. This disentangled representation, combined with the Qwen2.5 LLM and a chain-of-thought (CoT) generation approach, enables both coarse-grained control (e.g., gender, speaking style) and fine-grained adjustments (e.g., precise pitch values, speaking rate). To facilitate research in controllable TTS, we introduce VoxBox, a meticulously curated 100,000-hour dataset with comprehensive attribute annotations. Extensive experiments demonstrate that Spark-TTS not only achieves state-of-the-art zero-shot voice cloning but also generates highly customizable voices that surpass the limitations of reference-based synthesis. Source code, pre-trained models, and audio samples are available at https://github.com/SparkAudio/Spark-TTS.

Performance Analysis of Local Partial MMSE Precoding Based User-Centric Cell-Free Massive MIMO Systems and Deployment Optimization

Cell-free massive multiple-input multiple-output (MIMO) systems, leveraging tight cooperation among wireless access points, exhibit remarkable signal enhancement and interference suppression capabilities, demonstrating significant performance advantages over traditional cellular networks. This paper investigates the performance and deployment optimization of a user-centric scalable cell-free massive MIMO system with imperfect channel information over correlated Rayleigh fading channels. Based on the large-dimensional random matrix theory, this paper presents the deterministic equivalent of the ergodic sum rate for this system when applying the local partial minimum mean square error (LP-MMSE) precoding method, along with its derivative with respect to the channel correlation matrix. Furthermore, utilizing the derivative of the ergodic sum rate, this paper designs a Barzilai-Borwein based gradient descent method to improve system deployment. Simulation experiments demonstrate that under various parameter settings and large-scale antenna configurations, the deterministic equivalent of the ergodic sum rate accurately approximates the Monte Carlo ergodic sum rate of the system. Furthermore, the deployment optimization algorithm effectively enhances the ergodic sum rate of this system by optimizing the positions of access points.

M-Vec: Matryoshka Speaker Embeddings with Flexible Dimensions

Fixed-dimensional speaker embeddings have become the dominant approach in speaker modeling, typically spanning hundreds to thousands of dimensions. These dimensions are hyperparameters that are not specifically picked, nor are they hierarchically ordered in terms of importance. In large-scale speaker representation databases, reducing the dimensionality of embeddings can significantly lower storage and computational costs. However, directly training low-dimensional representations often yields suboptimal performance. In this paper, we introduce the Matryoshka speaker embedding, a method that allows dynamic extraction of sub-dimensions from the embedding while maintaining performance. Our approach is validated on the VoxCeleb dataset, demonstrating that it can achieve extremely low-dimensional embeddings, such as 8 dimensions, while preserving high speaker verification performance.

MacST: Multi-Accent Speech Synthesis via Text Transliteration for Accent Conversion

In accented voice conversion or accent conversion, we seek to convert the accent in speech from one another while preserving speaker identity and semantic content. In this study, we formulate a novel method for creating multi-accented speech samples, thus pairs of accented speech samples by the same speaker, through text transliteration for training accent conversion systems. We begin by generating transliterated text with Large Language Models (LLMs), which is then fed into multilingual TTS models to synthesize accented English speech. As a reference system, we built a sequence-to-sequence model on the synthetic parallel corpus for accent conversion. We validated the proposed method for both native and non-native English speakers. Subjective and objective evaluations further validate our dataset's effectiveness in accent conversion studies.

E1 TTS: Simple and Fast Non-Autoregressive TTS

This paper introduces Easy One-Step Text-to-Speech (E1 TTS), an efficient non-autoregressive zero-shot text-to-speech system based on denoising diffusion pretraining and distribution matching distillation. The training of E1 TTS is straightforward; it does not require explicit monotonic alignment between the text and audio pairs. The inference of E1 TTS is efficient, requiring only one neural network evaluation for each utterance. Despite its sampling efficiency, E1 TTS achieves naturalness and speaker similarity comparable to various strong baseline models. Audio samples are available at http://e1tts.github.io/ .

Mini-Slot-Assisted Short Packet URLLC:Differential or Coherent Detection?

One of the primary challenges in short packet ultra-reliable and low-latency communications (URLLC) is to achieve reliable channel estimation and data detection while minimizing the impact on latency performance. Given the small packet size in mini-slot-assisted URLLC, relying solely on pilot-based coherent detection is almost impossible to meet the seemingly contradictory requirements of high channel estimation accuracy, high reliability, low training overhead, and low latency. In this paper, we explore differential modulation both in the frequency domain and in the time domain, and propose adopting an adaptive approach that integrates both differential and coherent detection to achieve mini-slot-assisted short packet URLLC, striking a balance among training overhead, system performance, and computational complexity. Specifically, differential (especially in the frequency domain) and coherent detection schemes can be dynamically activated based on application scenarios, channel statistics, information payloads, mini-slot deployment options, and service requirements. Furthermore, we derive the block error rate (BLER) for pilot-based, frequency domain, and time domain differential OFDM using non-asymptotic information-theoretic bounds. Simulation results validate the feasibility and effectiveness of adaptive differential and coherent detection.

