Search

Recent years have witnessed a trend that large language model (LLM) based text-to-speech (TTS) emerges into the mainstream due to their high naturalness and zero-shot capacity. In this paradigm, speech signals are discretized into token sequences, which are modeled by an LLM with text as prompts and reconstructed by a token-based vocoder to waveforms. Obviously, speech tokens play a critical role in LLM-based TTS models. Current speech tokens are learned in an unsupervised manner, which lacks explicit semantic information and alignment to the text. In this paper, we propose to represent speech with supervised semantic tokens, which are derived from a multilingual speech recognition model by inserting vector quantization into the encoder. Based on the tokens, we further propose a scalable zero-shot TTS synthesizer, CosyVoice, which consists of an LLM for text-to-token generation and a conditional flow matching model for token-to-speech synthesis. Experimental results show that supervised semantic tokens significantly outperform existing unsupervised tokens in terms of content consistency and speaker similarity for zero-shot voice cloning. Moreover, we find that utilizing large-scale data further improves the synthesis performance, indicating the scalable capacity of CosyVoice. To the best of our knowledge, this is the first attempt to involve supervised speech tokens into TTS models., Comment: work in progress. arXiv admin note: substantial text overlap with arXiv:2407.04051

This report introduces FunAudioLLM, a model family designed to enhance natural voice interactions between humans and large language models (LLMs). At its core are two innovative models: SenseVoice, which handles multilingual speech recognition, emotion recognition, and audio event detection; and CosyVoice, which facilitates natural speech generation with control over multiple languages, timbre, speaking style, and speaker identity. SenseVoice-Small delivers exceptionally low-latency ASR for 5 languages, and SenseVoice-Large supports high-precision ASR for over 50 languages, while CosyVoice excels in multi-lingual voice generation, zero-shot in-context learning, cross-lingual voice cloning, and instruction-following capabilities. The models related to SenseVoice and CosyVoice have been open-sourced on Modelscope and Huggingface, along with the corresponding training, inference, and fine-tuning codes released on GitHub. By integrating these models with LLMs, FunAudioLLM enables applications such as speech-to-speech translation, emotional voice chat, interactive podcasts, and expressive audiobook narration, thereby pushing the boundaries of voice interaction technology. Demos are available at https://fun-audio-llm.github.io, and the code can be accessed at https://github.com/FunAudioLLM., Comment: Work in progress. Authors are listed in alphabetical order by family name

Interlayer magnetic interactions play a pivotal role in determining the magnetic arrangement within van der Waals (vdW) magnets, and the remarkable tunability of these interactions through applied pressure further enhances their significance. Here, we investigate NiI2 flakes, a representative vdW magnet, under hydrostatic pressures up to 11 GPa. We reveal a notable increase in magnetic transition temperatures for both helimagnetic and antiferromagnetic states, and find that a reversible transition from helimagnetic to antiferromagnetic (AFM) phases at approximately 7 GPa challenges established theoretical and experimental expectations. While the increase in transition temperature aligns with pressure-enhanced overall exchange interaction strengths, we identify the significant role of the second-nearest neighbor interlayer interaction, which competes with intra-layer frustration and favors the AFM state as demonstrated in the Monte Carlo simulations. Experimental and simulated results converge on the existence of an intermediate helimagnetic ordered state in NiI2 before transitioning to the AFM state. These findings underscore the pivotal role of interlayer interactions in shaping the magnetic ground state, providing fresh perspectives for innovative applications in nanoscale magnetic device design.

Formal Modelling is often used as part of the design and testing process of software development to ensure that components operate within suitable bounds even in unexpected circumstances. In this paper, we use predictive formal modelling (PFM) at runtime in a human-swarm mission and show that this integration can be used to improve the performance of human-swarm teams. We recruited 60 participants to operate a simulated aerial swarm to deliver parcels to target locations. In the PFM condition, operators were informed of the estimated completion times given the number of drones deployed, whereas in the No-PFM condition, operators did not have this information. The operators could control the mission by adding or removing drones from the mission and thereby, increasing or decreasing the overall mission cost. The evaluation of human-swarm performance relied on four key metrics: the time taken to complete tasks, the number of agents involved, the total number of tasks accomplished, and the overall cost associated with the human-swarm task. Our results show that PFM modelling at runtime improves mission performance without significantly affecting the operator's workload or the system's usability., Comment: This work has been accepted in HRI '24 LBR track. It consist of 5 pages, 2 figures, and 2 tables. This is the author's submitted manuscript, for your personal use. Not for redistribution. The definitive Version of Record will be published in the Companion of the 2024 ACM/IEEE International Conference on Human-Robot Interaction (HRI '24 Companion), https://doi.org/10.1145/3610978.3640725