DualVC 3: Leveraging Language Model Generated Pseudo Context for End-to-end Low Latency Streaming Voice Conversion

Streaming voice conversion has become increasingly popular for its potential in real-time applications. The recently proposed DualVC 2 has achieved robust and high-quality streaming voice conversion with a latency of about 180ms. Nonetheless, the recognition-synthesis framework hinders end-to-end optimization, and the instability of automatic speech recognition (ASR) model with short chunks makes it challenging to further reduce latency. To address these issues, we propose an end-to-end model, DualVC 3. With speaker-independent semantic tokens to guide the training of the content encoder, the dependency on ASR is removed and the model can operate under extremely small chunks, with cascading errors eliminated. A language model is trained on the content encoder output to produce pseudo context by iteratively predicting future frames, providing more contextual information for the decoder to improve conversion quality. Experimental results demonstrate that DualVC 3 achieves comparable performance to DualVC 2 in subjective and objective metrics, with a latency of only 50 ms.

MGS-SLAM: Monocular Sparse Tracking and Gaussian Mapping with Depth Smooth Regularization

This letter introduces a novel framework for dense Visual Simultaneous Localization and Mapping (VSLAM) based on Gaussian Splatting. Recently Gaussian Splatting-based SLAM has yielded promising results, but rely on RGB-D input and is weak in tracking. To address these limitations, we uniquely integrates advanced sparse visual odometry with a dense Gaussian Splatting scene representation for the first time, thereby eliminating the dependency on depth maps typical of Gaussian Splatting-based SLAM systems and enhancing tracking robustness. Here, the sparse visual odometry tracks camera poses in RGB stream, while Gaussian Splatting handles map reconstruction. These components are interconnected through a Multi-View Stereo (MVS) depth estimation network. And we propose a depth smooth loss to reduce the negative effect of estimated depth maps. Furthermore, the consistency in scale between the sparse visual odometry and the dense Gaussian map is preserved by Sparse-Dense Adjustment Ring (SDAR). We have evaluated our system across various synthetic and real-world datasets. The accuracy of our pose estimation surpasses existing methods and achieves state-of-the-art performance. Additionally, it outperforms previous monocular methods in terms of novel view synthesis fidelity, matching the results of neural SLAM systems that utilize RGB-D input.

Trainable Joint Channel Estimation, Detection and Decoding for MIMO URLLC Systems

The receiver design for multi-input multi-output (MIMO) ultra-reliable and low-latency communication (URLLC) systems can be a tough task due to the use of short channel codes and few pilot symbols. Consequently, error propagation can occur in traditional turbo receivers, leading to performance degradation. Moreover, the processing delay induced by information exchange between different modules may also be undesirable for URLLC. To address the issues, we advocate to perform joint channel estimation, detection, and decoding (JCDD) for MIMO URLLC systems encoded by short low-density parity-check (LDPC) codes. Specifically, we develop two novel JCDD problem formulations based on the maximum a posteriori (MAP) criterion for Gaussian MIMO channels and sparse mmWave MIMO channels, respectively, which integrate the pilots, the bit-to-symbol mapping, the LDPC code constraints, as well as the channel statistical information. Both the challenging large-scale non-convex problems are then solved based on the alternating direction method of multipliers (ADMM) algorithms, where closed-form solutions are achieved in each ADMM iteration. Furthermore, two JCDD neural networks, called JCDDNet-G and JCDDNet-S, are built by unfolding the derived ADMM algorithms and introducing trainable parameters. It is interesting to find via simulations that the proposed trainable JCDD receivers can outperform the turbo receivers with affordable computational complexities.

Accent-VITS:accent transfer for end-to-end TTS

Accent transfer aims to transfer an accent from a source speaker to synthetic speech in the target speaker's voice. The main challenge is how to effectively disentangle speaker timbre and accent which are entangled in speech. This paper presents a VITS-based end-to-end accent transfer model named Accent-VITS.Based on the main structure of VITS, Accent-VITS makes substantial improvements to enable effective and stable accent transfer.We leverage a hierarchical CVAE structure to model accent pronunciation information and acoustic features, respectively, using bottleneck features and mel spectrums as constraints.Moreover, the text-to-wave mapping in VITS is decomposed into text-to-accent and accent-to-wave mappings in Accent-VITS. In this way, the disentanglement of accent and speaker timbre becomes be more stable and effective.Experiments on multi-accent and Mandarin datasets show that Accent-VITS achieves higher speaker similarity, accent similarity and speech naturalness as compared with a strong baseline.