In supervised speech separation, permutation invariant training (PIT) is widely used to handle label ambiguity by selecting the best permutation to update the model. Despite its success, previous studies showed that PIT is plagued by excessive label assignment switching in adjacent epochs, impeding the model to learn better label assignments. To address this issue, we propose a novel training strategy, dynamic sample dropout (DSD), which considers previous best label assignments and evaluation metrics to exclude the samples that may negatively impact the learned label assignments during training. Additionally, we include layer-wise optimization (LO) to improve the performance by solving layer-decoupling. Our experiments showed that combining DSD and LO outperforms the baseline and solves excessive label assignment switching and layer-decoupling issues. The proposed DSD and LO approach is easy to implement, requires no extra training sets or steps, and shows generality to various speech separation tasks., Comment: Accepted by INTERSPEECH 2023

Large self-supervised models are effective feature extractors, but their application is challenging under on-device budget constraints and biased dataset collection, especially in keyword spotting. To address this, we proposed a knowledge distillation-based self-supervised speech representation learning (S3RL) architecture for on-device keyword spotting. Our approach used a teacher-student framework to transfer knowledge from a larger, more complex model to a smaller, light-weight model using dual-view cross-correlation distillation and the teacher's codebook as learning objectives. We evaluated our model's performance on an Alexa keyword spotting detection task using a 16.6k-hour in-house dataset. Our technique showed exceptional performance in normal and noisy conditions, demonstrating the efficacy of knowledge distillation methods in constructing self-supervised models for keyword spotting tasks while working within on-device resource constraints., Comment: Accepted to Interspeech 2023

Self-supervised speech representation learning (S3RL) is revolutionizing the way we leverage the ever-growing availability of data. While S3RL related studies typically use large models, we employ light-weight networks to comply with tight memory of compute-constrained devices. We demonstrate the effectiveness of S3RL on a keyword-spotting (KS) problem by using transformers with 330k parameters and propose a mechanism to enhance utterance-wise distinction, which proves crucial for improving performance on classification tasks. On the Google speech commands v2 dataset, the proposed method applied to the Auto-Regressive Predictive Coding S3RL led to a 1.2% accuracy improvement compared to training from scratch. On an in-house KS dataset with four different keywords, it provided 6% to 23.7% relative false accept improvement at fixed false reject rate. We argue this demonstrates the applicability of S3RL approaches to light-weight models for KS and confirms S3RL is a powerful alternative to traditional supervised learning for resource-constrained applications.

The research on two-dimensional (2D) van der Waals (vdW) ferromagnets has promoted the development of ultrahigh-density and nanoscale data storage. However, intrinsic ferromagnetism in layered magnets is always subject to many factors, such as stacking orders, interlayer couplings, and the number of layers. Here, we report a magnetic transition from soft to hard ferromagnetic behaviors as the thickness of CrSiTe$_3$ flakes decreases down to several nanometers. Phenomenally, in contrast to the negligible hysteresis loop in the bulk counterparts, atomically thin CrSiTe$_3$ shows a rectangular loop with finite magnetization and coercivity as thickness decreases down to ~8 nm, indicative of a single-domain and out-of-plane ferromagnetic order. We find that the stray field is weakened with decreasing thickness, which suppresses the formation of the domain wall. In addition, thickness-dependent ferromagnetic properties also reveal a crossover from 3 dimensional to 2 dimensional Ising ferromagnets at a ~7 nm thickness of CrSiTe$_3$, accompanied by a drop of the Curie temperature from 33 K for bulk to ~17 K for 4 nm sample.